{"meta":{"query_hash":"74abc49c2ae7","filters":{"venue":"Computerized Medical Imaging and Graphics"},"cohort_total":166,"direct_labels_cover":0,"predictions_cover":166,"exported":166,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/74abc49c2ae7","api":"https://metacan.xera.ac/api/v1/cohort?venue=Computerized+Medical+Imaging+and+Graphics"},"results":[{"id":"W1963503100","doi":"10.1016/j.compmedimag.2006.05.001","title":"Medical imaging and graphics in SIBGRAPI/SIACG","year":2006,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Connaught Fund; University of Toronto; University of Manchester; University of East Anglia","keywords":"Computer graphics (images); Computer science; Graphics; Medical imaging; Computer graphics; Computer vision; Artificial intelligence; Medical physics; Medicine","score_opus":0.010790875932430206,"score_gpt":0.29420125886350273,"score_spread":0.2834103829310725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963503100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4971769,0.011845278,0.20857713,0.2772705,0.00064966053,0.0012436361,0.000019712608,0.001419149,0.001798089],"genre_scores_gemma":[0.9627371,0.0053228014,0.013874168,0.017129239,0.00063639204,0.000075562624,0.000108148146,0.00006497222,0.000051641386],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99651694,0.00011599718,0.0007800554,0.0007340674,0.001211847,0.00064109947],"domain_scores_gemma":[0.9978831,0.00038790517,0.000116584415,0.00043972925,0.00011570925,0.0010570135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013147797,0.00036219874,0.0006717018,0.0005193698,0.00019612812,0.00009552384,0.00028349328,0.00024365417,0.000084164996],"category_scores_gemma":[0.0004316785,0.00031235395,0.00013272848,0.00078139384,0.001585523,0.0001240624,0.0003192927,0.0012736027,0.0000029533248],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001599885,0.0016283846,0.42898732,0.0009674008,0.0001044284,0.0037104061,0.0003349699,4.0095247e-7,0.0020660278,0.1235127,0.08711584,0.35141212],"study_design_scores_gemma":[0.011325991,0.00010962015,0.14000799,0.0035252054,0.0002345912,0.005277684,0.00013792442,0.62647444,0.00019595634,0.046255805,0.1652363,0.0012185132],"about_ca_topic_score_codex":0.00050673285,"about_ca_topic_score_gemma":0.000030448562,"teacher_disagreement_score":0.626474,"about_ca_system_score_codex":0.000024165753,"about_ca_system_score_gemma":0.0002154155,"threshold_uncertainty_score":0.9999328},"labels":[],"label_agreement":null},{"id":"W1963639442","doi":"10.1016/j.compmedimag.2007.07.006","title":"A 3D visualization tool for the design and customization of spinal braces","year":2007,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Scoliosis diagnosis and treatment","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Canadian Institutes of Health Research; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Brace; Visualization; Trunk; Computer science; Personalization; Plan (archaeology); Floor plan; Engineering drawing; Engineering; Artificial intelligence; Mechanical engineering; Geology","score_opus":0.025699161332166813,"score_gpt":0.34070160754169787,"score_spread":0.31500244620953105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963639442","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1254536,0.0033389179,0.86890626,0.0017155942,0.000110619396,0.00044447207,0.0000011456085,0.000023922259,0.0000054650195],"genre_scores_gemma":[0.97944504,0.0021269582,0.016899345,0.0013769591,0.00010988079,0.000021049364,0.00000778464,0.000009674277,0.0000032812063],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928576,0.000029610757,0.00021035584,0.0001420672,0.00021293446,0.00011926406],"domain_scores_gemma":[0.9990974,0.00056199613,0.00006766343,0.00008398223,0.00009326847,0.00009569919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006382025,0.00008294701,0.00017756094,0.000089845,0.00009414305,0.00002172998,0.00003477491,0.000045450324,0.0000044729927],"category_scores_gemma":[0.00021050603,0.00005218908,0.000036518897,0.00015258093,0.00017552715,0.00003818278,0.000025942232,0.00005575425,1.00023065e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011919884,0.0005778883,0.124029376,0.0005182143,0.00026823164,0.000037934642,0.0006148244,0.000010043871,0.0007181877,0.0071701896,0.0016792531,0.86318386],"study_design_scores_gemma":[0.009972527,0.0007455257,0.38507664,0.0012176976,0.00049008604,0.00021848943,0.00009176433,0.5942911,0.0018962761,0.0005820633,0.0052085943,0.0002092389],"about_ca_topic_score_codex":0.0000072739513,"about_ca_topic_score_gemma":9.832843e-7,"teacher_disagreement_score":0.86297464,"about_ca_system_score_codex":0.0000063594753,"about_ca_system_score_gemma":0.000037155267,"threshold_uncertainty_score":0.21282089},"labels":[],"label_agreement":null},{"id":"W1965258612","doi":"10.1016/j.compmedimag.2011.02.004","title":"Spino-pelvic postural changes between the standing and sitting human position: Proposal of a method for its systematic analysis","year":2011,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Scoliosis diagnosis and treatment","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Université de Montréal","funders":"","keywords":"Pelvis; Sitting; Scoliosis; Asymptomatic; Spinal Curvatures; Kinematics; Position (finance); Radiography; Computer science; Medicine; Physical medicine and rehabilitation; Orthodontics; Low back pain; Back pain; Photogrammetry; Pelvic tilt; Computer vision; Anatomy; Radiology; Surgery; Physics; Pathology","score_opus":0.05442437929469909,"score_gpt":0.3546347903138812,"score_spread":0.3002104110191821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965258612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9413077,0.0052532754,0.044801705,0.0070468835,0.000094965006,0.0013902276,0.000016565431,0.00006031118,0.000028335375],"genre_scores_gemma":[0.9876209,0.00015015004,0.011422215,0.0005808167,0.000117935895,0.00007002809,0.00002339354,0.000012046313,0.0000024982073],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987002,0.00015195935,0.00036947362,0.0002571932,0.0003192062,0.00020196044],"domain_scores_gemma":[0.99879104,0.0005207183,0.00018687951,0.00017077506,0.0001354833,0.00019512934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009942646,0.00016042523,0.0007132857,0.00024920187,0.00021450984,0.000035851837,0.000085976506,0.000060641563,0.000005393713],"category_scores_gemma":[0.00013111644,0.000094883464,0.00014868962,0.00036964542,0.00015436391,0.00004128206,0.00007314137,0.0001284542,1.1155246e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028459696,0.0008686572,0.89387774,0.037412886,0.01238914,0.0002087847,0.013885004,3.2019227e-7,0.0041432604,0.020062977,0.00019955749,0.016667075],"study_design_scores_gemma":[0.009272554,0.0016380587,0.88118184,0.019639825,0.023974396,0.00042945263,0.0018560091,0.05421241,0.0047457106,0.0024403727,0.00002761645,0.0005817309],"about_ca_topic_score_codex":0.000036499816,"about_ca_topic_score_gemma":0.000006873264,"teacher_disagreement_score":0.05421209,"about_ca_system_score_codex":0.000014180775,"about_ca_system_score_gemma":0.000030038462,"threshold_uncertainty_score":0.38692352},"labels":[],"label_agreement":null},{"id":"W1968694013","doi":"10.1016/j.compmedimag.2006.07.003","title":"Multistage graph-based segmentation of thoracoscopic images","year":2006,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Thresholding; Computer science; Segmentation; Computer vision; Pattern recognition (psychology); Smoothing; Image segmentation; Cut; Histogram; Image (mathematics)","score_opus":0.005010055227317554,"score_gpt":0.23771777689836465,"score_spread":0.23270772167104709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968694013","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16658495,0.0021235694,0.8296322,0.000691935,0.00030971132,0.00007803324,0.000013892847,0.00032814444,0.0002375636],"genre_scores_gemma":[0.98358583,0.00027473024,0.0155919865,0.00031443618,0.000118098236,0.0000073412807,0.00006889907,0.000022530976,0.000016136846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876934,0.000052468306,0.00035584992,0.0001919358,0.0004075216,0.0002228559],"domain_scores_gemma":[0.99941516,0.00014937323,0.000050947412,0.00015816888,0.00004933368,0.00017701717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002771979,0.00016168768,0.0002874596,0.00022947218,0.00006169828,0.00004009689,0.00013214718,0.000060263654,0.000033604487],"category_scores_gemma":[0.000041882282,0.00014554246,0.00009170067,0.00034145173,0.000337426,0.00007350528,0.000026953272,0.00021761717,0.0000014047029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030743176,0.00068558916,0.14516719,0.0033255822,0.0003948545,0.00046748164,0.0003050653,0.005147501,0.11721914,0.0026727007,0.032098416,0.69248575],"study_design_scores_gemma":[0.0015831884,0.000012085151,0.0085581085,0.0003214651,0.00008324176,0.000011675298,0.00002775515,0.97904724,0.007613255,0.0011686549,0.001304525,0.00026878534],"about_ca_topic_score_codex":0.00009181092,"about_ca_topic_score_gemma":0.0000026750904,"teacher_disagreement_score":0.9738998,"about_ca_system_score_codex":0.0000076034416,"about_ca_system_score_gemma":0.000021399785,"threshold_uncertainty_score":0.59350497},"labels":[],"label_agreement":null},{"id":"W1969334396","doi":"10.1016/j.compmedimag.2012.02.001","title":"A comparison of a Monte Carlo-based detection probability matrix with analytical probability matrix for small animal PET scanners","year":2012,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Nuclear Physics; Université Hassan II de Casablanca; Université Paris Diderot; Université de Montréal; Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke; Université du Québec à Chicoutimi","keywords":"Monte Carlo method; Photon; Matrix (chemical analysis); Probability distribution; Contrast (vision); Signal-to-noise ratio (imaging); Positron emission tomography; Statistical physics; Measure (data warehouse); Noise (video); Computer science; Probabilistic logic; Physics; Computational physics; Algorithm; Mathematics; Optics; Statistics; Artificial intelligence; Nuclear medicine; Image (mathematics); Materials science; Data mining","score_opus":0.04132836798912786,"score_gpt":0.36209123535745896,"score_spread":0.3207628673683311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969334396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67600447,0.00023195898,0.31701082,0.005353483,0.00005787341,0.0011022626,0.000015957374,0.00020674933,0.000016414882],"genre_scores_gemma":[0.8590737,0.000013528116,0.14022134,0.00032900483,0.00013859366,0.00016868596,0.000024436682,0.000024524663,0.000006212963],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977353,0.00010457211,0.0006480164,0.00045992312,0.00055275095,0.00049942324],"domain_scores_gemma":[0.9978658,0.00036314674,0.00019660717,0.00044114757,0.00031362622,0.00081968354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012556448,0.00025893038,0.00073659356,0.0001602401,0.0001380539,0.000028932882,0.00016531993,0.000121344594,0.00001143146],"category_scores_gemma":[0.0004906263,0.00019781136,0.00018521296,0.0004309595,0.0010144191,0.000075152544,0.00008302353,0.0005042596,4.1439606e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0057624145,0.008306338,0.8913324,0.00844823,0.00047811662,0.000048061323,0.0007759067,0.00004245927,0.008446799,0.013696526,0.003030014,0.05963275],"study_design_scores_gemma":[0.0038803138,0.00071341416,0.022147927,0.0005635525,0.0004687634,0.00021309516,0.0000588495,0.9668111,0.0013514548,0.0009174664,0.0025493249,0.00032469374],"about_ca_topic_score_codex":0.0000800379,"about_ca_topic_score_gemma":0.000009233718,"teacher_disagreement_score":0.9667687,"about_ca_system_score_codex":0.000053657564,"about_ca_system_score_gemma":0.00022786418,"threshold_uncertainty_score":0.8066513},"labels":[],"label_agreement":null},{"id":"W1971780140","doi":"10.1016/s0895-6111(00)00044-6","title":"Automated three-dimensional quantification of myocardial perfusion and brain SPECT","year":2001,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"","keywords":"Voxel; Computer science; Image registration; Artificial intelligence; Computer vision; Nuclear medicine; Positron emission tomography; Tomography; Data set; Pattern recognition (psychology); Radiology; Medical physics; Medicine; Image (mathematics)","score_opus":0.02006385805137147,"score_gpt":0.309038761853214,"score_spread":0.28897490380184254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971780140","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85846597,0.0008123035,0.07018629,0.069330744,0.00015041025,0.00033381136,0.0000057258685,0.00059008424,0.00012463258],"genre_scores_gemma":[0.9818246,0.0006274898,0.014101947,0.0031660406,0.00015972837,0.000012379431,0.00006420946,0.00001722939,0.000026373995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986602,0.000045990895,0.000339584,0.0003129664,0.00045507328,0.00018620779],"domain_scores_gemma":[0.9989927,0.00021439117,0.000085967025,0.0002419196,0.00009829938,0.00036673128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052970153,0.00013851082,0.00033161772,0.00014752595,0.000109041226,0.000020318017,0.00008223545,0.00008305102,0.00004950989],"category_scores_gemma":[0.00021151376,0.00011288595,0.00006641761,0.00028501352,0.0005989312,0.000044939505,0.00011617584,0.00027704253,0.0000015559726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062512327,0.0014414052,0.16216542,0.00073786546,0.00023981591,0.0006396337,0.00029543974,0.000003867702,0.16139038,0.03790438,0.12832522,0.5062314],"study_design_scores_gemma":[0.0022129407,0.00010454984,0.087259345,0.0005716143,0.00009110099,0.0013810736,0.0000090573885,0.8872015,0.00045355756,0.0022533264,0.01826669,0.00019522835],"about_ca_topic_score_codex":0.00006413961,"about_ca_topic_score_gemma":0.000001648461,"teacher_disagreement_score":0.8871977,"about_ca_system_score_codex":0.000007674454,"about_ca_system_score_gemma":0.000073103256,"threshold_uncertainty_score":0.46033555},"labels":[],"label_agreement":null},{"id":"W1972519108","doi":"10.1016/s0895-6111(00)00075-6","title":"A multiscale optimization approach for the dynamic contour-based boundary detection issue","year":2001,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Active contour model; Computer science; Segmentation; Image segmentation; Energy minimization; Context (archaeology); Boundary (topology); Minification; Mathematical optimization; Artificial intelligence; Algorithm; Mathematics","score_opus":0.01143591766278341,"score_gpt":0.2803534942312576,"score_spread":0.2689175765684742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972519108","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011024747,0.0006291906,0.9923386,0.0054839603,0.00042648034,0.000519247,0.0000021724577,0.00045890134,0.000031173706],"genre_scores_gemma":[0.03907436,0.00051616924,0.9524718,0.0074918126,0.00017136506,0.00018013407,0.00003622969,0.000020478219,0.000037666392],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998345,0.00012938214,0.00031371642,0.0004257391,0.00049884286,0.00028731037],"domain_scores_gemma":[0.99862367,0.00052458205,0.00010965734,0.0003627233,0.00013696833,0.00024238188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008512908,0.00017181538,0.00020041082,0.00014289464,0.00042859465,0.00031800425,0.0005939521,0.00009434905,0.0000136570525],"category_scores_gemma":[0.00025180486,0.000127509,0.00008488125,0.00040822232,0.00043528544,0.00028738444,0.00014365817,0.00026905054,6.2367747e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003070689,0.00012939064,0.00007540231,0.000062464984,0.000024804769,0.0000154762,0.00017435844,0.00066904386,0.0004643988,0.00017843377,0.0009442616,0.99723125],"study_design_scores_gemma":[0.0014022411,0.00004572977,0.00012686018,0.00004069572,0.000017011618,0.000069209804,0.000021929342,0.9945812,0.00034005285,0.00025765327,0.002943263,0.00015415032],"about_ca_topic_score_codex":0.000026253309,"about_ca_topic_score_gemma":0.0000033322078,"teacher_disagreement_score":0.9970771,"about_ca_system_score_codex":0.00002485345,"about_ca_system_score_gemma":0.000083579835,"threshold_uncertainty_score":0.5199666},"labels":[],"label_agreement":null},{"id":"W1973122015","doi":"10.1016/j.compmedimag.2004.04.001","title":"Simplification of analysis procedures in inter-subject studies with cardiac PET imaging","year":2004,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Positron emission tomography; Resampling; Computer science; Region of interest; Artificial intelligence; Nuclear medicine; Biomedical engineering; Pattern recognition (psychology); Medicine","score_opus":0.016679084696592596,"score_gpt":0.32948171400531917,"score_spread":0.3128026293087266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973122015","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7850991,0.0026839504,0.17873266,0.03255834,0.00007270207,0.00053299696,0.0000082863935,0.00023138759,0.00008060658],"genre_scores_gemma":[0.9759564,0.0014694242,0.021252668,0.0011580363,0.000055859407,0.000054882887,0.000032250704,0.000015471229,0.000005037991],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99848986,0.000044092274,0.0004349658,0.00037870795,0.0004201532,0.00023222913],"domain_scores_gemma":[0.998988,0.00014598208,0.00012503016,0.0003143633,0.00018870042,0.000237977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053661596,0.00017568648,0.0006247495,0.00047057596,0.00006520359,0.00001982992,0.00013081239,0.00003406965,0.000004847934],"category_scores_gemma":[0.00031780556,0.0001294327,0.00011941414,0.0011642921,0.0006989034,0.00006819209,0.00009304036,0.00032370238,3.960024e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036101395,0.0010688006,0.89557236,0.0022613872,0.0022461228,0.00062944245,0.003272664,0.000042280968,0.006003886,0.013135573,0.0022773955,0.073129065],"study_design_scores_gemma":[0.022809101,0.0007687568,0.5378416,0.01574504,0.007880129,0.0020775623,0.004312947,0.36649472,0.0055470904,0.026954548,0.0071662813,0.0024022176],"about_ca_topic_score_codex":0.00011510551,"about_ca_topic_score_gemma":0.000016752203,"teacher_disagreement_score":0.36645243,"about_ca_system_score_codex":0.00003346607,"about_ca_system_score_gemma":0.00017904527,"threshold_uncertainty_score":0.5278112},"labels":[],"label_agreement":null},{"id":"W1978566161","doi":"10.1016/j.compmedimag.2011.05.002","title":"Increasing specimen coverage using digital whole-mount breast pathology: Implementation, clinical feasibility and application in research","year":2011,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Health Sciences Centre; Sunnybrook Health Science Centre","funders":"Ontario Institute for Cancer Research","keywords":"Computer science; Sampling (signal processing); Visualization; Digital pathology; Image processing; Software; Mount; Computer vision; Artificial intelligence; Pathology; Biomedical engineering; Medical physics; Medicine; Image (mathematics)","score_opus":0.12077809785623259,"score_gpt":0.42455350166978256,"score_spread":0.30377540381354995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978566161","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54643947,0.00015243194,0.45245814,0.0005000618,0.00016416404,0.00019611901,0.0000052256046,0.000055834007,0.000028542147],"genre_scores_gemma":[0.9843873,0.00020649703,0.014908978,0.0003233924,0.00014258281,0.0000117591,0.000008435548,0.00001050754,5.5937164e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99731594,0.0005640925,0.00054660783,0.0007133968,0.00049501756,0.00036493858],"domain_scores_gemma":[0.998641,0.00040825745,0.0001177772,0.0004046563,0.00015339162,0.00027489194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004377005,0.00014468473,0.00026190988,0.00026190034,0.00022345444,0.00023552723,0.00037922795,0.0001122565,0.000003630892],"category_scores_gemma":[0.00014416399,0.00014281766,0.000039165236,0.0005795688,0.000697734,0.00067146315,0.0006790035,0.0005862249,0.0000016537939],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064752654,0.00013411627,0.5268527,0.000030097266,0.000010561945,0.000070220354,0.0007331742,4.9113925e-7,0.0002910742,0.00320894,0.000035981273,0.46856788],"study_design_scores_gemma":[0.0022092557,0.0000837571,0.7563022,0.00009758522,0.00000730686,0.001117378,0.00012692895,0.21247505,0.000023354996,0.026725313,0.0005941246,0.00023775508],"about_ca_topic_score_codex":0.0004528223,"about_ca_topic_score_gemma":0.000040570787,"teacher_disagreement_score":0.46833012,"about_ca_system_score_codex":0.00011637621,"about_ca_system_score_gemma":0.00015927394,"threshold_uncertainty_score":0.5823935},"labels":[],"label_agreement":null},{"id":"W1979587059","doi":"10.1016/j.compmedimag.2013.09.004","title":"Segmentation method of intravascular ultrasound images of human coronary arteries","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Cardiologie de Montréal; Boston Scientific Corporation","keywords":"Intravascular ultrasound; Segmentation; Fast marching method; Coronary arteries; Ultrasound; Computer science; Context (archaeology); Artificial intelligence; Image segmentation; Lumen (anatomy); Computer vision; Radiology; Biomedical engineering; Artery; Medicine; Geology; Internal medicine","score_opus":0.012169628066061478,"score_gpt":0.31074577438967516,"score_spread":0.2985761463236137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979587059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7926609,0.000976878,0.20488481,0.0009223285,0.00014909949,0.0002552372,0.000011222672,0.000036103876,0.000103443024],"genre_scores_gemma":[0.9670446,0.00063884724,0.031768993,0.00036430635,0.000055461973,0.000013966842,0.00007686552,0.000011875886,0.000025113133],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988927,0.00007897105,0.0004231611,0.00016777962,0.00030697737,0.00013039203],"domain_scores_gemma":[0.99901164,0.00033547488,0.0001171739,0.00018289323,0.00018709028,0.00016574548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000273509,0.00011524505,0.0003459221,0.00013393446,0.00005221625,0.000016259279,0.00007472893,0.00005441623,0.0002975242],"category_scores_gemma":[0.00016404456,0.00009798582,0.00012828477,0.00012769217,0.00044695902,0.00009183735,0.000061080566,0.00014558822,0.000001158194],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009243861,0.0012044193,0.18345086,0.001588251,0.00045063556,0.000121259196,0.0010166774,0.0000016824741,0.36802855,0.0037780725,0.0055504763,0.43471667],"study_design_scores_gemma":[0.0063128923,0.0010313218,0.94409084,0.0018264453,0.0004860149,0.001424858,0.0010788369,0.0066522765,0.028714132,0.0074508074,0.0005885231,0.00034303026],"about_ca_topic_score_codex":0.00013433282,"about_ca_topic_score_gemma":0.0000016463358,"teacher_disagreement_score":0.76064,"about_ca_system_score_codex":0.0000059129147,"about_ca_system_score_gemma":0.000035387442,"threshold_uncertainty_score":0.39957458},"labels":[],"label_agreement":null},{"id":"W1983383872","doi":"10.1016/j.compmedimag.2013.08.006","title":"Micro-CT image reconstruction based on alternating direction augmented Lagrangian method and total variation","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal University Hospital; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Augmented Lagrangian method; Regularization (linguistics); Total variation denoising; Iterative reconstruction; Algorithm; Computer science; Image quality; Reduction (mathematics); Mathematical optimization; Mathematics; Artificial intelligence; Image (mathematics)","score_opus":0.0056835538499412875,"score_gpt":0.23420832184492157,"score_spread":0.22852476799498028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983383872","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34251451,0.00008777404,0.6555462,0.000478506,0.00047144725,0.00012633996,0.000001607453,0.00055540685,0.00021820239],"genre_scores_gemma":[0.8672022,0.000152399,0.13199022,0.0004343024,0.00016255419,0.000014121284,0.000012763519,0.000026837015,0.0000045907886],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916965,0.00008103873,0.0001914644,0.0002185985,0.00017141842,0.00016783288],"domain_scores_gemma":[0.9995189,0.00014058867,0.000043650976,0.00011786225,0.000051481067,0.00012756113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022289675,0.00015092059,0.00017091642,0.00017727315,0.000104771985,0.00012792213,0.00005254023,0.000047691934,0.00001543824],"category_scores_gemma":[0.00004616806,0.0001443563,0.000038460228,0.00013162121,0.00007515065,0.0001506987,0.000029996821,0.0002398626,0.0000014315748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001261192,0.00003366382,0.00071650586,0.00006407842,0.000052066433,0.000027344453,0.000113903865,0.00024692103,0.14243324,0.00014564164,0.0007843783,0.8553696],"study_design_scores_gemma":[0.0005603652,0.000019040763,0.0065668006,0.00024988595,0.000016858203,0.00019354127,0.000008785906,0.98592246,0.0052952413,0.00088059483,0.00013096358,0.00015545951],"about_ca_topic_score_codex":0.00012156914,"about_ca_topic_score_gemma":0.0000010202211,"teacher_disagreement_score":0.9856755,"about_ca_system_score_codex":0.000016252821,"about_ca_system_score_gemma":0.000007791769,"threshold_uncertainty_score":0.58866787},"labels":[],"label_agreement":null},{"id":"W1983586689","doi":"10.1016/j.compmedimag.2004.07.005","title":"Acceleration of 3D, nonlinear warping using standard video graphics hardware: implementation and initial validation","year":2004,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Image warping; Computer science; Hardware acceleration; Acceleration; Graphics; Computer graphics (images); Nonlinear system; Graphics hardware; Computer hardware; Artificial intelligence; Field-programmable gate array","score_opus":0.029524011525254253,"score_gpt":0.3568382098593764,"score_spread":0.3273141983341222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983586689","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10332946,0.00029836607,0.8940562,0.001726533,0.00033094897,0.00014475388,0.0000064274036,0.00009863365,0.000008678579],"genre_scores_gemma":[0.5604346,0.00072066596,0.43715194,0.0014932129,0.00014423572,0.0000039671786,0.00003429268,0.00001668469,4.4010537e-7],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818754,0.00008573949,0.00048288848,0.00040872037,0.0005807276,0.00025440674],"domain_scores_gemma":[0.999066,0.000100333404,0.00020014957,0.0002203111,0.00020873647,0.00020447893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006014331,0.00017999424,0.00027217242,0.0002935795,0.00028054835,0.00022182577,0.00023745385,0.00006221151,0.000004460559],"category_scores_gemma":[0.0000940631,0.00017615505,0.00004745009,0.000474649,0.00024235397,0.0010202295,0.0002914202,0.00024400504,2.4849572e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049278915,0.00008795159,0.0026769575,0.00017737874,0.00004624872,0.000051099476,0.0017244456,0.0001747075,0.0074487748,0.03094562,0.000049610055,0.95656794],"study_design_scores_gemma":[0.005177151,0.00012514876,0.0013037486,0.00050156686,0.000037066795,0.0001954691,0.00016081122,0.9642176,0.009704781,0.016844768,0.0013067726,0.00042512055],"about_ca_topic_score_codex":0.00005536443,"about_ca_topic_score_gemma":0.000003916887,"teacher_disagreement_score":0.9640429,"about_ca_system_score_codex":0.000026407752,"about_ca_system_score_gemma":0.00016916811,"threshold_uncertainty_score":0.71833944},"labels":[],"label_agreement":null},{"id":"W1984245431","doi":"10.1016/j.compmedimag.2014.05.007","title":"Real-scale 3D models of the scoliotic spine from biplanar radiography without calibration objects","year":2014,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Scoliosis diagnosis and treatment","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Polytechnique Montréal","keywords":"Scoliosis; Calibration; Radiography; Computer science; Kyphosis; Lordosis; Artificial intelligence; Cobb angle; Computer vision; Scale (ratio); Spinal Curvatures; Medicine; Mathematics; Radiology; Statistics; Surgery; Physics","score_opus":0.011879558793990257,"score_gpt":0.25512300885964473,"score_spread":0.24324345006565448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984245431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95602965,0.0013227477,0.035821706,0.00544153,0.00048035025,0.00044124498,0.000011527014,0.00009825298,0.0003529644],"genre_scores_gemma":[0.9906615,0.0015109603,0.005514866,0.0020295132,0.00021225295,0.000016374246,0.00003102089,0.000019378986,0.000004150089],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99847955,0.00012710755,0.00034693422,0.00031445335,0.00052378536,0.00020816181],"domain_scores_gemma":[0.9989975,0.0001311398,0.00012587596,0.0003830749,0.00006792293,0.00029450312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026721982,0.00018200207,0.0004746304,0.00017605915,0.00010564498,0.00003255423,0.0001339425,0.00009579762,0.000009298109],"category_scores_gemma":[0.000057573077,0.000115632974,0.00016584166,0.00041460653,0.00035737976,0.000078347846,0.000082945844,0.00020298403,4.2139845e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018668738,0.0011425343,0.95545524,0.00036228448,0.0005016649,0.00004620637,0.0009893567,0.000058141974,0.0023983,0.0052963425,0.002415745,0.031147486],"study_design_scores_gemma":[0.0053703063,0.00017639133,0.34969056,0.0017456196,0.00042730707,0.000056769888,0.000034460292,0.6377729,0.0011175927,0.0030137275,0.00039175592,0.00020262144],"about_ca_topic_score_codex":0.00041554245,"about_ca_topic_score_gemma":0.000030443549,"teacher_disagreement_score":0.63771474,"about_ca_system_score_codex":0.000011128664,"about_ca_system_score_gemma":0.00007779389,"threshold_uncertainty_score":0.4715376},"labels":[],"label_agreement":null},{"id":"W1986878359","doi":"10.1016/j.compmedimag.2005.02.007","title":"Techniques for efficient, real-time, 3D visualization of multi-modality cardiac data using consumer graphics hardware","year":2005,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Cedars-Sinai Medical Center","keywords":"Computer science; Rendering (computer graphics); Computer graphics (images); Visualization; Computer vision; Volume rendering; Graphics; Artificial intelligence; Segmentation; Cardiac imaging; Modality (human–computer interaction); Computer graphics; Software rendering; Data visualization; Graphics hardware; 3D computer graphics; Radiology; Medicine","score_opus":0.043505279677948136,"score_gpt":0.3617521967072553,"score_spread":0.31824691702930713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986878359","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039686006,0.0007392684,0.99302393,0.00051468855,0.0002998274,0.00058975024,0.00009809677,0.0007507035,0.000015151193],"genre_scores_gemma":[0.18375984,0.004409987,0.80922425,0.001506235,0.0004467165,0.000054881708,0.0004960608,0.000090600595,0.000011454498],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99687165,0.000259238,0.0008288253,0.0009267311,0.0006909451,0.00042259277],"domain_scores_gemma":[0.9970866,0.00038146158,0.00037497762,0.0012624279,0.00058574846,0.00030880998],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020564345,0.0003387233,0.0006245538,0.0005653896,0.0003100332,0.00022576847,0.0014996704,0.00020487283,0.0000032325718],"category_scores_gemma":[0.00020401161,0.000332393,0.00016687703,0.0010033061,0.00048992183,0.00046852973,0.001335101,0.00021604003,3.8294675e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060697726,0.0013056834,0.006433991,0.0008766851,0.00032967216,0.000015973656,0.001110803,0.000043392036,0.00539778,0.6631324,0.006602864,0.31469002],"study_design_scores_gemma":[0.00069353956,0.00004045618,0.00039485612,0.0002602739,0.000049300255,0.000016685464,0.0000043612245,0.9848762,0.001325744,0.000996417,0.01098023,0.0003619188],"about_ca_topic_score_codex":0.00009988029,"about_ca_topic_score_gemma":0.0000034152183,"teacher_disagreement_score":0.9848328,"about_ca_system_score_codex":0.00002153891,"about_ca_system_score_gemma":0.00019824479,"threshold_uncertainty_score":0.9999128},"labels":[],"label_agreement":null},{"id":"W1986907517","doi":"10.1016/j.compmedimag.2014.11.002","title":"A physically based trunk soft tissue modeling for scoliosis surgery planning systems","year":2014,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Scoliosis diagnosis and treatment","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Natural Sciences and Engineering Research Council of Canada; Centre hospitalier universitaire Sainte-Justine","keywords":"Trunk; Scoliosis; Surgical planning; Spinal surgery; Idiopathic scoliosis; Medicine; Process (computing); Radiation treatment planning; Soft tissue; Computer science; Surgery; Radiation therapy","score_opus":0.033963306754920264,"score_gpt":0.31141958458104896,"score_spread":0.2774562778261287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986907517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22760053,0.0030990718,0.7623908,0.0054199165,0.0006106802,0.00060219865,0.0000066005873,0.00022565914,0.000044559143],"genre_scores_gemma":[0.99245006,0.000115428156,0.0027265993,0.0037970021,0.0006328809,0.00018507686,0.000048227084,0.00004051816,0.0000041827784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811953,0.00008826192,0.00043074242,0.00045687595,0.0004920032,0.00041260562],"domain_scores_gemma":[0.9979998,0.00094766275,0.00009460416,0.00026586943,0.00015073587,0.0005413214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000734638,0.00025411238,0.0007373699,0.0002550172,0.00019193809,0.000111909816,0.00009445217,0.00011329041,0.000003922806],"category_scores_gemma":[0.0004463636,0.00020672484,0.00019910902,0.00023334821,0.00012649353,0.00006583051,0.00004586493,0.00019750805,0.0000017034694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002180548,0.0061529404,0.31043714,0.010746371,0.0019629893,0.0009504375,0.0012361242,0.005185741,0.0027858901,0.015032837,0.035906397,0.6074226],"study_design_scores_gemma":[0.0029383034,0.00012676898,0.0025703416,0.0031380404,0.00020009743,0.0000593801,0.000019834853,0.9863057,0.00008612705,0.00020284725,0.0041377572,0.00021479084],"about_ca_topic_score_codex":0.000040785042,"about_ca_topic_score_gemma":6.4461733e-7,"teacher_disagreement_score":0.98112,"about_ca_system_score_codex":0.000023109373,"about_ca_system_score_gemma":0.00013676706,"threshold_uncertainty_score":0.8429994},"labels":[],"label_agreement":null},{"id":"W1994454819","doi":"10.1016/j.compmedimag.2014.06.017","title":"A data-driven approach to prostate cancer detection from dynamic contrast enhanced MRI","year":2014,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Principal component analysis; Dynamic contrast-enhanced MRI; Computer science; Prostate cancer; Artificial intelligence; Pattern recognition (psychology); Data set; Contrast (vision); Magnetic resonance imaging; Prostatectomy; Cross-validation; Support vector machine; Dynamic contrast; Medical imaging; Cancer; Medicine; Radiology","score_opus":0.015456698016417036,"score_gpt":0.29889261693713215,"score_spread":0.2834359189207151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994454819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16446646,0.0008130563,0.8201652,0.012556533,0.00085836026,0.0005947791,0.00018017035,0.00022316689,0.00014225508],"genre_scores_gemma":[0.96910244,0.0029914805,0.019338334,0.0075076423,0.0005460524,0.00014949034,0.00030154735,0.000042937947,0.00002004719],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979126,0.00010268081,0.00033578236,0.0007607287,0.00053074793,0.00035747208],"domain_scores_gemma":[0.9982971,0.00024500774,0.00008880556,0.00062889943,0.00010795159,0.00063222996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039769974,0.0002271771,0.00049104716,0.00014938945,0.000097256336,0.00006699627,0.00029814668,0.000106734944,0.000026462689],"category_scores_gemma":[0.00016042295,0.00019733715,0.00005384411,0.00030945658,0.00024059741,0.000108453816,0.00027922879,0.00042957417,0.000005380442],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005658354,0.0004847776,0.0065622358,0.00045720054,0.00036360332,0.000037418413,0.0015071986,0.00012316872,0.01456092,0.00012765259,0.009376759,0.96583325],"study_design_scores_gemma":[0.003908826,0.000087587425,0.009936717,0.0006583798,0.00017769216,0.00003452521,0.000041350842,0.9479642,0.00042988907,0.00023374405,0.036249824,0.00027726844],"about_ca_topic_score_codex":0.0003551938,"about_ca_topic_score_gemma":0.0001702904,"teacher_disagreement_score":0.96555597,"about_ca_system_score_codex":0.000048335813,"about_ca_system_score_gemma":0.000110440626,"threshold_uncertainty_score":0.8047176},"labels":[],"label_agreement":null},{"id":"W2000146673","doi":"10.1016/j.compmedimag.2006.07.002","title":"Kinetic modeling of PET-FDG in the brain without blood sampling","year":2006,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Positron emission tomography; Sampling (signal processing); Blood sampling; Computer science; Nuclear medicine; Medicine; Internal medicine; Computer vision","score_opus":0.02355489142169368,"score_gpt":0.31459639479690166,"score_spread":0.29104150337520795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000146673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5836146,0.0006467445,0.37450272,0.040347487,0.00005329351,0.00033645626,0.0000027075077,0.00012269994,0.00037328902],"genre_scores_gemma":[0.956631,0.00020984451,0.0389879,0.0039216094,0.0001731942,0.000024459483,0.000026694885,0.000015362493,0.000009949662],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846166,0.00006922399,0.00045573706,0.0002652784,0.0004993633,0.00024875146],"domain_scores_gemma":[0.9991313,0.00027480524,0.000070340255,0.00031191227,0.00006575122,0.0001458631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087599,0.00014283457,0.0003341781,0.00015482663,0.00007098092,0.000026745889,0.0002104622,0.000053766486,0.000010357537],"category_scores_gemma":[0.00021082092,0.00009849992,0.00007654245,0.0003604112,0.00035711852,0.00003188411,0.00008173062,0.00048483166,4.1748882e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054173765,0.009783485,0.35938624,0.0047665485,0.00042854535,0.002701256,0.0036119537,0.0004905799,0.08498636,0.3232636,0.038667988,0.17137173],"study_design_scores_gemma":[0.002341665,0.0000478462,0.004527377,0.00081714994,0.000098271346,0.0008850994,0.00005569463,0.977956,0.00007837725,0.009853311,0.0031820273,0.00015717733],"about_ca_topic_score_codex":0.0002692936,"about_ca_topic_score_gemma":0.0000057260568,"teacher_disagreement_score":0.97746545,"about_ca_system_score_codex":0.0000050615977,"about_ca_system_score_gemma":0.00006508133,"threshold_uncertainty_score":0.40167102},"labels":[],"label_agreement":null},{"id":"W2001652071","doi":"10.1016/j.compmedimag.2013.12.003","title":"Ensemble-based hybrid probabilistic sampling for imbalanced data learning in lung nodule CAD","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; China Scholarship Council; National Natural Science Foundation of China; Simon Fraser University; University of Alberta","keywords":"Probabilistic logic; Artificial intelligence; Pattern recognition (psychology); Subspace topology; CAD; Computer science; Dimensionality reduction; Sampling (signal processing); Nodule (geology); Computer-aided diagnosis; Probabilistic classification; Statistics; Mathematics; Machine learning; Support vector machine; Computer vision; Naive Bayes classifier; Biology","score_opus":0.03378149451165669,"score_gpt":0.3051422654233574,"score_spread":0.2713607709117007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001652071","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0070806895,0.00020337442,0.98527646,0.0059445244,0.0002533281,0.0006397925,0.0000188783,0.0005615841,0.000021376269],"genre_scores_gemma":[0.5593461,0.000100131285,0.43757862,0.0021866858,0.00010819462,0.00021923087,0.00042463967,0.00002673649,0.000009689917],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99766624,0.00013213584,0.00047689892,0.0008535998,0.00039621998,0.00047489352],"domain_scores_gemma":[0.9976183,0.00077899155,0.000154882,0.0010455357,0.00015940012,0.00024289956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011001329,0.00021737954,0.0003356268,0.00024704463,0.00018431258,0.00035190812,0.0016266811,0.00007562842,0.0000038805983],"category_scores_gemma":[0.0009865693,0.00020703697,0.000042645843,0.00040083603,0.00021159313,0.0006619929,0.000697949,0.00045684687,0.0000029599069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051176627,0.0004780125,0.022567753,0.0011498155,0.00005156411,0.000065478176,0.00035925675,0.00021678061,0.007911149,0.040321562,0.01777372,0.90905374],"study_design_scores_gemma":[0.0011080527,0.000024129045,0.0037314831,0.00022431058,0.0000059224853,0.000022627917,0.0000056492254,0.98376113,0.00022956294,0.005922999,0.004714395,0.0002497405],"about_ca_topic_score_codex":0.000052636304,"about_ca_topic_score_gemma":0.0000045496827,"teacher_disagreement_score":0.98354435,"about_ca_system_score_codex":0.00003653234,"about_ca_system_score_gemma":0.00017756775,"threshold_uncertainty_score":0.84427226},"labels":[],"label_agreement":null},{"id":"W201277942","doi":"10.1016/j.compmedimag.2012.07.003","title":"Understanding by seeing before treating: Present and future of medical imaging","year":2012,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Medical imaging; Exploit; Medical diagnosis; Reimbursement; Modalities; Medical physics; Imaging science; Computer science; Imaging technology; Nuclear medicine imaging; Medicine; Health care; Radiology; Artificial intelligence; Computer security; Political science","score_opus":0.03322170991425902,"score_gpt":0.32359624697598227,"score_spread":0.2903745370617232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W201277942","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12626438,0.022326421,0.5379297,0.31038272,0.0007072488,0.0007862629,0.000024572872,0.0006381688,0.00094050914],"genre_scores_gemma":[0.9816697,0.003491312,0.009568307,0.0035386896,0.0015685352,0.000024746118,0.00007164454,0.000042600645,0.000024469053],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743134,0.00008150598,0.0004906024,0.00034557912,0.0011650356,0.00048592233],"domain_scores_gemma":[0.99797857,0.00022174096,0.00013349917,0.00028100965,0.00007484012,0.0013103293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011965513,0.00024105437,0.00049228483,0.00016137375,0.00019887016,0.000041803316,0.00018925106,0.00017106363,0.00008309284],"category_scores_gemma":[0.0001672742,0.00019072996,0.000083188665,0.00034126884,0.00088152697,0.00013746046,0.00028336374,0.0006592057,5.371322e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008240449,0.00071964227,0.27911457,0.0013470636,0.00022433662,0.00016298398,0.0023211495,4.9786365e-8,0.001667936,0.064464405,0.12552151,0.52437395],"study_design_scores_gemma":[0.008195037,0.0001628795,0.013075417,0.0037155375,0.0005523675,0.0037967346,0.0017331486,0.6067013,0.00055200676,0.0070025674,0.35358968,0.00092333014],"about_ca_topic_score_codex":0.000058104528,"about_ca_topic_score_gemma":6.3399966e-7,"teacher_disagreement_score":0.85540533,"about_ca_system_score_codex":0.000032082287,"about_ca_system_score_gemma":0.000104083076,"threshold_uncertainty_score":0.7777742},"labels":[],"label_agreement":null},{"id":"W2014929720","doi":"10.1016/j.compmedimag.2006.12.003","title":"Assessment of glucose metabolism from the projections using the wavelet technique in small animal pet imaging","year":2007,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Wavelet; Iterative reconstruction; Parametric statistics; Projection (relational algebra); Image resolution; Filter (signal processing); Positron emission tomography; Artificial intelligence; Nuclear medicine; Mathematics; Computer science; Pattern recognition (psychology); Image quality; Computer vision; Algorithm; Image (mathematics); Medicine; Statistics","score_opus":0.02666874613227405,"score_gpt":0.3456867968146057,"score_spread":0.31901805068233163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014929720","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37205285,0.0007915197,0.6054154,0.020523256,0.00012564349,0.00081700715,0.000012225079,0.00013144212,0.00013064276],"genre_scores_gemma":[0.8494871,0.00038528643,0.14627668,0.0034769578,0.00026281003,0.000058547685,0.000025442594,0.000023952449,0.0000032153762],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809045,0.00013680571,0.0005970394,0.00035699867,0.00046035292,0.0003583275],"domain_scores_gemma":[0.998325,0.00066055224,0.00016216196,0.00048765962,0.00013211461,0.00023251225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023536414,0.00020269435,0.00039617307,0.00017759451,0.0002318819,0.000044165838,0.00032463894,0.0000644686,0.000018377068],"category_scores_gemma":[0.00025333348,0.00012059487,0.000119905206,0.00066945294,0.0008801068,0.000055236465,0.0002573374,0.0009820568,1.7748674e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034686603,0.0022638058,0.3219141,0.0005320602,0.00045644434,0.0014899797,0.0022747095,0.0000042532524,0.37298584,0.08489465,0.0057275514,0.20710972],"study_design_scores_gemma":[0.002903939,0.000056156267,0.25003603,0.001402206,0.00035753244,0.0016239516,0.0005331878,0.7184449,0.004304809,0.006046206,0.01387614,0.00041494358],"about_ca_topic_score_codex":0.0010389962,"about_ca_topic_score_gemma":0.000033473552,"teacher_disagreement_score":0.71844065,"about_ca_system_score_codex":0.00003219286,"about_ca_system_score_gemma":0.00024166258,"threshold_uncertainty_score":0.4917716},"labels":[],"label_agreement":null},{"id":"W2016452392","doi":"10.1016/j.compmedimag.2005.10.007","title":"An automatic variational level set segmentation framework for computer aided dental X-rays analysis in clinical environments","year":2006,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Pattern recognition (psychology); Scale-space segmentation; Support vector machine; Segmentation-based object categorization; Image segmentation; Classifier (UML); Computer-aided; Principal component analysis; Level set method; Computer vision; Feature extraction","score_opus":0.02886535993748987,"score_gpt":0.3516194388672539,"score_spread":0.32275407892976404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016452392","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032544516,0.000050461556,0.9656052,0.00079984387,0.00040512992,0.0003803466,0.000018927845,0.00019249726,0.0000030724973],"genre_scores_gemma":[0.12812538,0.000046323705,0.86803627,0.0031204505,0.000278938,0.000059932336,0.00031390807,0.000014601993,0.0000041807266],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965875,0.0004181265,0.0010188756,0.00074272335,0.00087111123,0.00036162385],"domain_scores_gemma":[0.9980427,0.0008735208,0.0002615048,0.00042873988,0.000046764046,0.00034678887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018617042,0.0002398296,0.00046275544,0.000500779,0.00015153736,0.00026441846,0.00067584956,0.00018687456,0.000025026786],"category_scores_gemma":[0.00014133536,0.00023534872,0.00017900045,0.00076063373,0.00029428856,0.00046165855,0.00022342458,0.0003588971,0.0000025099482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051995827,0.0020632849,0.2250745,0.00014044832,0.0005007643,0.00014665819,0.00082201854,0.00043123125,0.00077051594,0.050097156,0.002549555,0.71735185],"study_design_scores_gemma":[0.0014025258,0.00007538271,0.18969727,0.00005578056,0.00006115796,0.000012954191,0.000013277267,0.79476464,0.000089781824,0.01356744,0.000047997502,0.00021183258],"about_ca_topic_score_codex":0.000053113567,"about_ca_topic_score_gemma":0.000013921755,"teacher_disagreement_score":0.7943334,"about_ca_system_score_codex":0.000045042587,"about_ca_system_score_gemma":0.000083568935,"threshold_uncertainty_score":0.9597242},"labels":[],"label_agreement":null},{"id":"W2016794530","doi":"10.1016/j.compmedimag.2012.12.002","title":"On mixed reality environments for minimally invasive therapy guidance: Systems architecture, successes and challenges in their implementation from laboratory to clinic","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Augmented Reality Applications","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Center for Research Resources; Cancer Research UK","keywords":"Mixed reality; Computer science; Surgical procedures; Architecture; Invasive surgery; Clinical Practice; Field (mathematics); Augmented reality; Human–computer interaction; Virtual reality; Medical physics; Medicine; Surgery; Nursing","score_opus":0.04442616664967191,"score_gpt":0.3131953629886337,"score_spread":0.2687691963389618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016794530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2769744,0.004661848,0.6869139,0.029640006,0.00027259876,0.0013576268,0.0000850474,0.000082086786,0.000012473759],"genre_scores_gemma":[0.9725617,0.013739851,0.008831374,0.0038214945,0.00013091599,0.00081400684,0.00007617681,0.000022021744,0.000002470891],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99821186,0.0002489278,0.0004043971,0.0005920101,0.00028848814,0.00025431003],"domain_scores_gemma":[0.99794453,0.0012164856,0.00013384211,0.00040086306,0.00004925644,0.00025504746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064366375,0.00018705399,0.000277044,0.0001417152,0.00011578072,0.00014987221,0.00044757576,0.000076457414,0.0000038989165],"category_scores_gemma":[0.00009011624,0.00015503507,0.000032245258,0.00019115234,0.0001518004,0.00016457892,0.00020591721,0.00016810182,0.0000021295289],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097001575,0.00053647597,0.0036770285,0.00028126928,0.00017321468,0.000012257087,0.005068398,0.000050512193,0.0055078696,0.019596437,0.003690527,0.961309],"study_design_scores_gemma":[0.021386703,0.0014654441,0.4946377,0.0020402076,0.00005538587,0.00003269904,0.003419232,0.21411574,0.0055976156,0.1689079,0.08585076,0.0024906222],"about_ca_topic_score_codex":0.0002848093,"about_ca_topic_score_gemma":0.00010135528,"teacher_disagreement_score":0.9588184,"about_ca_system_score_codex":0.000022239514,"about_ca_system_score_gemma":0.000070640366,"threshold_uncertainty_score":0.63221467},"labels":[],"label_agreement":null},{"id":"W2023585057","doi":"10.1016/j.compmedimag.2014.12.001","title":"Phantom study of an ultrasound guidance system for transcatheter aortic valve implantation","year":2014,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Robarts Clinical Trials; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Biplane; Imaging phantom; Software deployment; Intracardiac injection; Aortic valve; Stent; Medicine; Radiology; Computer science; Biomedical engineering; Surgery; Engineering","score_opus":0.011846695970451265,"score_gpt":0.3297432384227126,"score_spread":0.3178965424522613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023585057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96418375,0.0003352054,0.034523726,0.00006052055,0.0002662054,0.00052295544,0.000023281724,0.00006420292,0.000020154748],"genre_scores_gemma":[0.99878395,0.000038925788,0.0006840588,0.00020625466,0.00014755371,0.00004302978,0.00007687889,0.000017449538,0.0000019282415],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988507,0.00008615315,0.00029585516,0.00027060808,0.00032322883,0.00017344866],"domain_scores_gemma":[0.9990951,0.00021494202,0.00007961263,0.00021473675,0.000103114406,0.00029248875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031274976,0.00013754569,0.00038902645,0.00008632233,0.000077174795,0.00002265201,0.00006230403,0.000041883195,0.0000019906283],"category_scores_gemma":[0.000056569814,0.00010888624,0.00044599958,0.00009647672,0.00008284039,0.00005468943,0.000012422736,0.000069995855,3.5752217e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016912839,0.00557848,0.6926648,0.003321588,0.0039201155,0.00003541946,0.004171518,0.000005406591,0.0031091857,0.0011828932,0.00014805248,0.28417128],"study_design_scores_gemma":[0.02715876,0.0019696308,0.91372275,0.00091396214,0.0039060188,0.00032784592,0.0011218019,0.04973665,0.00024602257,0.0003840079,0.0001705738,0.00034196203],"about_ca_topic_score_codex":0.000046977057,"about_ca_topic_score_gemma":0.0000016845845,"teacher_disagreement_score":0.2838293,"about_ca_system_score_codex":0.000010435481,"about_ca_system_score_gemma":0.000030666535,"threshold_uncertainty_score":0.4440252},"labels":[],"label_agreement":null},{"id":"W2025668285","doi":"10.1016/j.compmedimag.2007.06.002","title":"Vector edge operators for cDNA microarray spot localization","year":2007,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Victoria Park","funders":"","keywords":"Complementary DNA; Edge detection; Computer science; Microarray; Support vector machine; Enhanced Data Rates for GSM Evolution; Classification of discontinuities; Pattern recognition (psychology); Artificial intelligence; Biology; Image processing; Mathematics; Gene expression; Gene; Genetics; Image (mathematics)","score_opus":0.00982513963708688,"score_gpt":0.27716240467280345,"score_spread":0.2673372650357166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025668285","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11933333,0.0012738227,0.87738293,0.0011414707,0.00061876694,0.0001543611,0.000004899289,0.000026798036,0.000063603606],"genre_scores_gemma":[0.99242586,0.0004912624,0.0028545614,0.0033569355,0.0005827057,0.00001550849,0.0001720183,0.00002034523,0.00008081764],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99915195,0.000027839633,0.00019136997,0.0002974208,0.00013803678,0.00019336001],"domain_scores_gemma":[0.9994642,0.000022723834,0.0000483427,0.00016651559,0.000094684365,0.00020349468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041106786,0.00010988816,0.0001077459,0.00006569499,0.00012339531,0.00003353668,0.00012168562,0.00011468157,0.000006567427],"category_scores_gemma":[0.00009705173,0.000098281474,0.00005320759,0.00011572419,0.00013634146,0.0000038134967,0.00005458515,0.00007548539,6.6300197e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018591205,0.00009605184,0.004275259,0.00007904856,0.000035126006,0.000004838275,0.0001148399,0.000003822004,0.85523945,0.001550346,0.02671387,0.11170144],"study_design_scores_gemma":[0.0028651347,0.00011820905,0.00566438,0.00010213561,0.000026126763,0.00004286654,0.00010476399,0.014603623,0.1698404,0.0002684631,0.8059756,0.00038827866],"about_ca_topic_score_codex":0.0000030768913,"about_ca_topic_score_gemma":0.0000033143658,"teacher_disagreement_score":0.8745284,"about_ca_system_score_codex":0.0000054768975,"about_ca_system_score_gemma":0.000063451145,"threshold_uncertainty_score":0.40078023},"labels":[],"label_agreement":null},{"id":"W2027361807","doi":"10.1016/j.compmedimag.2013.06.007","title":"Synchronized 2D/3D optical mapping for interactive exploration and real-time visualization of multi-function neurological images","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CancerCare Manitoba; University of Winnipeg; Centre for Imaging Technology Commercialization; Western University","funders":"","keywords":"Computer science; Visualization; Software; Volume rendering; Rendering (computer graphics); Interactivity; Artificial intelligence; Computer vision; Data visualization; Interactive visualization; Image processing; Computer graphics (images); Image (mathematics); Multimedia","score_opus":0.020906656744474648,"score_gpt":0.2984976817356936,"score_spread":0.2775910249912189,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027361807","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074772686,0.00009235105,0.9890628,0.0022888482,0.000205519,0.00054083124,0.0000017629511,0.00030627692,0.000024365758],"genre_scores_gemma":[0.15347841,0.00093709794,0.843037,0.0021282951,0.00012837666,0.0001929277,0.000056194276,0.000024264638,0.000017407287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817777,0.00024047891,0.00048277064,0.0004742968,0.00038738348,0.00023731138],"domain_scores_gemma":[0.99813944,0.00091347244,0.00018845791,0.00020154016,0.00029258843,0.00026452835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007049321,0.0001820934,0.0003253469,0.0002228594,0.00012404143,0.00019426971,0.00025151082,0.000111701665,0.00002219823],"category_scores_gemma":[0.0008247406,0.0001561702,0.00005518409,0.000270494,0.00043248665,0.0010390751,0.0002853107,0.00016903545,0.000002357161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007856633,0.00028165506,0.00046647832,0.00021258087,0.00005374614,0.000013330573,0.00086520496,0.0000023032574,0.09326645,0.004387311,0.001803767,0.89856863],"study_design_scores_gemma":[0.0016819523,0.00022109861,0.0035524208,0.00014347791,0.000019865687,0.00003967751,0.00004026452,0.98758966,0.002487133,0.0039654262,0.000072757,0.00018627699],"about_ca_topic_score_codex":0.00002337575,"about_ca_topic_score_gemma":2.848574e-7,"teacher_disagreement_score":0.98758733,"about_ca_system_score_codex":0.000011044088,"about_ca_system_score_gemma":0.000043489017,"threshold_uncertainty_score":0.63684356},"labels":[],"label_agreement":null},{"id":"W2028735777","doi":"10.1016/j.compmedimag.2009.12.005","title":"An enhancement of quantitative accuracy of the SPECT/CT activity distribution reconstructions: Physical phantom experiments","year":2010,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Voxel; Imaging phantom; Computer science; Projection (relational algebra); Iterative reconstruction; Computer vision; Artificial intelligence; Partial volume; Attenuation; Nuclear medicine; Object (grammar); Medicine; Algorithm; Physics; Optics","score_opus":0.02335505343614873,"score_gpt":0.3717402729561389,"score_spread":0.34838521951999013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028735777","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9199038,0.00003967556,0.07622611,0.0032247743,0.0002221786,0.00027670272,0.000021776716,0.00004789474,0.000037083562],"genre_scores_gemma":[0.9897659,0.00012550157,0.00977424,0.00018324252,0.000087236396,0.00002570337,0.000027106222,0.000008075488,0.000003010845],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988496,0.000067222274,0.00027420666,0.00023934567,0.00042048935,0.00014914531],"domain_scores_gemma":[0.99887604,0.00020150206,0.00019694072,0.000396097,0.000111949186,0.00021746529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030119342,0.00012163332,0.0003082593,0.000046049423,0.000102899714,0.000012314999,0.00018154763,0.000024073568,0.000029392575],"category_scores_gemma":[0.00036646985,0.00008337777,0.00010234678,0.00025904312,0.00113659,0.0000902223,0.00009483561,0.0004562106,3.601411e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008701248,0.0016255138,0.006261485,0.00015156947,0.00007259649,0.000010723379,0.00026517964,5.923838e-8,0.84859926,0.022321416,0.0008173198,0.11978787],"study_design_scores_gemma":[0.0024401478,0.00027051754,0.019353434,0.00071351125,0.00017385805,0.00042734272,0.00015217769,0.13801888,0.8294063,0.0056214426,0.0031716172,0.0002507753],"about_ca_topic_score_codex":0.000062291525,"about_ca_topic_score_gemma":0.000001506166,"teacher_disagreement_score":0.13801882,"about_ca_system_score_codex":0.000009312071,"about_ca_system_score_gemma":0.00011590592,"threshold_uncertainty_score":0.4187813},"labels":[],"label_agreement":null},{"id":"W2029980780","doi":"10.1016/j.compmedimag.2009.05.001","title":"Perk Station—Percutaneous surgery training and performance measurement platform","year":2009,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institutes of Health; Queen's University; National Institute of Biomedical Imaging and Bioengineering; Johns Hopkins University","keywords":"Medical physics; Software; Computer science; Workflow; Visualization; Process (computing); Medicine; Human–computer interaction; Artificial intelligence; Operating system","score_opus":0.058932350081025,"score_gpt":0.2868755900927831,"score_spread":0.22794324001175809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029980780","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9864781,0.0010971966,0.006671286,0.0044693653,0.0002386686,0.00013511784,0.0000013143359,0.00017389111,0.0007350849],"genre_scores_gemma":[0.9925471,0.0007945033,0.0011282403,0.0053476077,0.00014477888,0.0000016590524,0.00001723162,0.000010068816,0.000008829562],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846405,0.000028162005,0.00031096608,0.00025586176,0.00066979695,0.00027114962],"domain_scores_gemma":[0.9990251,0.00024369646,0.0000513865,0.00010257985,0.00010640662,0.00047079963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007901164,0.00015339754,0.00035133355,0.00014910221,0.00017485561,0.000051922678,0.00003876132,0.00007108022,0.000037103746],"category_scores_gemma":[0.00026607333,0.00012594245,0.000062711166,0.00017863647,0.00017265206,0.00009737183,0.000020104273,0.00028835877,0.000001214793],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118768054,0.000056071727,0.008635103,0.000059383507,0.000029022998,0.00025254776,0.0008017946,0.0000019692493,0.000069834314,0.00041637386,0.00010994029,0.9894492],"study_design_scores_gemma":[0.007386107,0.0003997268,0.31694046,0.0018140608,0.00015907733,0.0059837084,0.0005948745,0.63254166,0.000037477024,0.0014620705,0.032006696,0.0006741115],"about_ca_topic_score_codex":0.000003820472,"about_ca_topic_score_gemma":6.7037547e-7,"teacher_disagreement_score":0.9887751,"about_ca_system_score_codex":0.000017091477,"about_ca_system_score_gemma":0.00011191309,"threshold_uncertainty_score":0.51357836},"labels":[],"label_agreement":null},{"id":"W2031408555","doi":"10.1016/s0895-6111(02)00091-5","title":"Generalized 3D nonlinear transformations for medical imaging: an object-oriented implementation in VTK","year":2003,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Institut des Systèmes Intelligents et de Robotique, Université Pierre et Marie Curie; Canadian Institutes of Health Research; Western University; Ministère de l'Éducation, du Loisir et du Sport Québec","keywords":"Computer science; Polygon mesh; Visualization; Interpolation (computer graphics); Nonlinear system; Medical imaging; Transformation (genetics); Computer graphics (images); Computer vision; Artificial intelligence; Image (mathematics)","score_opus":0.009967964132338794,"score_gpt":0.2874973421532235,"score_spread":0.2775293780208847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031408555","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13663,0.00079836475,0.8607963,0.00094810646,0.0003408125,0.00017327674,0.000020800939,0.00023476167,0.000057591977],"genre_scores_gemma":[0.9630303,0.0011767274,0.033898603,0.0011973557,0.00018071977,0.00006255659,0.00040424181,0.000046163823,0.0000033466652],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983032,0.00009264717,0.0005343163,0.00026101456,0.0004382895,0.0003705342],"domain_scores_gemma":[0.9992574,0.000099256125,0.00003265124,0.00015696323,0.000072897376,0.00038085127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080814,0.00019864895,0.00030943492,0.00030361596,0.00013279304,0.00006433351,0.00014129769,0.00008905045,0.00006293738],"category_scores_gemma":[0.00008700601,0.00019232757,0.000098628334,0.00038569712,0.0000969487,0.00019871345,0.000014969776,0.00028705387,9.730692e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009139743,0.00072282366,0.012953876,0.0008287595,0.0005454632,0.00018023886,0.0068766433,0.008139755,0.0013577011,0.0140401125,0.0042781993,0.949985],"study_design_scores_gemma":[0.0029294307,0.000011778635,0.00013356743,0.00006814445,0.00004237173,0.00003228723,0.00017333176,0.99068105,0.00008468931,0.00061835867,0.005006544,0.00021842822],"about_ca_topic_score_codex":0.000045608085,"about_ca_topic_score_gemma":0.00007604475,"teacher_disagreement_score":0.9825413,"about_ca_system_score_codex":0.000021696336,"about_ca_system_score_gemma":0.00007704309,"threshold_uncertainty_score":0.78428906},"labels":[],"label_agreement":null},{"id":"W2032302562","doi":"10.1016/j.compmedimag.2013.03.002","title":"Prediction of deformations during endovascular aortic aneurysm repair using finite element simulation","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Aortic aneurysm repair treatments","field":"Medicine","cited_by":55,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Canadian Society for Vascular Surgery","keywords":"Finite element method; Aortic aneurysm; Aneurysm; Endovascular aneurysm repair; Abdominal aortic aneurysm; Computer science; Medicine; Radiology; Structural engineering; Engineering","score_opus":0.020283516800456078,"score_gpt":0.2689805113974961,"score_spread":0.24869699459704003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032302562","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8873983,0.00023684824,0.111287646,0.00026778143,0.00013271574,0.0004436669,0.000004593744,0.00020437987,0.000024093937],"genre_scores_gemma":[0.99220455,0.000105225714,0.007255859,0.00025773045,0.00008244021,0.000019197274,0.00004472891,0.000018594601,0.000011651574],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982777,0.000067551686,0.00060583063,0.00025493454,0.00055163074,0.00024231855],"domain_scores_gemma":[0.9989841,0.00012823178,0.00015475856,0.00028435804,0.00016723195,0.00028132732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002191781,0.00016307853,0.00030866903,0.00020723882,0.00013695283,0.000018328741,0.000053528653,0.000077231256,0.000060386592],"category_scores_gemma":[0.00023407373,0.00013948628,0.00015739707,0.0002404466,0.00018895007,0.00020752712,0.00008468154,0.00018954622,0.0000031976656],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019052869,0.0013707448,0.9457745,0.0025140124,0.0009893563,0.0006341774,0.0018207609,0.0064780586,0.011102103,0.00019356378,0.00021511184,0.028717065],"study_design_scores_gemma":[0.002085808,0.000064274034,0.14108801,0.00021340387,0.00021061323,0.00035889144,0.00004427639,0.85556144,0.00014710288,0.00010064922,0.00004654992,0.000078979385],"about_ca_topic_score_codex":0.00006716547,"about_ca_topic_score_gemma":3.1273237e-7,"teacher_disagreement_score":0.84908336,"about_ca_system_score_codex":0.00003911355,"about_ca_system_score_gemma":0.0000689801,"threshold_uncertainty_score":0.5688085},"labels":[],"label_agreement":null},{"id":"W2032421849","doi":"10.1016/j.compmedimag.2011.12.001","title":"3D segmentation of abdominal aorta from CT-scan and MR images","year":2012,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Aortic aneurysm repair treatments","field":"Medicine","cited_by":66,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Université de Bourgogne","keywords":"Segmentation; Hausdorff distance; Abdominal aortic aneurysm; Aorta; Abdominal aorta; Medicine; Computer science; Artificial intelligence; Radiology; Lumen (anatomy); Magnetic resonance imaging; Nuclear medicine; Computer vision; Aneurysm; Surgery","score_opus":0.011466809277504167,"score_gpt":0.28631940805365197,"score_spread":0.2748525987761478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032421849","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97960675,0.0029619457,0.015802562,0.0010626965,0.00021973588,0.00016494378,0.000012641594,0.000056958765,0.00011174392],"genre_scores_gemma":[0.9798342,0.0006855123,0.018408587,0.0007886762,0.0001775334,0.0000064982933,0.000058401092,0.000015279555,0.000025303281],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99884164,0.00005468356,0.0003014574,0.00021198328,0.0003643674,0.00022587614],"domain_scores_gemma":[0.9990913,0.00017117478,0.00010170847,0.00016478638,0.00004120075,0.00042978197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023006175,0.00014871712,0.00033258102,0.00008682461,0.000057668498,0.000013509137,0.00004865309,0.000040267383,0.000050820418],"category_scores_gemma":[0.00008809394,0.000119985096,0.000051256317,0.000095017174,0.00042214562,0.000111557754,0.000085744425,0.0001625352,0.0000016130895],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012197705,0.00031953084,0.7905586,0.0001425231,0.00017594064,0.00019380415,0.00059124053,4.430821e-8,0.0055346885,0.00007764984,0.0010432446,0.20124081],"study_design_scores_gemma":[0.010728512,0.00023947211,0.9527209,0.00073545246,0.0009549906,0.0017106364,0.0004155116,0.025339188,0.0046473234,0.00045475052,0.0016685283,0.00038478148],"about_ca_topic_score_codex":0.0001485374,"about_ca_topic_score_gemma":9.4436143e-7,"teacher_disagreement_score":0.20085602,"about_ca_system_score_codex":0.0000117543805,"about_ca_system_score_gemma":0.000045154182,"threshold_uncertainty_score":0.48928502},"labels":[],"label_agreement":null},{"id":"W2037002160","doi":"10.1016/j.compmedimag.2012.03.003","title":"3D registration of MR and X-ray spine images using an articulated model","year":2012,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Scoliosis diagnosis and treatment","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal","funders":"Canadian Institutes of Health Research","keywords":"Scoliosis; Magnetic resonance imaging; Position (finance); Computer science; Computer vision; Artificial intelligence; Image registration; SPINE (molecular biology); Vertebral body; Medicine; Radiology; Anatomy; Image (mathematics); Surgery","score_opus":0.04005031118516752,"score_gpt":0.3273231931118297,"score_spread":0.2872728819266622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037002160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95763695,0.0026555497,0.038203634,0.0011971727,0.00008872306,0.0001445984,0.0000024179083,0.000039915343,0.00003106464],"genre_scores_gemma":[0.97251964,0.00069512613,0.025952822,0.0006871446,0.00010731016,0.0000044473145,0.000018420096,0.000011681379,0.0000033907381],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990266,0.000040763654,0.00026435006,0.00018198596,0.00028435414,0.00020193066],"domain_scores_gemma":[0.9992359,0.000038356873,0.00008186071,0.00016215739,0.00007475649,0.0004069448],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034011586,0.00012684191,0.00028846727,0.00010280613,0.00006490964,0.000022606217,0.000032040993,0.00006465328,0.0000059159365],"category_scores_gemma":[0.00007521197,0.00009844945,0.0000400431,0.00012996818,0.00024383307,0.00015706055,0.00004029222,0.00011704138,1.7116405e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034455568,0.0070443866,0.7333278,0.001210687,0.00070315355,0.000263465,0.0027301104,0.00022799999,0.09528058,0.007896279,0.0010556049,0.14991537],"study_design_scores_gemma":[0.0026596028,0.00011918664,0.1608338,0.00048514127,0.00026953884,0.00020003493,0.00003178627,0.83383465,0.0011035805,0.00023145166,0.000093181625,0.00013803178],"about_ca_topic_score_codex":0.000039143564,"about_ca_topic_score_gemma":8.733011e-7,"teacher_disagreement_score":0.83360666,"about_ca_system_score_codex":0.000009658516,"about_ca_system_score_gemma":0.000044685406,"threshold_uncertainty_score":0.40146518},"labels":[],"label_agreement":null},{"id":"W2037874768","doi":"10.1016/j.compmedimag.2009.08.001","title":"Computational aspects in high intensity ultrasonic surgery planning","year":2009,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Ultrasound and Hyperthermia Applications","field":"Engineering","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre","funders":"","keywords":"Transducer; Ultrasonic sensor; Ultrasound; Acoustics; Nonlinear system; Computer science; Time domain; Power (physics); Frequency domain; Materials science; Therapeutic ultrasound; Coupling (piping); Biomedical engineering; Physics; Engineering","score_opus":0.009782240780804951,"score_gpt":0.23123116736717275,"score_spread":0.2214489265863678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037874768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9037754,0.0009266832,0.09232212,0.0021329403,0.00027200516,0.000069049085,0.0000031828972,0.0003380747,0.00016057695],"genre_scores_gemma":[0.99644417,0.00021253763,0.0017546831,0.0014171315,0.000116612704,0.000003534457,0.000039277067,0.000010816754,0.0000012450934],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991718,0.000018251474,0.00022142263,0.000173538,0.00019193917,0.00022307753],"domain_scores_gemma":[0.9993532,0.00034372127,0.000019335142,0.000096123906,0.000028137645,0.00015950474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001901811,0.0001266464,0.0002460372,0.00016249839,0.00006818339,0.00004578011,0.000091996524,0.000063177926,0.000009440318],"category_scores_gemma":[0.000047393907,0.00012580783,0.00004279391,0.000265648,0.00009164581,0.000073025585,0.000013414702,0.00030909196,0.0000026526022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000110225956,0.0008491317,0.21064277,0.00040137256,0.0002628438,0.0012092371,0.0032709953,0.04240864,0.004850288,0.07667217,0.022665372,0.63665694],"study_design_scores_gemma":[0.0007690207,0.00001099121,0.35087833,0.000281033,0.000012383539,0.00027414504,0.000032586537,0.6229338,0.00003963709,0.022447798,0.0019893947,0.0003308669],"about_ca_topic_score_codex":0.000010910341,"about_ca_topic_score_gemma":0.0000018088446,"teacher_disagreement_score":0.6363261,"about_ca_system_score_codex":0.000014596282,"about_ca_system_score_gemma":0.00003086109,"threshold_uncertainty_score":0.5130294},"labels":[],"label_agreement":null},{"id":"W2045224542","doi":"10.1016/j.compmedimag.2004.03.005","title":"A relational-tubular (ReTu) deformable model for vasculature quantification of zebrafish embryo from microangiography image series","year":2004,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Angiogenesis and VEGF in Cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto; City, University of London; City University of Hong Kong","keywords":"Microangiography; Zebrafish; Computer science; Embryo; Series (stratigraphy); Image (mathematics); Computer vision; Artificial intelligence; Anatomy; Computational biology; Biology; Cell biology","score_opus":0.012703864190879332,"score_gpt":0.24670017400972818,"score_spread":0.23399630981884886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045224542","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27477565,0.005466634,0.7184441,0.00090863364,0.00013865034,0.00014726527,0.00008461625,0.00001824481,0.000016179156],"genre_scores_gemma":[0.918503,0.002204232,0.07710847,0.00091660954,0.00024203048,0.000034148292,0.00093385123,0.000030549265,0.000027139124],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904066,0.00002037155,0.0002601509,0.00031736417,0.00018539646,0.0001760777],"domain_scores_gemma":[0.9993597,0.000018959843,0.00010228838,0.00023374584,0.00017176333,0.00011352749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020468482,0.00014532506,0.00019777878,0.00007180743,0.000110891306,0.000024885414,0.00013848013,0.00016293376,0.0000031588843],"category_scores_gemma":[0.000045782897,0.00013227787,0.00024549617,0.0001270202,0.00028370964,0.000018110228,0.000071502174,0.00008195322,2.6162127e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005756036,0.00027468055,0.003383303,0.0002511067,0.00064739084,0.000006704298,0.00045174753,0.0018203168,0.96524936,0.014637784,0.0062643313,0.006437662],"study_design_scores_gemma":[0.014767531,0.0003764381,0.019957233,0.00086152315,0.00061596493,0.0001366303,0.00022905463,0.66297084,0.20535286,0.056663014,0.03631207,0.0017568769],"about_ca_topic_score_codex":0.00002651305,"about_ca_topic_score_gemma":0.000008816142,"teacher_disagreement_score":0.7598965,"about_ca_system_score_codex":0.0000045860666,"about_ca_system_score_gemma":0.00010119524,"threshold_uncertainty_score":0.5394135},"labels":[],"label_agreement":null},{"id":"W2049205912","doi":"10.1016/j.compmedimag.2013.05.006","title":"Low-dose computed tomography via spatially adaptive Monte–Carlo reconstruction","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Ontario Ministry of Economic Development and Innovation","keywords":"Monte Carlo method; Imaging phantom; Noise (video); Image noise; Iterative reconstruction; Computer science; Image quality; Parametric statistics; Computer vision; Artificial intelligence; Physics; Optics; Mathematics; Image (mathematics); Statistics","score_opus":0.01223548495139641,"score_gpt":0.25966143805725905,"score_spread":0.24742595310586266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049205912","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29293525,0.00063227286,0.6709861,0.03204368,0.00062095234,0.0012791707,0.000008434776,0.0010926838,0.00040145934],"genre_scores_gemma":[0.8964646,0.00038510063,0.0958448,0.006684113,0.00040537058,0.00011839909,0.000033258788,0.000037810612,0.00002654724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978483,0.00008640505,0.00052691466,0.00053563254,0.0005890574,0.00041372364],"domain_scores_gemma":[0.9980746,0.00016715571,0.00013803414,0.0004126624,0.0002687091,0.0009388529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032985347,0.00028654333,0.00050496927,0.0002994977,0.0001959607,0.00008494092,0.000208321,0.00017555372,0.00018453968],"category_scores_gemma":[0.000091511174,0.0002414826,0.00017784422,0.0004783407,0.00087927317,0.00016558733,0.00017284536,0.0007143466,0.000018571825],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000762319,0.00048758366,0.007963751,0.00018944615,0.0001593917,0.000111150184,0.00015574999,0.0000012195975,0.0047010556,0.0015519965,0.0188545,0.9657479],"study_design_scores_gemma":[0.0032870308,0.00020766827,0.024124095,0.0010990623,0.00013527642,0.0014983936,0.00004740274,0.95904195,0.00058989634,0.0050280737,0.0044691875,0.00047194315],"about_ca_topic_score_codex":0.00026849846,"about_ca_topic_score_gemma":0.000003174631,"teacher_disagreement_score":0.965276,"about_ca_system_score_codex":0.00002069673,"about_ca_system_score_gemma":0.00010677077,"threshold_uncertainty_score":0.98473746},"labels":[],"label_agreement":null},{"id":"W2050278510","doi":"10.1016/j.compmedimag.2013.08.005","title":"A local angle compensation method based on kinematics constraints for non-invasive vascular axial strain computations on human carotid arteries","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Medicine; Ultrasound; Kinematics; Stenosis; Elastography; Anatomy; Biomedical engineering; Mathematics; Radiology; Physics","score_opus":0.0177145845842777,"score_gpt":0.2991867574167089,"score_spread":0.2814721728324312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050278510","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06906817,0.000017260401,0.9252213,0.0040556174,0.00029617452,0.00095280557,0.00006337139,0.00016399087,0.00016127389],"genre_scores_gemma":[0.85215646,0.000014133705,0.13945231,0.007385145,0.00023004824,0.00011607771,0.00059548113,0.000043984648,0.0000063638035],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978434,0.00015694792,0.00048337353,0.00048351815,0.0006166513,0.00041609537],"domain_scores_gemma":[0.99749625,0.0012645238,0.00013454111,0.00030934034,0.00029733707,0.00049799157],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000540572,0.00033345228,0.00059241,0.0004186442,0.00038096585,0.00013583366,0.00013062642,0.00013172309,0.000060199196],"category_scores_gemma":[0.00029513575,0.00028878788,0.00027497194,0.0003001486,0.0011068884,0.000086236185,0.000029597808,0.00044768403,0.0000066732705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014838253,0.01256053,0.049262773,0.011303909,0.0038340278,0.0003267631,0.015204222,0.008258928,0.109444484,0.04733168,0.05032603,0.6906628],"study_design_scores_gemma":[0.012203124,0.0013338863,0.025694273,0.0019959216,0.0002977539,0.0001713499,0.000841775,0.9498839,0.00037102617,0.0049833297,0.0015866576,0.0006370497],"about_ca_topic_score_codex":0.00004137787,"about_ca_topic_score_gemma":0.0000035056762,"teacher_disagreement_score":0.94162494,"about_ca_system_score_codex":0.000026895255,"about_ca_system_score_gemma":0.00016396458,"threshold_uncertainty_score":0.9999564},"labels":[],"label_agreement":null},{"id":"W2055618923","doi":"10.1016/j.compmedimag.2004.05.008","title":"Imaging diagnosis of congenital uterine malformation","year":2004,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Gynecological conditions and treatments","field":"Medicine","cited_by":90,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University Medical Centre","funders":"","keywords":"Medicine; Hysteroscopy; Infertility; Magnetic resonance imaging; Laparoscopy; Obstetrics; Hysterosalpingography; Gynecology; Uterus; Adenomyosis; Pregnancy; Radiology","score_opus":0.013140402450827843,"score_gpt":0.2862468604052056,"score_spread":0.2731064579543777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055618923","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.979232,0.000571447,0.01507545,0.004433235,0.00016733934,0.00016543886,0.000014986549,0.00007449439,0.00026559742],"genre_scores_gemma":[0.9945027,0.00033148465,0.0037125074,0.0013169517,0.000033158616,0.000021324542,0.00006739955,0.000008296459,0.0000061535484],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99910164,0.000019748666,0.00027332013,0.00017022056,0.00025967805,0.0001753955],"domain_scores_gemma":[0.99938583,0.00008624048,0.00006608426,0.00012864139,0.00008757467,0.0002456125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012976902,0.000120619065,0.00026053583,0.00013043535,0.000078676996,0.000019225216,0.000057105688,0.000045601933,0.000101658545],"category_scores_gemma":[0.000109427674,0.00009338879,0.00008176197,0.00016739086,0.00028938983,0.0001050009,0.00007496303,0.00015179893,0.0000041824987],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078445264,0.0014538304,0.7241151,0.00040018378,0.00029595027,0.0012278736,0.00035684183,0.0000034119014,0.0006752184,0.011750105,0.00027797557,0.25936508],"study_design_scores_gemma":[0.016704392,0.00040645388,0.9516302,0.0006865147,0.00030250443,0.0008992078,0.000115179435,0.011156427,0.0012587181,0.012178366,0.004308336,0.0003537499],"about_ca_topic_score_codex":0.000036459445,"about_ca_topic_score_gemma":0.0000016798062,"teacher_disagreement_score":0.25901133,"about_ca_system_score_codex":0.000017448285,"about_ca_system_score_gemma":0.00005228496,"threshold_uncertainty_score":0.38082844},"labels":[],"label_agreement":null},{"id":"W2057477305","doi":"10.1016/j.compmedimag.2014.07.002","title":"Detection of temporal lobe epilepsy using support vector machines in multi-parametric quantitative MR imaging","year":2014,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Robarts Clinical Trials; Western University","funders":"Canadian Institutes of Health Research","keywords":"Support vector machine; Pattern recognition (psychology); Artificial intelligence; Epilepsy; Temporal lobe; Computer science; Diffusion MRI; Parametric statistics; Principal component analysis; Fractional anisotropy; Magnetic resonance imaging; Mathematics; Radiology; Medicine; Psychology; Neuroscience; Statistics","score_opus":0.0627627876946144,"score_gpt":0.3776114421191385,"score_spread":0.3148486544245241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057477305","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33848885,0.00025164138,0.6598964,0.0009073418,0.000108715096,0.00020815812,0.000003977165,0.00011810361,0.0000168045],"genre_scores_gemma":[0.8905671,0.00012077271,0.10853032,0.000675526,0.000049261784,0.000011833626,0.000015901416,0.00002561566,0.000003633655],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985082,0.00009333567,0.00046581117,0.000384473,0.00029376944,0.0002543941],"domain_scores_gemma":[0.9989918,0.000260519,0.00017331481,0.0002551773,0.000111081165,0.00020811032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050871255,0.00018818144,0.00044133278,0.0005158261,0.00009027006,0.000019690602,0.00011852612,0.00005842856,0.000005821345],"category_scores_gemma":[0.00046740673,0.00017142571,0.00008887058,0.0007759703,0.0003935531,0.00010627927,0.000104403414,0.00041901102,6.738323e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002190781,0.00059292174,0.75775355,0.00050820626,0.000040881925,0.00014429349,0.00032076915,0.000029006113,0.058031686,0.003477934,0.000090810056,0.17879088],"study_design_scores_gemma":[0.0018673987,0.00008419598,0.06005863,0.0002880491,0.000040424286,0.00025067074,0.000021404087,0.9341142,0.0011556221,0.0011855598,0.00076047675,0.00017332265],"about_ca_topic_score_codex":0.00017151119,"about_ca_topic_score_gemma":0.0000067420397,"teacher_disagreement_score":0.93408525,"about_ca_system_score_codex":0.00002276102,"about_ca_system_score_gemma":0.000056172827,"threshold_uncertainty_score":0.6990537},"labels":[],"label_agreement":null},{"id":"W2060326747","doi":"10.1016/j.compmedimag.2005.01.001","title":"Study of myocardial glucose metabolism in rats with PET using wavelet analysis techniques","year":2005,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Wavelet; Artificial intelligence; Parametric statistics; Pattern recognition (psychology); Image resolution; Pixel; Computer vision; Computer science; Noise (video); Mathematics; Image quality; Image (mathematics); Statistics","score_opus":0.018522484040619545,"score_gpt":0.31907692246149416,"score_spread":0.3005544384208746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060326747","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92892885,0.00028768508,0.06634443,0.003695242,0.000024575378,0.0004968826,0.00000393667,0.00015925149,0.000059139453],"genre_scores_gemma":[0.8985365,0.00031668646,0.099778675,0.0011449605,0.00014997937,0.000034558325,0.00001702135,0.000018032333,0.0000036124113],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980919,0.00010412213,0.0005140295,0.00039274976,0.0006331332,0.00026408877],"domain_scores_gemma":[0.99891937,0.00010016535,0.0001252757,0.0003928461,0.0001248747,0.00033746404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069240003,0.00020010678,0.00077455485,0.0006245567,0.000066283246,0.000024309902,0.00015881621,0.000061194216,0.000017465636],"category_scores_gemma":[0.00007659335,0.00015069667,0.00011124251,0.0013323285,0.00036455033,0.00007742595,0.00012797405,0.0004589068,2.3225164e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012150952,0.0147871245,0.3128236,0.0006233739,0.0047804625,0.003493742,0.0055162786,0.000046947363,0.032200504,0.005720941,0.0032838685,0.6155081],"study_design_scores_gemma":[0.014560728,0.0007780336,0.11228918,0.0013464622,0.0065295757,0.0017222401,0.00097330246,0.83567107,0.008126087,0.00068428856,0.016092818,0.0012262277],"about_ca_topic_score_codex":0.00020459264,"about_ca_topic_score_gemma":0.000025512298,"teacher_disagreement_score":0.8356241,"about_ca_system_score_codex":0.000018888582,"about_ca_system_score_gemma":0.00010674238,"threshold_uncertainty_score":0.6145232},"labels":[],"label_agreement":null},{"id":"W2062322640","doi":"10.1016/j.compmedimag.2012.04.005","title":"An edge-region force guided active shape approach for automatic lung field detection in chest radiographs","year":2012,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Segmentation; Radiography; Computer science; Artificial intelligence; Active shape model; Computer vision; Lung; Field (mathematics); Edge detection; Sensitivity (control systems); Radiology; Image segmentation; Computer-aided diagnosis; Pattern recognition (psychology); Image processing; Medicine; Image (mathematics); Mathematics; Engineering","score_opus":0.020988304581501274,"score_gpt":0.30864239393535703,"score_spread":0.2876540893538558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062322640","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014454716,0.00034075955,0.9829914,0.0007406468,0.00039481506,0.00055728375,8.316796e-7,0.00047348265,0.000046075816],"genre_scores_gemma":[0.68742526,0.00013071069,0.30910584,0.0029124587,0.00021382127,0.00017105804,0.000019138783,0.000018135499,0.0000036021602],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979815,0.00020207287,0.00043094959,0.00045357595,0.00044153252,0.00049036427],"domain_scores_gemma":[0.998474,0.00040815186,0.00013679787,0.00037910495,0.000079683865,0.00052228215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010140793,0.00021832953,0.0003131304,0.00044218852,0.00016032114,0.00014439087,0.0005913903,0.00015940961,0.0000050730914],"category_scores_gemma":[0.00027965955,0.00020083784,0.00009841163,0.0006628054,0.00019694056,0.0010514669,0.0001539675,0.00035702027,3.0841184e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014523352,0.00021529636,0.0020679734,0.00016666253,0.000019204484,0.000008069984,0.00089830183,7.791135e-7,0.0011592314,0.00079284084,0.00077489275,0.99388224],"study_design_scores_gemma":[0.0011960266,0.00008111218,0.0043101097,0.00010531138,0.000016553164,0.00011653918,0.000049784376,0.987243,0.005285296,0.001249737,0.00010032712,0.00024619338],"about_ca_topic_score_codex":0.000026231972,"about_ca_topic_score_gemma":0.0000015065933,"teacher_disagreement_score":0.993636,"about_ca_system_score_codex":0.000034900557,"about_ca_system_score_gemma":0.000052340423,"threshold_uncertainty_score":0.818993},"labels":[],"label_agreement":null},{"id":"W2063533408","doi":"10.1016/j.compmedimag.2013.09.006","title":"Assessment of inflammation in large arteries with 18F-FDG-PET in elderly","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Medicine; Coronary arteries; Aorta; Calcification; Nuclear medicine; Positron emission tomography; Artery; Fluorodeoxyglucose; Radiology; Internal medicine","score_opus":0.006180032040744384,"score_gpt":0.2717266846035698,"score_spread":0.2655466525628254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063533408","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9802163,0.00027920664,0.014400159,0.0042490903,0.00012982036,0.0002754561,0.0000032299115,0.000041635998,0.00040508382],"genre_scores_gemma":[0.99456155,0.00020955606,0.0044516562,0.0006277396,0.00006822075,0.000027908836,0.000034187437,0.000012668642,0.0000064808323],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99871767,0.00006656007,0.00036519472,0.00021135877,0.00038714142,0.00025207354],"domain_scores_gemma":[0.99922353,0.00024005608,0.000073852425,0.0001804573,0.00010506034,0.00017704684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042792218,0.00013714973,0.0004113885,0.00030192817,0.000026477877,0.000036952646,0.000057613517,0.00003771301,0.000022935967],"category_scores_gemma":[0.00017364699,0.00011024518,0.00004379148,0.00031702442,0.00022596981,0.00012831397,0.00005577707,0.00034455652,0.0000011851339],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029980403,0.00018438991,0.9700039,0.00023951045,0.000021924661,0.00038156938,0.00028468645,0.0000036499234,0.0005518098,0.0012679286,0.00027371335,0.02675694],"study_design_scores_gemma":[0.0048753605,0.000118782846,0.9345927,0.0010490223,0.000026498017,0.00024711897,0.00017267477,0.057630293,0.000059636797,0.0005062146,0.0005889294,0.0001327262],"about_ca_topic_score_codex":0.00015776834,"about_ca_topic_score_gemma":0.000033575427,"teacher_disagreement_score":0.057626646,"about_ca_system_score_codex":0.000017850378,"about_ca_system_score_gemma":0.00014693425,"threshold_uncertainty_score":0.4495668},"labels":[],"label_agreement":null},{"id":"W2064866805","doi":"10.1016/j.compmedimag.2009.10.003","title":"An integrated and interactive decision support system for automated melanoma recognition of dermoscopic images","year":2009,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Computer science; Thresholding; Pattern recognition (psychology); Context (archaeology); Segmentation; Precision and recall; Feature (linguistics); Computer vision; Image (mathematics)","score_opus":0.011344092323520506,"score_gpt":0.2937157325578684,"score_spread":0.2823716402343479,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064866805","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6355214,0.00018481295,0.36160836,0.0010234601,0.0004565678,0.0005780917,0.000021126563,0.0005038045,0.000102343096],"genre_scores_gemma":[0.9804188,0.00014553375,0.018492304,0.00073900184,0.00006517028,0.00001023287,0.00010620227,0.000011822444,0.000010945892],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989531,0.000052836327,0.00033709925,0.00028109102,0.00021812045,0.00015773681],"domain_scores_gemma":[0.9991607,0.00015306109,0.00010363054,0.0001421288,0.00018159543,0.00025886888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029683032,0.0001446235,0.0003536152,0.00024764115,0.00007465722,0.000041232404,0.000056862733,0.00007876978,0.0000121581625],"category_scores_gemma":[0.00012729876,0.000118391756,0.00005296355,0.0001589327,0.00011782265,0.00008873525,0.000026329792,0.00014881552,7.220008e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075881474,0.00019135338,0.00045756262,0.0003029285,0.00006757479,0.00018499837,0.00019470687,3.2670155e-7,0.006206402,0.00010424828,0.0010706648,0.9904604],"study_design_scores_gemma":[0.015430602,0.004333198,0.03457293,0.004053612,0.00058310246,0.006003051,0.0015287867,0.9177765,0.007734807,0.00093680754,0.0064744805,0.0005720896],"about_ca_topic_score_codex":0.000016547661,"about_ca_topic_score_gemma":0.000001895936,"teacher_disagreement_score":0.9898883,"about_ca_system_score_codex":0.00002159744,"about_ca_system_score_gemma":0.000045881116,"threshold_uncertainty_score":0.48278755},"labels":[],"label_agreement":null},{"id":"W2067018786","doi":"10.1016/j.compmedimag.2007.10.001","title":"Medical image retrieval with probabilistic multi-class support vector machine classifiers and adaptive similarity fusion","year":2007,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Artificial intelligence; Support vector machine; Computer science; Pattern recognition (psychology); Image retrieval; Probabilistic logic; Feature (linguistics); Similarity (geometry); Feature vector; Precision and recall; Data mining; Image (mathematics); Machine learning","score_opus":0.01681605932782204,"score_gpt":0.2747772097401341,"score_spread":0.25796115041231205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067018786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005830987,0.00034863813,0.9857464,0.006730768,0.0003234676,0.00032719786,0.000007559576,0.000528447,0.00015655205],"genre_scores_gemma":[0.7937886,0.0010701194,0.19907843,0.0055517172,0.00031965828,0.000015167195,0.000041969135,0.000054598877,0.00007973033],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99650294,0.00017155166,0.0005375924,0.00083015754,0.0013863334,0.00057142874],"domain_scores_gemma":[0.9974156,0.00051524193,0.00017570627,0.0004629479,0.0003892085,0.001041267],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002419124,0.00034439808,0.0004469397,0.00024078794,0.0003258528,0.00022126475,0.00070168317,0.00025484018,0.000026684815],"category_scores_gemma":[0.0009229707,0.00025942305,0.000075610646,0.0007238412,0.0014719899,0.0003980858,0.0005942414,0.0009169849,0.0000024454082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020098733,0.0024743737,0.011237802,0.0009913595,0.0003352376,0.005435407,0.0031857758,3.8777435e-7,0.010620597,0.12926106,0.0032912777,0.83115685],"study_design_scores_gemma":[0.004855457,0.00060877437,0.02222131,0.00044087184,0.00006158711,0.0009842551,0.00008066403,0.9556401,0.0028777309,0.0026835364,0.008618059,0.0009276927],"about_ca_topic_score_codex":0.000029614002,"about_ca_topic_score_gemma":0.00001687467,"teacher_disagreement_score":0.95563966,"about_ca_system_score_codex":0.00004387417,"about_ca_system_score_gemma":0.00033821564,"threshold_uncertainty_score":0.9999858},"labels":[],"label_agreement":null},{"id":"W2070735882","doi":"10.1016/s0895-6111(00)00076-8","title":"Boundary detection of retinoblastoma tumors with neural networks","year":2001,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Ocular Oncology and Treatments","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Retinoblastoma; Computer science; Artificial neural network; Artificial intelligence; Boundary (topology); Pattern recognition (psychology); Mathematics","score_opus":0.006914240754128267,"score_gpt":0.2523405248095982,"score_spread":0.2454262840554699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070735882","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9426132,0.0009639118,0.05456226,0.0013722195,0.00018179514,0.00012493109,5.1753915e-7,0.00007067955,0.000110508074],"genre_scores_gemma":[0.9978698,0.0002523191,0.00070359913,0.0010111348,0.000118626616,0.0000045838674,0.000011052623,0.000012141016,0.000016767617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914134,0.000055030403,0.00018578173,0.00019603128,0.00023313082,0.00018870061],"domain_scores_gemma":[0.9994396,0.0000732752,0.00006761339,0.00013757548,0.000057557914,0.00022440786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016008355,0.00012025379,0.00028319712,0.0000955218,0.00009949971,0.000010403446,0.0000460261,0.00008431725,0.000011745922],"category_scores_gemma":[0.00003224054,0.00008734045,0.00005389171,0.00020822165,0.0005261298,0.00004440512,0.000037882106,0.00029575315,4.8682307e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020911773,0.00052177155,0.48838523,0.000135139,0.0003058709,0.004212423,0.00015419538,0.000013720137,0.00079160655,0.00013896891,0.0001251492,0.5031248],"study_design_scores_gemma":[0.011079398,0.0015528693,0.4361452,0.0006519627,0.0003388556,0.010577992,0.00005301692,0.5354761,0.00030523443,0.00026655954,0.003298911,0.0002539591],"about_ca_topic_score_codex":0.00001668128,"about_ca_topic_score_gemma":0.0000062326276,"teacher_disagreement_score":0.5354623,"about_ca_system_score_codex":0.000009405322,"about_ca_system_score_gemma":0.00005007659,"threshold_uncertainty_score":0.356164},"labels":[],"label_agreement":null},{"id":"W2072891925","doi":"10.1016/j.compmedimag.2012.05.002","title":"Extraction of time activity curves from gated FDG-PET images for small animals’ heart studies","year":2012,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bishop's University; Université de Sherbrooke","funders":"","keywords":"Computer science; Cardiac PET; Sampling (signal processing); Blood sampling; Standardized uptake value; Artificial intelligence; Nuclear medicine; Biomedical engineering; Positron emission tomography; Pattern recognition (psychology); Computer vision; Medicine; Internal medicine","score_opus":0.05125203526879301,"score_gpt":0.37317731965042716,"score_spread":0.32192528438163415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072891925","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76909375,0.013552705,0.1670332,0.048438124,0.0003372039,0.0009420796,0.00008675961,0.0004523784,0.00006377537],"genre_scores_gemma":[0.8881739,0.007984031,0.09910721,0.0039055105,0.0005361223,0.000087108856,0.00011521216,0.000037486545,0.000053429587],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866754,0.00007928764,0.00034287,0.00027882593,0.00032431475,0.0003071719],"domain_scores_gemma":[0.99818385,0.0007852276,0.00013764545,0.0002616022,0.00020632784,0.00042534794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078512734,0.00018914469,0.00059155683,0.00009982136,0.000103546416,0.00001351996,0.000101109705,0.00006780324,0.000039363433],"category_scores_gemma":[0.0006947562,0.000151776,0.00013461555,0.00018907577,0.00053912523,0.000101056125,0.00010533983,0.00030971694,0.0000023509965],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000483245,0.001968644,0.020580754,0.003114469,0.00071290234,0.00004959213,0.00039638035,1.1465488e-7,0.59449315,0.0009822708,0.28544778,0.091770716],"study_design_scores_gemma":[0.019732656,0.0012705238,0.21498722,0.023264728,0.0038728744,0.003158239,0.00042008943,0.20926298,0.1583466,0.011868491,0.3511088,0.002706802],"about_ca_topic_score_codex":0.000063711064,"about_ca_topic_score_gemma":4.2025405e-7,"teacher_disagreement_score":0.43614653,"about_ca_system_score_codex":0.00001431567,"about_ca_system_score_gemma":0.000058490416,"threshold_uncertainty_score":0.61892456},"labels":[],"label_agreement":null},{"id":"W2073252747","doi":"10.1016/j.compmedimag.2008.05.001","title":"Optimal 3D reconstruction of coronary arteries for 3D clinical assessment","year":2008,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"RANSAC; Outlier; Frenet–Serret formulas; Computer vision; Constraint (computer-aided design); Artificial intelligence; Coronary arteries; Fluoroscopy; Pixel; Curvature; 3D reconstruction; Mathematics; Computer science; Artery; Image (mathematics); Medicine; Radiology; Geometry; Surgery","score_opus":0.033690365866199515,"score_gpt":0.3499853660381664,"score_spread":0.3162950001719669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073252747","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03243507,0.00030581016,0.9638462,0.0017532022,0.0012875741,0.00015013274,0.000003559353,0.00013286313,0.00008555147],"genre_scores_gemma":[0.10669991,0.0011921902,0.89046496,0.0014512757,0.00014937106,0.000011176291,0.000007035763,0.000010889396,0.000013173011],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818164,0.00010910058,0.0006128471,0.00045405072,0.00037171537,0.00027067063],"domain_scores_gemma":[0.9985963,0.0004556128,0.00019092619,0.00032214535,0.00016197725,0.00027300479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065612065,0.00016492745,0.00039730693,0.00013273406,0.00024594413,0.000044003074,0.00038958475,0.00007493611,0.00000836484],"category_scores_gemma":[0.00013854848,0.00014734376,0.00012580781,0.00020528471,0.000850529,0.00043996706,0.0002909223,0.00029836557,6.5319466e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029029838,0.00010528762,0.01131394,0.000037513793,0.000023617815,0.00004348638,0.00013408138,0.000004984942,0.000109093045,0.003044945,0.00067954854,0.9844745],"study_design_scores_gemma":[0.0019269291,0.00014985498,0.020304399,0.0001303819,0.0000103420225,0.0009791104,0.000024589182,0.9645227,0.000030109535,0.0012443463,0.01047842,0.00019882673],"about_ca_topic_score_codex":0.0000024795625,"about_ca_topic_score_gemma":1.9720385e-7,"teacher_disagreement_score":0.98427564,"about_ca_system_score_codex":0.0000093918015,"about_ca_system_score_gemma":0.00018068212,"threshold_uncertainty_score":0.6008504},"labels":[],"label_agreement":null},{"id":"W2078972258","doi":"10.1016/j.compmedimag.2014.06.013","title":"Real-time bronchoscope three-dimensional motion estimation using multiple sensor-driven alignment of CT images and electromagnetic measurements","year":2014,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Japan Society for the Promotion of Science","keywords":"Fiducial marker; Computer vision; Initialization; Computer science; Artificial intelligence; Imaging phantom; Tracking (education); Match moving; Image registration; Motion (physics); Image (mathematics); Medicine; Radiology","score_opus":0.012171042661849403,"score_gpt":0.22719601746527435,"score_spread":0.21502497480342495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078972258","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50139344,0.000108496184,0.4981566,0.00007290643,0.000096124175,0.000090162495,0.0000020253783,0.000068347545,0.00001191404],"genre_scores_gemma":[0.9432372,0.0001149954,0.056481577,0.000055125874,0.000046999663,0.000001988178,0.000036596684,0.00002397781,0.0000015512868],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988574,0.000072761395,0.00028896573,0.00020061097,0.00038843934,0.00019181462],"domain_scores_gemma":[0.9994841,0.00010972582,0.000059107984,0.00012569506,0.00006988351,0.00015149431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028703274,0.00015730524,0.0002387427,0.000116601244,0.00008180195,0.000036093348,0.000056816898,0.000046239118,0.0000067907413],"category_scores_gemma":[0.0000750984,0.00015393872,0.0000325262,0.00011674756,0.00013417234,0.00007491901,0.000035446523,0.00010620316,7.510472e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003442504,0.00012584895,0.015995517,0.0005014931,0.000120695746,0.000015674488,0.00010838382,0.23438181,0.6565373,0.00022818062,0.00030255408,0.091648094],"study_design_scores_gemma":[0.00097304716,0.000041388386,0.004704674,0.00019552356,0.00004053922,0.0000296054,0.0000015812725,0.9902284,0.0034330143,0.00019203748,0.000016619199,0.00014357244],"about_ca_topic_score_codex":0.000061010498,"about_ca_topic_score_gemma":0.0000021544838,"teacher_disagreement_score":0.75584656,"about_ca_system_score_codex":0.000020951287,"about_ca_system_score_gemma":0.000014905516,"threshold_uncertainty_score":0.6277439},"labels":[],"label_agreement":null},{"id":"W2079224110","doi":"10.1016/j.compmedimag.2011.01.005","title":"Quantization and analysis of hippocampal morphometric changes due to dementia of Alzheimer type using metric distances based on large deformation diffeomorphic metric mapping","year":2011,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Alzheimer's disease research and treatments","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Center for Research Resources; National Institute on Aging","keywords":"Metric (unit); Mathematics; Measure (data warehouse); Pattern recognition (psychology); Artificial intelligence; Shape analysis (program analysis); Fisher information metric; Metric space; Quantization (signal processing); Computer science; Mathematical analysis; Injective metric space; Statistics; Data mining","score_opus":0.06143497301841136,"score_gpt":0.3191383658844442,"score_spread":0.25770339286603283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079224110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8438492,0.012387651,0.1431895,0.00011788688,0.00007891919,0.0002928681,0.00004025441,0.000024675766,0.000019078881],"genre_scores_gemma":[0.9941057,0.00059745146,0.0049142144,0.00020781269,0.000018056136,0.0000056048725,0.00013911491,0.000011863448,1.8914062e-7],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983206,0.00011082303,0.00034961945,0.0002576234,0.0007081037,0.00025325618],"domain_scores_gemma":[0.9988176,0.00017144224,0.00018355822,0.00018676747,0.00024283718,0.00039778958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005546164,0.00016037075,0.0005646888,0.0041963123,0.000088841276,0.000015817364,0.000073625815,0.000061394116,0.00003877571],"category_scores_gemma":[0.0002793776,0.00012684918,0.00009392271,0.007174304,0.00014402674,0.0000726044,0.00006796009,0.00011192419,4.869647e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007081589,0.0014466231,0.9241812,0.000582134,0.02006996,0.00014133356,0.0005380971,0.00002386539,0.0003794413,0.00039386653,0.000032105774,0.051503204],"study_design_scores_gemma":[0.001971312,0.00028611528,0.54530185,0.00024420285,0.004990177,0.000010258783,0.00006513082,0.44653937,0.00040141208,0.000052542426,0.000011105118,0.00012651064],"about_ca_topic_score_codex":0.00008877741,"about_ca_topic_score_gemma":0.000004704918,"teacher_disagreement_score":0.4465155,"about_ca_system_score_codex":0.000014472299,"about_ca_system_score_gemma":0.000072051684,"threshold_uncertainty_score":0.5172759},"labels":[],"label_agreement":null},{"id":"W2086297115","doi":"10.1016/j.compmedimag.2015.01.004","title":"Right ventricular segmentation in cardiac MRI with moving mesh correspondences","year":2015,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Congenital Heart Disease Studies","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CARE Canada; Western University; Canadian VIGOUR Centre; University of Alberta","funders":"Servier Canada","keywords":"Segmentation; Endocardium; Ventricle; Cardiac cycle; Computer science; Artificial intelligence; Magnetic resonance imaging; Level set (data structures); Robustness (evolution); Computer vision; Dice; Image segmentation; Pattern recognition (psychology); Cardiac magnetic resonance; Hypoplastic left heart syndrome; Mathematics; Heart disease; Medicine; Cardiology; Radiology; Geometry","score_opus":0.011895390285587575,"score_gpt":0.27772663227681943,"score_spread":0.26583124199123187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086297115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98099613,0.006786702,0.007464753,0.003614582,0.00045100754,0.00035224142,0.0000044774724,0.00009629709,0.00023379801],"genre_scores_gemma":[0.9957981,0.00040129368,0.00263553,0.0009050573,0.00016280901,0.00002266648,0.000021266858,0.00001344059,0.000039818708],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986529,0.000093132396,0.00019201594,0.00025069807,0.00059345213,0.00021783054],"domain_scores_gemma":[0.9991881,0.00011969308,0.000030223115,0.00012291201,0.00010709196,0.0004319705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004209229,0.00013303262,0.00032028175,0.00018583675,0.000062006686,0.000030221536,0.000052723983,0.000040427512,0.00000991336],"category_scores_gemma":[0.00012000389,0.00009768526,0.000048892864,0.00036707494,0.0002592866,0.00009330469,0.00008222622,0.00020152582,0.0000027138042],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007236247,0.00027333756,0.90875566,0.00027307222,0.0002161641,0.0063954927,0.001407167,0.0000019257282,0.00012854043,0.00031836625,0.0043485155,0.07715816],"study_design_scores_gemma":[0.037676245,0.0013039188,0.5388152,0.0053725555,0.0012440989,0.0025493177,0.006934138,0.367982,0.0007152369,0.0030908203,0.032486357,0.0018301114],"about_ca_topic_score_codex":0.000046433233,"about_ca_topic_score_gemma":0.000009996128,"teacher_disagreement_score":0.36994043,"about_ca_system_score_codex":0.000030079293,"about_ca_system_score_gemma":0.00018409004,"threshold_uncertainty_score":0.39834893},"labels":[],"label_agreement":null},{"id":"W2090256705","doi":"10.1016/j.compmedimag.2013.01.009","title":"The state of the art of visualization in mixed reality image guided surgery","year":2013,"lang":"en","type":"review","venue":"Computerized Medical Imaging and Graphics","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; California HIV/AIDS Research Program","keywords":"Visualization; Computer science; Focus (optics); Mixed reality; Human–computer interaction; Data science; Augmented reality; Data visualization; Information visualization; Interface (matter); Domain (mathematical analysis); Graphical user interface; Field (mathematics); Information retrieval; Data mining; Mathematics","score_opus":0.04930875546966439,"score_gpt":0.3635457187806287,"score_spread":0.3142369633109643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090256705","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028354672,0.49342564,0.50497985,0.00032073108,0.00063192594,0.0005051546,0.0000078427265,0.00008491607,0.000015570786],"genre_scores_gemma":[0.00012546177,0.9982617,0.0013196092,0.00014713666,0.000040151433,0.000043737862,0.000024016343,0.000023793236,0.000014430625],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99555486,0.0011055729,0.0017119884,0.00049702916,0.00080679165,0.00032376256],"domain_scores_gemma":[0.99569684,0.0016786343,0.001100695,0.0010303138,0.000347989,0.00014555246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029714864,0.00035494188,0.0013332572,0.00046537645,0.00015159672,0.0002068673,0.0016772684,0.00015530962,0.0000016191108],"category_scores_gemma":[0.0004180399,0.0002075725,0.00047473374,0.0019527916,0.0007425304,0.00019761751,0.0012277304,0.00043511152,5.4511924e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010117146,0.00006368524,0.000047852915,0.0025531005,0.00003874039,0.000004327284,0.00007069319,1.0845169e-7,0.0000011075567,0.04465877,0.00537269,0.9471879],"study_design_scores_gemma":[0.00033069105,0.000022997183,0.00041434867,0.013976975,0.000072021365,0.00006730707,0.000002804078,0.21101375,0.00003320036,0.020415192,0.7531645,0.00048619966],"about_ca_topic_score_codex":0.00007866024,"about_ca_topic_score_gemma":0.00001203051,"teacher_disagreement_score":0.9467017,"about_ca_system_score_codex":0.000017513188,"about_ca_system_score_gemma":0.0004454876,"threshold_uncertainty_score":0.8464561},"labels":[],"label_agreement":null},{"id":"W2097572665","doi":"10.1016/j.compmedimag.2009.04.008","title":"External landmark and head-shape-based functional data normalization","year":2009,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Down Syndrome Research Foundation; Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Landmark; Normalization (sociology); Spatial normalization; Computer vision; Transformation (genetics); Image registration; Pattern recognition (psychology); Pooling; Magnetoencephalography; Voxel; Image (mathematics); Electroencephalography; Medicine","score_opus":0.05350357437842966,"score_gpt":0.2990326230775273,"score_spread":0.24552904869909764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097572665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32729924,0.0012856707,0.6044853,0.06483405,0.0012492818,0.00022309968,0.000046465375,0.00033346898,0.00024343742],"genre_scores_gemma":[0.9624857,0.00029395346,0.0015041118,0.035318673,0.00033324218,0.0000031750928,0.000037147558,0.000009269601,0.0000147701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998504,0.00011287853,0.00017229318,0.0005275728,0.00048418972,0.00019907902],"domain_scores_gemma":[0.9978901,0.0015949574,0.00005155432,0.00023963576,0.000040564624,0.00018319176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041166728,0.0001393185,0.00016468088,0.000112312395,0.00030887788,0.000100097466,0.00019114194,0.00004582398,0.000024344536],"category_scores_gemma":[0.0022071316,0.00012294397,0.00002471276,0.00021070239,0.0003209351,0.00024603153,0.00019553278,0.0002150381,0.0000019257784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069352676,0.00067789404,0.057848834,0.0001927579,0.000038863833,0.00040628138,0.0002032017,0.000054339842,0.032197278,0.02659,0.034666695,0.8464303],"study_design_scores_gemma":[0.0022861708,0.00009526712,0.117497094,0.00014038454,0.000021392052,0.00026945287,0.0000065265745,0.85775805,0.00023679975,0.0042754323,0.017158844,0.0002546187],"about_ca_topic_score_codex":0.000008159821,"about_ca_topic_score_gemma":0.0000035116716,"teacher_disagreement_score":0.8577037,"about_ca_system_score_codex":0.000007117272,"about_ca_system_score_gemma":0.000057159374,"threshold_uncertainty_score":0.50135094},"labels":[],"label_agreement":null},{"id":"W2106383675","doi":"10.1016/j.compmedimag.2010.02.002","title":"Fast construction of panoramic images for cystoscopic exploration","year":2010,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Ligue Contre le Cancer; Consejo Nacional de Ciencia y Tecnología","keywords":"Artificial intelligence; Computer vision; Initialization; Computer science; Pixel; Translation (biology); Imaging phantom; Visualization; Coordinate system; Cystoscopy; Image registration; Image (mathematics); Nuclear medicine; Medicine; Anatomy","score_opus":0.01234504526581599,"score_gpt":0.2818790975941255,"score_spread":0.2695340523283095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106383675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6282704,0.00015299031,0.36837456,0.0018994907,0.0009386314,0.00020166588,0.0000057346924,0.000090314556,0.00006623454],"genre_scores_gemma":[0.9751392,0.00012429092,0.024125906,0.00025256176,0.00028737882,0.000021091528,0.000026805237,0.000010840547,0.000011939361],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924695,0.000018371064,0.00021367443,0.00019113711,0.00020677541,0.00012307434],"domain_scores_gemma":[0.9994039,0.00010029575,0.00008036731,0.0001239301,0.00014701438,0.00014451769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021532386,0.00009248701,0.00022174713,0.00013584268,0.00007902352,0.000020423362,0.000041717303,0.000084567444,0.00000887434],"category_scores_gemma":[0.00018506993,0.00008178671,0.00006475381,0.0001558941,0.00032687702,0.00009114696,0.000026355625,0.0002535119,3.1932905e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014301441,0.00010693868,0.009373112,0.00047210781,0.000059783222,0.00001117881,0.0002742978,9.948926e-7,0.088019274,0.0025315322,0.000659925,0.8970607],"study_design_scores_gemma":[0.041319747,0.006451502,0.09560953,0.002666775,0.00095351395,0.0043495735,0.0012776245,0.6366362,0.14699967,0.030195564,0.032009587,0.0015307426],"about_ca_topic_score_codex":0.000029059343,"about_ca_topic_score_gemma":0.0000072138287,"teacher_disagreement_score":0.89553,"about_ca_system_score_codex":0.0000053280964,"about_ca_system_score_gemma":0.000077293495,"threshold_uncertainty_score":0.33351654},"labels":[],"label_agreement":null},{"id":"W2110343138","doi":"10.1016/j.compmedimag.2013.12.002","title":"Automated classification of four types of developmental odontogenic cysts","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Oral and Maxillofacial Pathology","field":"Dentistry","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Odontogenic; Cyst; Support vector machine; Odontogenic cyst; Artificial intelligence; Pattern recognition (psychology); Computer science; Logistic regression; Set (abstract data type); Data set; Biology; Pathology; Medicine; Machine learning","score_opus":0.02350127940725133,"score_gpt":0.27706882500558216,"score_spread":0.25356754559833083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110343138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942101,0.0002150502,0.004365106,0.00037395913,0.00038906172,0.00010343689,0.0000067557366,0.00012251116,0.00021400097],"genre_scores_gemma":[0.99651706,0.00006433306,0.003159516,0.00016731961,0.0000295366,0.0000053892168,0.000017205812,0.000007604159,0.000032034946],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990815,0.0000573226,0.0003300448,0.00016138623,0.00022955984,0.00014018093],"domain_scores_gemma":[0.99950206,0.00005298306,0.00012096826,0.00009736502,0.00011181449,0.00011477678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017462582,0.00009230194,0.0002394583,0.00009203237,0.000037922575,0.000012838837,0.00013407221,0.00008963971,0.00008574241],"category_scores_gemma":[0.00010155158,0.00007744168,0.00005102324,0.00015845864,0.00030250088,0.0000735576,0.00009863896,0.00010833573,0.000017978206],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086993125,0.00039365827,0.22248617,0.0005817238,0.00021388402,0.00017920048,0.0006335239,9.596829e-7,0.36934248,0.008242813,0.006528714,0.3913099],"study_design_scores_gemma":[0.0014728496,0.00004258801,0.93475455,0.00013418446,0.00003440429,0.00039809122,0.000076983226,0.057839144,0.0017473013,0.0017655952,0.0015443226,0.00018998231],"about_ca_topic_score_codex":0.000108275715,"about_ca_topic_score_gemma":0.0000071389827,"teacher_disagreement_score":0.7122684,"about_ca_system_score_codex":0.0000057437783,"about_ca_system_score_gemma":0.000051862284,"threshold_uncertainty_score":0.31579798},"labels":[],"label_agreement":null},{"id":"W2116780167","doi":"10.1016/s0895-6111(03)00018-1","title":"PET kinetic modeling of 11C-acetate from projections","year":2003,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Scanner; Positron emission tomography; Kinetic energy; Homogeneous; Iterative reconstruction; Computer science; Bin; Pet imaging; Biological system; Chemistry; Nuclear medicine; Algorithm; Materials science; Computer vision; Artificial intelligence; Physics; Statistical physics; Medicine","score_opus":0.025070002647593424,"score_gpt":0.30630081715513635,"score_spread":0.28123081450754295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116780167","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27969754,0.0007575924,0.70895463,0.008750381,0.00019944379,0.00035418055,0.000011756823,0.00027691058,0.0009975431],"genre_scores_gemma":[0.8968418,0.00092436303,0.10047546,0.0015569243,0.00008638323,0.000029665845,0.000036096397,0.000020362328,0.00002893101],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862915,0.000061214036,0.0003878507,0.00030958158,0.0003923435,0.00021985295],"domain_scores_gemma":[0.99899554,0.00011470349,0.00007040377,0.0003122264,0.00011688625,0.00039025274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033028552,0.00014828256,0.00035783142,0.00013469861,0.00009108615,0.000020083085,0.00010550217,0.000055887886,0.0000769679],"category_scores_gemma":[0.0003072554,0.00012406407,0.00009282353,0.00030491193,0.00035009033,0.000039776387,0.000059747937,0.0003883218,0.0000018123671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006841591,0.00823795,0.081476085,0.003912758,0.0018997301,0.0022652426,0.0043192753,0.00018616201,0.12722535,0.3541716,0.07465776,0.34096393],"study_design_scores_gemma":[0.0018250191,0.00004987384,0.00045982556,0.00054863724,0.0001449194,0.00047300037,0.00005798984,0.9705411,0.00044337925,0.008692144,0.016578598,0.00018546979],"about_ca_topic_score_codex":0.00014163955,"about_ca_topic_score_gemma":0.000001376069,"teacher_disagreement_score":0.970355,"about_ca_system_score_codex":0.000008367315,"about_ca_system_score_gemma":0.00012709288,"threshold_uncertainty_score":0.5059186},"labels":[],"label_agreement":null},{"id":"W2118333481","doi":"10.1016/j.compmedimag.2009.04.002","title":"Dynamic real-time 4D cardiac MDCT image display using GPU-accelerated volume rendering","year":2009,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Volume rendering; Computer science; Rendering (computer graphics); Visualization; Computer vision; Stereoscopy; Artificial intelligence; Computer graphics (images); Graphics; Software; Pipeline (software); Computer graphics; Stereo display","score_opus":0.013825439716645401,"score_gpt":0.3010589116873543,"score_spread":0.2872334719707089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118333481","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053572487,0.00041285725,0.94279784,0.0012248504,0.00051785534,0.00020434886,0.0000060442335,0.0011655673,0.00009813162],"genre_scores_gemma":[0.72814816,0.0028797756,0.26573765,0.002723059,0.00029331035,0.000013729896,0.0000842163,0.000070491755,0.000049595044],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969882,0.00021940749,0.000604226,0.00086237077,0.00071562204,0.00061022036],"domain_scores_gemma":[0.9982443,0.00011359036,0.00019242655,0.000708533,0.00021896974,0.0005221855],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008310412,0.000405784,0.00058559264,0.0004829405,0.0005038919,0.0009967643,0.0009805096,0.00016402769,0.000010877051],"category_scores_gemma":[0.00005395175,0.0003974138,0.00020073474,0.0011978382,0.0003271407,0.00068708765,0.0005606396,0.00043153364,0.0000031470695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006401838,0.0007818652,0.0038110146,0.00027450128,0.00030146935,0.0009390911,0.0020478521,0.000032049848,0.071591415,0.44872072,0.00702572,0.46441028],"study_design_scores_gemma":[0.0005008812,0.000071856244,0.0040862607,0.00020852932,0.00002032675,0.00010019257,0.000005145879,0.9872654,0.00018789861,0.005700006,0.0013827726,0.00047070792],"about_ca_topic_score_codex":0.000062252555,"about_ca_topic_score_gemma":8.38858e-7,"teacher_disagreement_score":0.9872334,"about_ca_system_score_codex":0.00004096361,"about_ca_system_score_gemma":0.00016639964,"threshold_uncertainty_score":0.99984777},"labels":[],"label_agreement":null},{"id":"W2118979849","doi":"10.1016/j.compmedimag.2011.06.001","title":"Quick detection of brain tumors and edemas: A bounding box method using symmetry","year":2011,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Minimum bounding box; Computer science; Artificial intelligence; Bounding overwatch; Pattern recognition (psychology); Magnetic resonance imaging; Histogram; Sørensen–Dice coefficient; Image segmentation; Computer vision; Image (mathematics); Medicine; Radiology","score_opus":0.028607222027919404,"score_gpt":0.31644253616642337,"score_spread":0.28783531413850394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118979849","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02307828,0.00043540026,0.9753152,0.0004710608,0.00029085262,0.00013575694,8.562286e-7,0.00022734811,0.000045238],"genre_scores_gemma":[0.22537461,0.00012452294,0.7724992,0.0019173041,0.000060471757,0.000005866917,0.000001113762,0.000013526782,0.000003351615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796486,0.0003030085,0.00047583494,0.00044835545,0.0005213405,0.00028658545],"domain_scores_gemma":[0.9986248,0.0004013139,0.00020515922,0.00028693507,0.00009205505,0.00038973565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017538335,0.00018091724,0.00034877806,0.00037550283,0.00015948538,0.000095668554,0.00039799127,0.000097425465,0.000008124486],"category_scores_gemma":[0.0004747328,0.00016632106,0.000062057974,0.0005515069,0.00046744398,0.00042159384,0.00044046078,0.0003134645,3.1694321e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021533271,0.000119410906,0.0019260301,0.0003035532,0.00005518832,0.000117053,0.0026337365,1.6758223e-7,0.051852018,0.011246668,0.00015567773,0.931569],"study_design_scores_gemma":[0.0017045278,0.00018233624,0.003281585,0.00087633106,0.00004858824,0.0009619468,0.00021842273,0.88304514,0.08463644,0.024322249,0.00019896161,0.00052346085],"about_ca_topic_score_codex":0.00016064564,"about_ca_topic_score_gemma":0.0000020289647,"teacher_disagreement_score":0.93104553,"about_ca_system_score_codex":0.000016350077,"about_ca_system_score_gemma":0.00007954909,"threshold_uncertainty_score":0.6782376},"labels":[],"label_agreement":null},{"id":"W2119872305","doi":"10.1016/j.compmedimag.2015.04.006","title":"Preliminary investigation into sources of uncertainty in quantitative imaging features","year":2015,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":94,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"National Cancer Institute; American Association of Physicists in Medicine; Radiological Society of North America","keywords":"Texture (cosmology); Breathing; Feature (linguistics); Lung cancer; Region of interest; Nuclear medicine; Medicine; Computer science; Mathematics; Radiology; Biomedical engineering; Artificial intelligence; Image (mathematics); Pathology","score_opus":0.017770306139179723,"score_gpt":0.3098605386461667,"score_spread":0.29209023250698696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119872305","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9604677,0.0054029417,0.011572457,0.02169523,0.00034355617,0.00020982958,0.0000013598212,0.00009002802,0.00021687527],"genre_scores_gemma":[0.9823059,0.0003123489,0.013820758,0.0033356922,0.00013010061,0.000008302032,0.000035839108,0.000023921366,0.000027180464],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981419,0.00018406853,0.0004486643,0.00034210618,0.0006178848,0.00026536506],"domain_scores_gemma":[0.9985702,0.00035488216,0.00014351356,0.00018512586,0.00016396299,0.00058233814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013473397,0.00018817768,0.00046991193,0.0003825095,0.00006290352,0.00003386493,0.00014935462,0.00007833941,0.0000044771473],"category_scores_gemma":[0.0017649583,0.0001563226,0.00007090153,0.00041852085,0.000976091,0.000120158875,0.0001470086,0.0007016272,7.48774e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009834176,0.00035335936,0.60849637,0.0009500184,0.00012553281,0.0010959493,0.022033948,0.0004096959,0.0021389062,0.00877308,0.006084704,0.34855503],"study_design_scores_gemma":[0.005670727,0.00025068974,0.08437334,0.0018568808,0.00008235258,0.00067554123,0.0017633971,0.89159065,0.0001223619,0.011077039,0.0022487158,0.00028832728],"about_ca_topic_score_codex":0.0010037145,"about_ca_topic_score_gemma":0.000011393333,"teacher_disagreement_score":0.89118093,"about_ca_system_score_codex":0.000032172986,"about_ca_system_score_gemma":0.00025838497,"threshold_uncertainty_score":0.637465},"labels":[],"label_agreement":null},{"id":"W2121264001","doi":"10.1016/j.compmedimag.2004.08.003","title":"Improved lesion detection from spatially adaptive, minimally complex, Pixon® reconstruction of planar scintigraphic images","year":2005,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Memorial University of Newfoundland; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Lesion; Nuclear medicine; Medicine; Artifact (error); Noise (video); Null (SQL); Artificial intelligence; Computer science; Pathology; Image (mathematics)","score_opus":0.02509845934565221,"score_gpt":0.28463698934065684,"score_spread":0.25953852999500465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121264001","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42182505,0.0005661341,0.5578004,0.018492559,0.00022130055,0.00048953434,0.00003157671,0.00038567992,0.00018776162],"genre_scores_gemma":[0.81220615,0.0008343146,0.18482164,0.001674153,0.0003520221,0.00002104138,0.000059746337,0.000022715703,0.000008241418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804235,0.00008346889,0.0006291077,0.00048448326,0.00048651855,0.00027406472],"domain_scores_gemma":[0.9985815,0.00019485378,0.00023470983,0.00034391123,0.00018831782,0.00045665266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004322943,0.00023561735,0.0005131809,0.00029295002,0.00015646208,0.000032881093,0.00017591126,0.00016241918,0.00007252295],"category_scores_gemma":[0.00016861512,0.0002065092,0.00014619446,0.00034250028,0.00086406094,0.0001126604,0.00008663405,0.0005124618,0.0000019153088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025312146,0.00023934149,0.003386917,0.00008224883,0.0000804075,0.000017456989,0.00006397126,3.5057283e-7,0.30390236,0.00047518857,0.0016948628,0.6898038],"study_design_scores_gemma":[0.006831721,0.0005167442,0.06349462,0.0016688881,0.0003975741,0.00075960654,0.00008371527,0.8704001,0.03629736,0.0038763187,0.015025535,0.0006478484],"about_ca_topic_score_codex":0.0003115029,"about_ca_topic_score_gemma":0.000033662684,"teacher_disagreement_score":0.8703997,"about_ca_system_score_codex":0.000022390186,"about_ca_system_score_gemma":0.00011016787,"threshold_uncertainty_score":0.84212005},"labels":[],"label_agreement":null},{"id":"W2130125423","doi":"10.1016/j.compmedimag.2013.07.001","title":"Standardized evaluation methodology and reference database for evaluating IVUS image segmentation","year":2013,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":137,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; National Heart, Lung, and Blood Institute; Ministère du Développement Économique, de l’Innovation et de l’Exportation; Boston Scientific Corporation","keywords":"Computer science; Segmentation; Visualization; Artificial intelligence; Computer vision; Data mining","score_opus":0.13139692413624687,"score_gpt":0.4467274760191264,"score_spread":0.3153305518828795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130125423","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40913045,0.0012877312,0.58436,0.0039070505,0.00024005513,0.00093253376,0.00003347664,0.000051928568,0.000056761543],"genre_scores_gemma":[0.3876345,0.0012472483,0.6072001,0.002450573,0.0001999982,0.00038460013,0.0008195687,0.000028584966,0.00003486178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842453,0.00027512645,0.000344308,0.00031665227,0.00044438653,0.00019500058],"domain_scores_gemma":[0.9977764,0.0011658373,0.00009708737,0.00017627605,0.00053283764,0.0002515944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002279297,0.00013217656,0.000287051,0.00012932412,0.00014565696,0.00006704478,0.000052897143,0.00006502633,0.0002497307],"category_scores_gemma":[0.002586061,0.00011253818,0.000056487326,0.00010357071,0.00022528693,0.0001630794,0.00009641657,0.0001832484,0.0000019821389],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025126888,0.00015440969,0.003203359,0.00049751136,0.000096763426,0.000014399459,0.00026796825,6.9874176e-7,0.03146521,0.0017399532,0.0038693778,0.95843905],"study_design_scores_gemma":[0.016096376,0.00070909783,0.028835073,0.00090269756,0.0007041053,0.00037762508,0.0004964165,0.93366915,0.00087546563,0.015586881,0.0014377951,0.00030934077],"about_ca_topic_score_codex":0.00006686693,"about_ca_topic_score_gemma":0.0000042550932,"teacher_disagreement_score":0.95812976,"about_ca_system_score_codex":0.000021647875,"about_ca_system_score_gemma":0.00012588836,"threshold_uncertainty_score":0.4589174},"labels":[],"label_agreement":null},{"id":"W2134484996","doi":"10.1016/j.compmedimag.2010.07.002","title":"A novel method for detection of pigment network in dermoscopic images using graphs","year":2010,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":100,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Vancouver Coastal Health Research Institute; Vancouver Coastal Health; Simon Fraser University; BC Cancer Agency","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Graph; Binary image; Image (mathematics); Computer vision; Image processing; Combinatorics; Mathematics; Theoretical computer science","score_opus":0.015985131269287856,"score_gpt":0.3076820629127886,"score_spread":0.29169693164350075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134484996","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21413125,0.00016233297,0.78388447,0.00061465753,0.00078640686,0.0003529265,0.000001724565,0.00004256432,0.000023703455],"genre_scores_gemma":[0.74771494,0.00010999227,0.2508999,0.000996695,0.00021708217,0.000023821656,0.00000552438,0.000019804256,0.00001225602],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989397,0.000032248587,0.0003204252,0.00025053896,0.00022863412,0.00022847294],"domain_scores_gemma":[0.9993441,0.00016557526,0.00008890838,0.00015905715,0.00006908835,0.00017325499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006175999,0.00012704422,0.0003186808,0.00023765708,0.00007409099,0.000018230348,0.00006123957,0.00008614878,0.000008230828],"category_scores_gemma":[0.00012225406,0.000114813294,0.000088378896,0.0002992144,0.00013532741,0.00003146221,0.00006504757,0.00030592867,1.1071268e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028546725,0.0002867321,0.003912063,0.00048736422,0.00009625704,0.000059564394,0.00012718896,0.000018729146,0.6936137,0.001833027,0.00012371744,0.2991562],"study_design_scores_gemma":[0.009882887,0.00030633132,0.016264087,0.00070090295,0.00026968628,0.0022529194,0.00009042346,0.9459644,0.011430887,0.0046953317,0.0077849864,0.00035717335],"about_ca_topic_score_codex":0.00010876772,"about_ca_topic_score_gemma":0.00005050355,"teacher_disagreement_score":0.9459457,"about_ca_system_score_codex":0.000011273656,"about_ca_system_score_gemma":0.00004586154,"threshold_uncertainty_score":0.46819502},"labels":[],"label_agreement":null},{"id":"W2135944657","doi":"10.1016/j.compmedimag.2008.07.004","title":"Efficient interactive 3D Livewire segmentation of complex objects with arbitrary topology","year":2008,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Robustness (evolution); Segmentation; Computer science; Network topology; Computer vision; Artificial intelligence; Scale-space segmentation; Image segmentation; Synthetic data; Pattern recognition (psychology); Algorithm","score_opus":0.015839153051179018,"score_gpt":0.2792759575551961,"score_spread":0.2634368045040171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135944657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07450177,0.00016173314,0.9235183,0.0009899166,0.00018547973,0.0002004622,0.0000022462839,0.00022544219,0.00021466393],"genre_scores_gemma":[0.60580504,0.00017373775,0.39085373,0.0030715226,0.000046744015,0.000016126933,0.000014854984,0.000010543412,0.000007674357],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811554,0.00018550757,0.00037977088,0.00041151576,0.00065018976,0.0002574954],"domain_scores_gemma":[0.9987889,0.00028743705,0.00019091561,0.00028667707,0.0001586915,0.00028738097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002921404,0.00018275187,0.00032955172,0.000241704,0.00015318512,0.000033908553,0.00044327762,0.00006565582,0.00003194278],"category_scores_gemma":[0.00008748138,0.00014732913,0.000049874747,0.00042027238,0.0010123791,0.00017051645,0.00028015388,0.00031462265,0.0000017277431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030562465,0.0017473344,0.008339809,0.00052224094,0.00035311255,0.0023285078,0.022410985,0.000055227996,0.029591957,0.009958409,0.0037115486,0.9206752],"study_design_scores_gemma":[0.00385077,0.00051964493,0.019077731,0.0004892239,0.000033974193,0.0019259765,0.00034202242,0.95799994,0.013976596,0.0010670272,0.00017600789,0.0005410728],"about_ca_topic_score_codex":0.000056158817,"about_ca_topic_score_gemma":0.0000016743049,"teacher_disagreement_score":0.95794475,"about_ca_system_score_codex":0.000018798171,"about_ca_system_score_gemma":0.00014757273,"threshold_uncertainty_score":0.6007908},"labels":[],"label_agreement":null},{"id":"W2136298381","doi":"10.1016/j.compmedimag.2015.08.006","title":"Medical image computing in diagnosis and intervention of spinal diseases","year":2015,"lang":"en","type":"review","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lawson Health Research Institute; Western University","funders":"","keywords":"Computer science; Intervention (counseling); Modality (human–computer interaction); Medical imaging; Analytics; Physical medicine and rehabilitation; Medicine; Data science; Computer vision; Medical physics; Artificial intelligence","score_opus":0.023904056557765428,"score_gpt":0.33845075749736886,"score_spread":0.3145467009396034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136298381","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004318922,0.9790753,0.019545501,0.00018159855,0.00041134842,0.0001537881,0.000020270129,0.00015246586,0.000027815366],"genre_scores_gemma":[0.0016319131,0.9971766,0.0007021544,0.00008298358,0.0002462601,0.000021067792,0.00008898515,0.000048069454,0.000001988884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686015,0.00028303475,0.0011245948,0.00044220765,0.00091328437,0.00037670427],"domain_scores_gemma":[0.9981819,0.0004459889,0.00016726698,0.00023687964,0.000066516346,0.0009014419],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013200666,0.0004301233,0.0020100102,0.00058813515,0.000042606072,0.000072149545,0.000361091,0.00028254648,0.000037258935],"category_scores_gemma":[0.0007523747,0.00035906295,0.00033426887,0.00059797516,0.00068282615,0.0000960424,0.0003414119,0.0009854033,0.0000018869455],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001498486,0.00007737175,0.00063394674,0.015414673,0.00011112322,0.0002074021,0.000033331835,5.29357e-7,5.6389023e-8,0.000052621228,0.0008208625,0.9826466],"study_design_scores_gemma":[0.0024029685,0.000058100504,0.0003812061,0.1395845,0.0013500729,0.0004172621,0.00005266511,0.43348852,4.1175124e-7,0.00053712045,0.42071822,0.00100896],"about_ca_topic_score_codex":0.000048092246,"about_ca_topic_score_gemma":0.0000036204754,"teacher_disagreement_score":0.9816376,"about_ca_system_score_codex":0.000031339667,"about_ca_system_score_gemma":0.00012874386,"threshold_uncertainty_score":0.99988616},"labels":[],"label_agreement":null},{"id":"W2136550549","doi":"10.1016/j.compmedimag.2010.06.002","title":"VascuSynth: Simulating vascular trees for generating volumetric image data with ground-truth segmentation and tree analysis","year":2010,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Computer Graphics and Visualization Techniques","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Ground truth; Computer science; Tree (set theory); Segmentation; Artificial intelligence; Image segmentation; Computer vision; Image (mathematics); Hierarchy; Tree structure; Pattern recognition (psychology); Data mining; Mathematics; Binary tree; Algorithm","score_opus":0.019665035372999868,"score_gpt":0.30770281695453705,"score_spread":0.2880377815815372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136550549","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.095410265,0.00030955632,0.9032298,0.00028524324,0.0002145662,0.0002371513,0.000010513961,0.00029777005,0.000005175822],"genre_scores_gemma":[0.50156194,0.00027897896,0.4973558,0.00043403663,0.00017816252,0.000020814914,0.00014783467,0.000020638012,0.0000017860928],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759233,0.000109417466,0.00044252363,0.00093616894,0.00058736035,0.00033221775],"domain_scores_gemma":[0.9976328,0.0007308199,0.00020009253,0.00090235693,0.00022975988,0.0003041954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011633501,0.0002705777,0.00043495125,0.00083586096,0.00046121047,0.0009471193,0.00090147456,0.000098753924,0.000002784771],"category_scores_gemma":[0.0002538368,0.00022742372,0.000110062436,0.0019437313,0.0002596286,0.0008171285,0.0008010544,0.00030967226,1.1178111e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017470698,0.00021737436,0.02451604,0.00018162323,0.0009359253,0.000033148084,0.0007475755,0.000035110723,0.003819539,0.09337927,0.00024965382,0.87586725],"study_design_scores_gemma":[0.0010495496,0.00006129087,0.011311972,0.00004038035,0.00022074624,0.000023931829,0.000018897716,0.9849251,0.00008395629,0.0015956768,0.00036463546,0.00030386276],"about_ca_topic_score_codex":0.00006869986,"about_ca_topic_score_gemma":0.000056942517,"teacher_disagreement_score":0.98489,"about_ca_system_score_codex":0.0000062559466,"about_ca_system_score_gemma":0.00006536561,"threshold_uncertainty_score":0.927407},"labels":[],"label_agreement":null},{"id":"W2147925844","doi":"10.1016/j.compmedimag.2009.07.004","title":"Integrated navigation and control software system for MRI-guided robotic prostate interventions","year":2009,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Soft Robotics and Applications","field":"Engineering","cited_by":63,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Center for Research Resources; National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute; National Institutes of Health","keywords":"Computer science; Fiducial marker; Software; Artificial intelligence; Computer vision; Visualization; Robotics; Workflow; Navigation system; Robot; Real-time computing","score_opus":0.013219414447902577,"score_gpt":0.2638300403063643,"score_spread":0.2506106258584617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147925844","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012736147,0.0010435043,0.98396057,0.0011411767,0.00023814643,0.0003739422,0.000018067214,0.00048063067,0.000007807346],"genre_scores_gemma":[0.9767613,0.00014791758,0.02260556,0.00023304256,0.0000730821,0.00005408615,0.00010176343,0.000017692291,0.000005586356],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999212,0.000018617742,0.00029321478,0.00018018988,0.000114380025,0.00018154651],"domain_scores_gemma":[0.99945015,0.00012933175,0.00003764249,0.00011513143,0.00008559049,0.00018218147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020110526,0.00013520152,0.000219027,0.000082526814,0.00012926667,0.00009361801,0.00008259749,0.000060692244,0.0000010019329],"category_scores_gemma":[0.00005082869,0.00012387734,0.00006995222,0.00015546283,0.00008430104,0.00006472158,0.00001483526,0.00016192623,6.063509e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098189346,0.00046365245,0.0063078483,0.0070695286,0.0006362355,0.000094155796,0.0013928465,0.016090916,0.006587502,0.073954135,0.018439434,0.86886555],"study_design_scores_gemma":[0.0015993031,0.0000314825,0.0017085563,0.0008888781,0.00006804334,0.00007888547,0.00003812355,0.99178326,0.00004240276,0.002562133,0.0010331555,0.00016579965],"about_ca_topic_score_codex":0.0000041229773,"about_ca_topic_score_gemma":5.764057e-7,"teacher_disagreement_score":0.97569233,"about_ca_system_score_codex":0.000015917545,"about_ca_system_score_gemma":0.000015206392,"threshold_uncertainty_score":0.5051571},"labels":[],"label_agreement":null},{"id":"W2151912546","doi":"10.1016/j.compmedimag.2008.06.004","title":"An affine transformation invariance approach to cell tracking","year":2008,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Immunotherapy and Immune Responses","field":"Immunology and Microbiology","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"","keywords":"Affine transformation; Transformation (genetics); Artificial intelligence; Computer vision; Mathematics; Affine combination; Affine shape adaptation; Tracking (education); Affine coordinate system; Clutter; Algorithm; Computer science; Pattern recognition (psychology); Affine space; Geometry","score_opus":0.01616096245858376,"score_gpt":0.24656602303664518,"score_spread":0.23040506057806143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151912546","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6932198,0.0053629116,0.29841715,0.0012073269,0.0005818626,0.00025276458,0.000006496158,0.0001982375,0.00075347716],"genre_scores_gemma":[0.99434584,0.0011552827,0.0017954081,0.002440554,0.000049131137,0.000014151825,0.00007921846,0.000016781742,0.000103615675],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99879634,0.00024351022,0.00029464072,0.00027034638,0.00008208222,0.0003130725],"domain_scores_gemma":[0.99948555,0.00010710913,0.000049972696,0.00022325822,0.000051506297,0.00008258083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041472062,0.00017436889,0.00026835306,0.0001683878,0.00039127472,0.000030277417,0.000261635,0.00015188666,0.00004730225],"category_scores_gemma":[0.000037063084,0.0001527993,0.00006177447,0.00022737145,0.0003310816,0.0002286404,0.00003380116,0.00037147192,0.000018165463],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016267984,0.0012766183,0.00096933404,0.00013489522,0.00013144732,0.000047353307,0.016982062,0.00002075913,0.71800977,0.0033065586,0.0027008085,0.2547936],"study_design_scores_gemma":[0.03408292,0.0019558806,0.06712254,0.0006768857,0.00018534066,0.009075051,0.0016982326,0.03274784,0.2443949,0.000875971,0.6040161,0.0031683221],"about_ca_topic_score_codex":0.00003478435,"about_ca_topic_score_gemma":5.939811e-7,"teacher_disagreement_score":0.6013153,"about_ca_system_score_codex":0.000007665988,"about_ca_system_score_gemma":0.00006842346,"threshold_uncertainty_score":0.6230974},"labels":[],"label_agreement":null},{"id":"W2154204373","doi":"10.1016/j.compmedimag.2009.06.001","title":"Adaptive ultrasound imaging of the lumbar spine for guidance of epidural anesthesia","year":2009,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Photoacoustic and Ultrasonic Imaging","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"B.C. Women's Hospital & Health Centre; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Image warping; Imaging phantom; Compounding; Computer science; Computer vision; Pixel; Artificial intelligence; Ultrasound imaging; Ultrasound; Image quality; Image registration; Biomedical engineering; Medicine; Image (mathematics); Radiology","score_opus":0.0065730392769877384,"score_gpt":0.22448042397580556,"score_spread":0.21790738469881782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154204373","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21038695,0.0047829,0.78183657,0.001814227,0.00043833736,0.00035904552,0.000015807254,0.00016740579,0.00019875956],"genre_scores_gemma":[0.99019945,0.0002768559,0.008645897,0.0007498412,0.000094905765,0.0000055293294,0.000004132715,0.000018148485,0.000005242212],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987918,0.00003440135,0.00040067176,0.00018796591,0.00028639144,0.00029878528],"domain_scores_gemma":[0.999261,0.00019297119,0.00009592404,0.0002341033,0.000094828225,0.00012115583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003872574,0.00018369858,0.00035366864,0.000073576106,0.00008037421,0.000017245482,0.00029583587,0.000046166693,0.000003609447],"category_scores_gemma":[0.00017942394,0.00014376227,0.0001340344,0.00023190945,0.0004000994,0.000091101676,0.00002493455,0.00021945342,1.02982305e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025729297,0.0006931741,0.032412346,0.0027183148,0.0005906388,0.00018231329,0.004327724,0.0041521387,0.34027696,0.04153791,0.016403574,0.5564476],"study_design_scores_gemma":[0.0017600787,0.00004777562,0.06767001,0.0008230574,0.000087867505,0.00042147932,0.00010365362,0.91881365,0.0049447236,0.004240398,0.0007698485,0.0003174756],"about_ca_topic_score_codex":0.000008640189,"about_ca_topic_score_gemma":4.9920084e-7,"teacher_disagreement_score":0.91466147,"about_ca_system_score_codex":0.000012575593,"about_ca_system_score_gemma":0.000046291356,"threshold_uncertainty_score":0.58624554},"labels":[],"label_agreement":null},{"id":"W2161739205","doi":"10.1016/s0895-6111(03)00019-3","title":"3D/2D registration and segmentation of scoliotic vertebrae using statistical models","year":2003,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":173,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Centre Hospitalier de l’Université de Montréal; École de Technologie Supérieure; Université de Montréal; Centre Hospitalier Universitaire de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Vertebra; Artificial intelligence; Computer science; Radiography; Computer vision; Segmentation; Image registration; Pattern recognition (psychology); Anatomy; Medicine; Image (mathematics); Radiology","score_opus":0.01572344107674521,"score_gpt":0.25581530450651907,"score_spread":0.24009186342977387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161739205","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12799753,0.0010766163,0.87041825,0.00009726937,0.00014815167,0.000051918065,0.0000041337044,0.000068330715,0.00013779386],"genre_scores_gemma":[0.95721895,0.00066363194,0.041861158,0.00018623586,0.000035895755,0.0000018419788,0.0000147428855,0.000014638764,0.0000029037762],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989292,0.00007286314,0.00030840363,0.00017969207,0.00033114105,0.00017870689],"domain_scores_gemma":[0.9994397,0.00012146206,0.00004047292,0.000106151965,0.000039636052,0.0002525703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036765836,0.00012614932,0.0002479122,0.00012804799,0.000064415704,0.000044984732,0.00005340349,0.000057750793,0.000016085434],"category_scores_gemma":[0.00012493039,0.00011886688,0.000028291188,0.0002001227,0.00028828764,0.00012945596,0.000018740202,0.00018549139,2.7610824e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051016195,0.0005929608,0.028956106,0.0055736545,0.001111925,0.0004799574,0.0036373904,0.021430828,0.04047448,0.14998676,0.0049679205,0.742737],"study_design_scores_gemma":[0.00058753224,0.00000767446,0.00023337433,0.00016602183,0.0000702884,0.000055348268,0.00004467081,0.99435943,0.00017717197,0.004094764,0.000084474,0.00011927238],"about_ca_topic_score_codex":0.000025470177,"about_ca_topic_score_gemma":0.0000011600868,"teacher_disagreement_score":0.9729286,"about_ca_system_score_codex":0.000010104002,"about_ca_system_score_gemma":0.000036287212,"threshold_uncertainty_score":0.48472506},"labels":[],"label_agreement":null},{"id":"W2162965383","doi":"10.1016/j.compmedimag.2014.10.009","title":"3D multimodal MRI brain glioma tumor and edema segmentation: A graph cut distribution matching approach","year":2014,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CARE Canada","funders":"","keywords":"Glioma; Segmentation; Matching (statistics); Artificial intelligence; Computer science; Graph; Distribution (mathematics); Brain tumor; Pattern recognition (psychology); Medicine; Pathology; Mathematics; Cancer research; Theoretical computer science","score_opus":0.008233496131512096,"score_gpt":0.2656703201993193,"score_spread":0.2574368240678072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162965383","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011955258,0.00020272512,0.9814336,0.005194437,0.00030056457,0.00027363483,0.000006567627,0.00055504654,0.000078194105],"genre_scores_gemma":[0.18340637,0.0002204939,0.80614746,0.009668633,0.00029259323,0.00007318087,0.00015176376,0.000028505274,0.000011009823],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720216,0.00036532275,0.00048599788,0.0007167555,0.0008201076,0.0004096626],"domain_scores_gemma":[0.99828917,0.00046749564,0.00016852235,0.00037518668,0.00009576224,0.00060385204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014357031,0.0002808376,0.00035944337,0.00021216391,0.0003415415,0.00042687685,0.0005422611,0.000096873744,0.000008350399],"category_scores_gemma":[0.00027079997,0.00025263062,0.0000727593,0.0005314006,0.0005519006,0.00058012677,0.0005147823,0.00040422598,0.0000019604236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028562183,0.0003054636,0.0011385435,0.00037218657,0.00006812802,0.00015211945,0.00156032,0.000008171051,0.0035917806,0.027068874,0.006987528,0.9587183],"study_design_scores_gemma":[0.0023787795,0.000083344,0.0016711042,0.00020775947,0.000022363552,0.0007118652,0.00007683422,0.98036885,0.0010512394,0.011800307,0.0011695101,0.00045805666],"about_ca_topic_score_codex":0.000045827008,"about_ca_topic_score_gemma":0.0000012988266,"teacher_disagreement_score":0.9803607,"about_ca_system_score_codex":0.000020261361,"about_ca_system_score_gemma":0.000053673717,"threshold_uncertainty_score":0.9999926},"labels":[],"label_agreement":null},{"id":"W2163888797","doi":"10.1016/s0895-6111(02)00030-7","title":"Ultrasound of the carotid arteries: a pictorial review","year":2002,"lang":"en","type":"review","venue":"Computerized Medical Imaging and Graphics","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University Medical Centre","funders":"","keywords":"Medicine; Stenosis; Carotid endarterectomy; Carotid bifurcation; Carotid arteries; Radiology; Stroke (engine); Endarterectomy; Ultrasound; Cardiology; Vascular disease; Carotid artery disease; Internal medicine","score_opus":0.02076224055105105,"score_gpt":0.29607325660541833,"score_spread":0.2753110160543673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163888797","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000072287107,0.9968324,0.00014750438,0.00040028166,0.0013067619,0.0009826042,0.000041345033,0.00005680977,0.0002251094],"genre_scores_gemma":[0.000030154368,0.9971916,0.00006004804,0.0016688744,0.0008241678,0.000050085102,0.00008657636,0.000042764754,0.00004571938],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972574,0.00030649808,0.0008339751,0.0004440512,0.0008678391,0.0002902131],"domain_scores_gemma":[0.9980514,0.00033469926,0.00029947006,0.0007779943,0.000111274254,0.00042516057],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003834494,0.00043104056,0.0023290396,0.000114057715,0.000102241174,0.000031188545,0.00034624708,0.00018640276,0.00018207978],"category_scores_gemma":[0.00051953795,0.00025341698,0.0014778653,0.00047795303,0.0006976221,0.00003812843,0.00018977138,0.0006800097,0.0000046111945],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036163842,0.00017114497,0.00029791644,0.12401249,0.0004400306,0.00001976632,0.000049641123,2.0396622e-9,4.7861727e-7,0.00015730206,0.017011175,0.8578364],"study_design_scores_gemma":[0.00067865767,0.000026783055,0.00011705488,0.13684843,0.00283788,0.0018551347,0.000004720986,0.000009790725,2.0203233e-7,0.000021405858,0.8573902,0.00020972431],"about_ca_topic_score_codex":0.000007573562,"about_ca_topic_score_gemma":6.795132e-7,"teacher_disagreement_score":0.8576267,"about_ca_system_score_codex":0.000020770845,"about_ca_system_score_gemma":0.00035989608,"threshold_uncertainty_score":0.99999183},"labels":[],"label_agreement":null},{"id":"W2167461451","doi":"10.1016/j.compmedimag.2009.04.003","title":"Simultaneous attenuation and scatter corrections in small animal PET imaging","year":2009,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"Nuclear Physics; Natural Sciences and Engineering Research Council of Canada; Université de Montréal; Université de Sherbrooke; Université du Québec à Chicoutimi","keywords":"Attenuation; Photon; Compton scattering; Correction for attenuation; Physics; Monte Carlo method; Optics; Scanner; Scattering; Transmission (telecommunications); Computational physics; Computer science; Mathematics; Statistics","score_opus":0.01330671646859268,"score_gpt":0.2934096532526517,"score_spread":0.28010293678405906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167461451","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77070904,0.0007461193,0.09565196,0.13158554,0.00015592368,0.0004666978,0.0000043644177,0.00040199517,0.00027838474],"genre_scores_gemma":[0.9687298,0.0005130566,0.015683169,0.014807354,0.00017034973,0.000016727225,0.000035312307,0.000015632144,0.000028576533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986348,0.00004951607,0.00034904608,0.000411302,0.00025218635,0.00030312792],"domain_scores_gemma":[0.99896914,0.00023977463,0.00006179181,0.0002153247,0.00008302146,0.00043096617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039751796,0.0001827501,0.00031002372,0.00024211314,0.0001432318,0.000064046384,0.00009581142,0.000056172525,0.000020708727],"category_scores_gemma":[0.0003107385,0.00016433944,0.00005096434,0.0003253334,0.00034742933,0.00007029113,0.000071663126,0.0005423051,0.0000021483597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020462683,0.00069492037,0.17614612,0.00020889885,0.000037383208,0.0019234588,0.0005843208,0.0000026451544,0.010860731,0.006177718,0.007660756,0.79549843],"study_design_scores_gemma":[0.0023998928,0.00010788911,0.05861941,0.00067358377,0.00007098131,0.0021771076,0.00006008499,0.9254798,0.000075508986,0.003221893,0.006816473,0.00029735526],"about_ca_topic_score_codex":0.000058432233,"about_ca_topic_score_gemma":0.000005899237,"teacher_disagreement_score":0.92547715,"about_ca_system_score_codex":0.000020983325,"about_ca_system_score_gemma":0.0000614687,"threshold_uncertainty_score":0.6701568},"labels":[],"label_agreement":null},{"id":"W2167791816","doi":"10.1016/s0895-6111(01)00016-7","title":"A flexible image segmentation prior to parametric estimation","year":2001,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Positron emission tomography; Pixel; Parametric statistics; Segmentation; Nuclear medicine; Blood flow; Artificial intelligence; Fluorodeoxyglucose; Image segmentation; Mathematics; Image (mathematics); Computer science; Pattern recognition (psychology); Physics; Medicine; Statistics; Internal medicine","score_opus":0.02055622666683135,"score_gpt":0.3451419694624448,"score_spread":0.3245857427956135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167791816","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13089506,0.00013910464,0.8235111,0.044144455,0.00010055532,0.00048591607,0.0000022062115,0.00044670896,0.00027484525],"genre_scores_gemma":[0.44500396,0.000874563,0.5371642,0.016299428,0.00023583716,0.00013481142,0.00009261643,0.000034531033,0.00016002305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846387,0.000036574824,0.00033340583,0.00035397883,0.0005341316,0.00027805715],"domain_scores_gemma":[0.99867886,0.00013930844,0.000061229264,0.00027502497,0.000113835136,0.00073173444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004449124,0.00015817683,0.00027393867,0.00034259455,0.00014708615,0.00007535488,0.00012246206,0.00007400734,0.00008483445],"category_scores_gemma":[0.0004477201,0.00013631792,0.00006475643,0.000944918,0.00020261815,0.00010118986,0.00010606314,0.00029682094,0.000023415287],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001088079,0.00040287114,0.00546629,0.00017576586,0.000040424053,0.0001951709,0.00020308225,0.000002372167,0.008086891,0.0028050388,0.032119974,0.9503933],"study_design_scores_gemma":[0.0047288234,0.00027155367,0.021687813,0.00097040244,0.0002090827,0.0019181616,0.00008261425,0.87393004,0.0028509004,0.0055136154,0.08726233,0.00057468243],"about_ca_topic_score_codex":0.000033600547,"about_ca_topic_score_gemma":4.4366053e-7,"teacher_disagreement_score":0.9498186,"about_ca_system_score_codex":0.000026737698,"about_ca_system_score_gemma":0.00008079088,"threshold_uncertainty_score":0.55588835},"labels":[],"label_agreement":null},{"id":"W2169451412","doi":"10.1016/j.compmedimag.2007.11.004","title":"SketchSnakes: Sketch-line initialized Snakes for efficient interactive medical image segmentation","year":2008,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Sketch; Computer science; Computer vision; Artificial intelligence; Segmentation; Computer graphics (images); Initialization; Robustness (evolution); Image segmentation; Object (grammar); Algorithm","score_opus":0.021472156532947255,"score_gpt":0.32395098885215395,"score_spread":0.3024788323192067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169451412","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010941987,0.00030207305,0.9776627,0.008674508,0.0009647081,0.0006148532,0.000011778522,0.000723614,0.0001037895],"genre_scores_gemma":[0.18565217,0.0017597275,0.7911686,0.020022044,0.00072887674,0.00036042262,0.00018255037,0.000071191884,0.000054456515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99578047,0.00031295605,0.00083492015,0.00081781944,0.0016983148,0.00055550213],"domain_scores_gemma":[0.99689656,0.0010825648,0.00025356113,0.00045818486,0.00036790548,0.0009412228],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014281278,0.0003608381,0.0005403716,0.0003737018,0.00041787262,0.00019628169,0.0010187415,0.00019087941,0.00010690981],"category_scores_gemma":[0.0016103653,0.00031357392,0.00018597576,0.0005559274,0.0010569501,0.0005370219,0.0004969912,0.00056484865,0.000008352262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026514163,0.0013701075,0.0004356208,0.00043495497,0.00023656878,0.0015077974,0.006628933,0.000005252846,0.008357711,0.010299465,0.024330778,0.94612765],"study_design_scores_gemma":[0.007210094,0.00026287884,0.00047372608,0.00051790447,0.000040338404,0.0010920024,0.0001727402,0.9691952,0.014012755,0.0038998963,0.0024213027,0.0007011702],"about_ca_topic_score_codex":0.000030798572,"about_ca_topic_score_gemma":0.0000026812882,"teacher_disagreement_score":0.96918994,"about_ca_system_score_codex":0.000046975783,"about_ca_system_score_gemma":0.00037642877,"threshold_uncertainty_score":0.99993163},"labels":[],"label_agreement":null},{"id":"W2222318341","doi":"10.1016/j.compmedimag.2015.12.006","title":"A multi-center milestone study of clinical vertebral CT segmentation","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":137,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of British Columbia","funders":"National Institutes of Health","keywords":"Segmentation; Vertebra; Sørensen–Dice coefficient; Milestone; Medicine; Thoracic vertebrae; Computer science; Artificial intelligence; Image segmentation; Lumbar; Lumbar vertebrae; Radiology; Anatomy; Cartography","score_opus":0.02823088218053465,"score_gpt":0.3265334777514597,"score_spread":0.29830259557092503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2222318341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83146936,0.00025813538,0.16686837,0.0005249722,0.00059939496,0.000095455835,0.000005060933,0.00016248181,0.000016764012],"genre_scores_gemma":[0.99586505,0.00060723955,0.003024305,0.000312614,0.00014174328,0.000007468889,0.000007019852,0.000019276273,0.000015311243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982904,0.00013884371,0.0006445907,0.00026423816,0.00043724777,0.00022463372],"domain_scores_gemma":[0.9990759,0.00023926458,0.000065213564,0.00021017951,0.00004767219,0.0003617685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064565433,0.00015874128,0.00044279735,0.00013855715,0.00004556083,0.000019200566,0.00017219444,0.00004112228,0.000036109566],"category_scores_gemma":[0.00019688848,0.000105536354,0.00010860921,0.00019198474,0.00028055583,0.000091872964,0.0000786243,0.00022878403,0.000004755669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013406584,0.0013949532,0.3234528,0.000108439184,0.0003230527,0.00015914951,0.00037869933,0.0000056116137,0.001407095,0.000022790884,0.0026573003,0.6700767],"study_design_scores_gemma":[0.026033055,0.00013609239,0.07294352,0.000740061,0.00021303055,0.00009312816,0.00035426105,0.8961412,0.00020015555,0.00010676187,0.0025361108,0.0005026672],"about_ca_topic_score_codex":0.000023667864,"about_ca_topic_score_gemma":0.00000493711,"teacher_disagreement_score":0.89613557,"about_ca_system_score_codex":0.000006774607,"about_ca_system_score_gemma":0.000020000842,"threshold_uncertainty_score":0.43036476},"labels":[],"label_agreement":null},{"id":"W2297514228","doi":"10.1016/j.compmedimag.2016.03.001","title":"Statistical shape analysis of subcortical structures using spectral matching","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Hôpital Notre-Dame; Polytechnique Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Janssen Research and Development; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; Eisai; Servier; U.S. Department of Defense; Eli Lilly and Company; Stanley Foundation; Lundbeckfonden; Canada Research Chairs; Centre de recherche du CHU Sainte-Justine; Pfizer; BioClinica; Biogen; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; F. Hoffmann-La Roche; Roche; Merck; Alzheimer's Drug Discovery Foundation; Takeda Pharmaceutical Company; AbbVie; Fujirebio Europe; Alzheimer's Association; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Johnson and Johnson; Meso Scale Diagnostics","keywords":"Pattern recognition (psychology); Shape analysis (program analysis); Artificial intelligence; Computer science; Polygon mesh; Curvature; Matching (statistics); Perimeter; Population; Mathematics; Geometry; Medicine; Statistics","score_opus":0.016715399119284543,"score_gpt":0.3118269522216882,"score_spread":0.29511155310240367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2297514228","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.107024394,0.00010220371,0.89144415,0.0009917599,0.00017413509,0.00006875178,0.000010393958,0.00017138195,0.000012842654],"genre_scores_gemma":[0.60250044,0.0001196128,0.39641535,0.00089352875,0.000053330285,0.0000020357627,0.0000053084336,0.000008664773,0.0000017361092],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758106,0.00017795929,0.0005540276,0.00046907994,0.000868419,0.00034945627],"domain_scores_gemma":[0.9982149,0.0007165339,0.00013756061,0.00035903123,0.0000960646,0.00047591855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005933946,0.00018090414,0.00047522783,0.00047381368,0.00008892995,0.000093891875,0.0005861106,0.00008272016,0.00014973377],"category_scores_gemma":[0.00031334453,0.00012250862,0.00012040073,0.0008181587,0.00070883357,0.00028654424,0.0003748212,0.00020826644,7.3672345e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028532455,0.00013503952,0.013732582,0.000079296886,0.0005591466,0.00027897485,0.00039351278,0.0000038051612,0.025966886,0.20597062,0.0003745403,0.75247705],"study_design_scores_gemma":[0.0011383104,0.00006099906,0.050109874,0.00017997508,0.00033301165,0.00010711516,0.000019609939,0.90275973,0.0033368943,0.041526552,0.000049961636,0.0003779881],"about_ca_topic_score_codex":0.00004247016,"about_ca_topic_score_gemma":0.0000020256746,"teacher_disagreement_score":0.9027559,"about_ca_system_score_codex":0.000020443846,"about_ca_system_score_gemma":0.000099322126,"threshold_uncertainty_score":0.49957564},"labels":[],"label_agreement":null},{"id":"W2302646539","doi":"10.1016/j.compmedimag.2016.03.002","title":"Scatter to volume registration for model-free respiratory motion estimation from dynamic MRIs","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Siemens (Canada); Lawson Health Research Institute; University of British Columbia","funders":"Canada Foundation for Innovation; Ontario Research Foundation; Lawson Health Research Institute","keywords":"Computer science; Computer vision; Artificial intelligence; Motion (physics); Image registration; Motion compensation; Motion estimation; Volume (thermodynamics); Breathing; Image (mathematics); Medicine; Physics","score_opus":0.021071886245011075,"score_gpt":0.31566504853286154,"score_spread":0.2945931622878505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2302646539","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04233892,0.00006866989,0.8372617,0.11943389,0.00009785129,0.00047355035,0.00005547351,0.00024703023,0.000022960174],"genre_scores_gemma":[0.5431912,0.00013545359,0.43595153,0.019586543,0.00032326733,0.00028084408,0.00017683292,0.000048312693,0.00030606042],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984923,0.00003271238,0.00038059033,0.00044205767,0.00041627916,0.00023607665],"domain_scores_gemma":[0.99858916,0.00016253743,0.00009046092,0.00051984115,0.00015056763,0.0004874146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048289393,0.0001608114,0.00026096002,0.00014807524,0.00012202787,0.000041490763,0.00018802052,0.00011837707,0.00003158694],"category_scores_gemma":[0.0006473113,0.00011799488,0.00008133104,0.00015507739,0.00023762256,0.00011582394,0.00010529233,0.00016198705,0.0000064013116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001356061,0.00017830862,0.0018384216,0.00012614459,0.00003992775,0.000012460732,0.00011193595,0.000007911789,0.029918337,0.0033881227,0.116656505,0.84758633],"study_design_scores_gemma":[0.0021105574,0.00007127703,0.0028190312,0.00057451637,0.00007293654,0.00001912312,0.0000041512067,0.9558583,0.00038497063,0.015128162,0.02277708,0.00017992654],"about_ca_topic_score_codex":0.000020123853,"about_ca_topic_score_gemma":0.0000040602204,"teacher_disagreement_score":0.95585036,"about_ca_system_score_codex":0.00004186833,"about_ca_system_score_gemma":0.00009000984,"threshold_uncertainty_score":0.48116916},"labels":[],"label_agreement":null},{"id":"W2321283863","doi":"10.1016/j.compmedimag.2016.02.002","title":"Multi-modal vertebrae recognition using Transformed Deep Convolution Network","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":95,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Artificial intelligence; Computer science; Vertebra; Feature (linguistics); Deep learning; Pattern recognition (psychology); Process (computing); Computer vision; Convolution (computer science); Convolutional neural network; Representation (politics); Modal; Artificial neural network; Anatomy; Medicine","score_opus":0.0174755098400779,"score_gpt":0.2395417669989261,"score_spread":0.2220662571588482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2321283863","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09714056,0.0013510328,0.89937454,0.00088269927,0.00072795636,0.0000736138,0.000005873188,0.0004056866,0.000038026403],"genre_scores_gemma":[0.9698676,0.0024502217,0.025997713,0.000957396,0.0006280585,0.000009899342,0.000034449582,0.00004616829,0.000008484505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848324,0.000074650765,0.00035560122,0.00027507523,0.00035777615,0.0004536687],"domain_scores_gemma":[0.99912995,0.00016655862,0.000034432986,0.00014884016,0.00005661343,0.00046361986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043774376,0.00021032996,0.00031686825,0.00013304398,0.00014545245,0.000046547582,0.0001346568,0.00012327603,0.000070897004],"category_scores_gemma":[0.00010733644,0.0001552377,0.000113232396,0.00029757657,0.000326006,0.00018115432,0.000033079094,0.00026447023,0.000010084103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011117674,0.000052177053,0.003492071,0.00013455277,0.00015396664,0.000063676875,0.00013574495,0.00013275794,0.0058050943,0.00006694376,0.0010038813,0.988948],"study_design_scores_gemma":[0.0018639636,0.000007014436,0.0010538694,0.00050949334,0.000080572965,0.000069493195,0.000013296153,0.993653,0.00009621109,0.0007859135,0.0016044494,0.0002627098],"about_ca_topic_score_codex":0.000019417317,"about_ca_topic_score_gemma":0.000005745951,"teacher_disagreement_score":0.99352026,"about_ca_system_score_codex":0.00002962741,"about_ca_system_score_gemma":0.000031136085,"threshold_uncertainty_score":0.633041},"labels":[],"label_agreement":null},{"id":"W2360393060","doi":"10.1016/j.compmedimag.2016.05.001","title":"WITHDRAWN: Adaptive Swarm Balancing Algorithms for rare-event prediction in imbalanced healthcare data","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Event (particle physics); Rare events; Event data; Swarm behaviour; Algorithm; Artificial intelligence; Data mining; Mathematics; Statistics","score_opus":0.03440100624848556,"score_gpt":0.32043466044108965,"score_spread":0.28603365419260407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2360393060","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008037099,0.0010243701,0.98025817,0.016349701,0.0009788427,0.00034181896,0.00006052803,0.00016628923,0.000016595919],"genre_scores_gemma":[0.23224162,0.00065673416,0.7636165,0.0028836057,0.00045315753,0.000056743625,0.000037419602,0.000024652854,0.000029574381],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975718,0.00021767807,0.00043748596,0.0008645514,0.00042822526,0.00048026108],"domain_scores_gemma":[0.9981845,0.00045176904,0.000120763834,0.00075857586,0.000107582295,0.0003768038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016805445,0.00021841662,0.00038059612,0.00018013774,0.00014639486,0.00008879779,0.000964567,0.00012291524,0.0000015740741],"category_scores_gemma":[0.00018147271,0.00015411187,0.000058348844,0.00033400016,0.00017277358,0.00051760545,0.00063281954,0.0002626736,7.157879e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041230905,0.000060484974,0.0010336535,0.00006378864,0.00002088457,0.00004794179,0.0003002014,7.9537307e-7,0.00016942139,0.03141507,0.0014649779,0.96538156],"study_design_scores_gemma":[0.003044478,0.000109118904,0.0023905248,0.0007716043,0.000009951002,0.00010172866,0.000012206812,0.9339757,0.00006754637,0.056368265,0.0028915417,0.00025736584],"about_ca_topic_score_codex":0.00004386369,"about_ca_topic_score_gemma":0.000015124576,"teacher_disagreement_score":0.9651242,"about_ca_system_score_codex":0.000036666926,"about_ca_system_score_gemma":0.00020725865,"threshold_uncertainty_score":0.6284499},"labels":[],"label_agreement":null},{"id":"W2414079435","doi":"10.1016/j.compmedimag.2016.06.001","title":"A multi-scale tensor voting approach for small retinal vessel segmentation in high resolution fundus images","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Fundus (uterus); Computer vision; Segmentation; Computer science; Pixel; Sensitivity (control systems); Diabetic retinopathy; Pattern recognition (psychology); Line (geometry); Image segmentation; False positive rate; Mathematics; Ophthalmology; Medicine","score_opus":0.0253056685054254,"score_gpt":0.28914885877201046,"score_spread":0.2638431902665851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2414079435","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18286029,0.0004633293,0.80796903,0.008207071,0.00010116858,0.00026829934,0.000009914506,0.00009930173,0.000021610973],"genre_scores_gemma":[0.70458287,0.00039611646,0.29334202,0.0010547293,0.00028217322,0.000053626165,0.00008643567,0.000030970983,0.00017103816],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981998,0.00014626965,0.0004344428,0.00050393725,0.0003263378,0.00038919394],"domain_scores_gemma":[0.9989507,0.00031232057,0.00012414584,0.00017495094,0.00015290474,0.00028496364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011410794,0.00020205395,0.00042922853,0.0003037141,0.00013275437,0.00005241492,0.000107273765,0.00009882249,0.0000056568974],"category_scores_gemma":[0.0004900436,0.00014030765,0.00012715992,0.0003116576,0.0003384743,0.00009960807,0.000068887144,0.0002604853,0.0000010781761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013790007,0.0012343416,0.44283125,0.0011653081,0.00022589664,0.00027100515,0.00060562417,0.000014298124,0.1375328,0.0003068924,0.002695236,0.41173837],"study_design_scores_gemma":[0.015220128,0.00017924949,0.14355832,0.0018734368,0.00031754083,0.0004104046,0.00030154834,0.83506477,0.0016728473,0.00020191396,0.0007290867,0.000470746],"about_ca_topic_score_codex":0.00009507797,"about_ca_topic_score_gemma":0.0000033625681,"teacher_disagreement_score":0.83505046,"about_ca_system_score_codex":0.00003818754,"about_ca_system_score_gemma":0.00005925539,"threshold_uncertainty_score":0.572158},"labels":[],"label_agreement":null},{"id":"W2463715500","doi":"10.1016/j.compmedimag.2016.06.008","title":"WITHDRAWN: Clinical pathways inference from decision rules by hybrid stream mining and fuzzy unordered rule induction strategy","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Universidade de Macau","keywords":"Rule induction; Rule of inference; Computer science; Inference; Artificial intelligence; Fuzzy inference system; Data mining; Fuzzy inference; Decision rule; Fuzzy rule; Fuzzy logic; Fuzzy set; Fuzzy control system; Adaptive neuro fuzzy inference system","score_opus":0.025612501070720325,"score_gpt":0.29934863912570053,"score_spread":0.2737361380549802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463715500","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4150415,0.0004601598,0.5825975,0.0013405734,0.0002641447,0.000061976505,0.00007542872,0.00013405277,0.000024657827],"genre_scores_gemma":[0.80152434,0.0028179209,0.19450945,0.00071272097,0.00028632546,0.000019185372,0.0001005399,0.000019448984,0.000010067949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780697,0.00011839936,0.00052452396,0.0008097538,0.00042880955,0.0003115211],"domain_scores_gemma":[0.99757934,0.0011751415,0.00016251113,0.00051215716,0.00009236911,0.00047851197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062038144,0.00022693715,0.0003323817,0.00010121033,0.0002654302,0.00037019188,0.00060885074,0.00011123421,0.000007849843],"category_scores_gemma":[0.00028870572,0.00016303238,0.000049911043,0.00020403201,0.0005210328,0.00055005675,0.00057326735,0.00025053113,0.0000048984098],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008860015,0.000077154975,0.002913071,0.0000044124567,0.000017494016,0.00001606241,0.000058736234,8.529178e-8,0.00041626545,0.0020350718,0.0020965587,0.99235624],"study_design_scores_gemma":[0.009146277,0.0005479592,0.08959182,0.0018358311,0.000087512424,0.00030479953,0.00020654812,0.70724815,0.00044628416,0.1654769,0.023455529,0.0016523966],"about_ca_topic_score_codex":0.000079270416,"about_ca_topic_score_gemma":0.0000048942634,"teacher_disagreement_score":0.9907038,"about_ca_system_score_codex":0.000009121234,"about_ca_system_score_gemma":0.00012718352,"threshold_uncertainty_score":0.6648268},"labels":[],"label_agreement":null},{"id":"W2481773658","doi":"10.1016/j.compmedimag.2016.07.011","title":"Ensemble based adaptive over-sampling method for imbalanced data learning in computer aided detection of microaneurysm","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Ensemble learning; Adaptive sampling; Sampling (signal processing); Machine learning; Pattern recognition (psychology); Training set; Computer vision; Mathematics; Monte Carlo method; Statistics","score_opus":0.038982278655162794,"score_gpt":0.3250309721664764,"score_spread":0.2860486935113136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2481773658","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002722848,0.00009302872,0.9947021,0.0016096933,0.00027052028,0.00028651944,0.000025014673,0.00028670247,0.0000035892235],"genre_scores_gemma":[0.33491296,0.00007184496,0.66430527,0.0005739781,0.00006626686,0.000024833273,0.00002809088,0.000014339484,0.000002406077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99777883,0.00025941237,0.0005077849,0.00077392015,0.00034580752,0.00033425036],"domain_scores_gemma":[0.9970336,0.0016043127,0.00025952898,0.00081652356,0.00014227034,0.00014376687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016514382,0.00019607949,0.00038303164,0.00033098483,0.000102054895,0.00006985525,0.001103638,0.00011224979,0.0000013646206],"category_scores_gemma":[0.00041916157,0.00015839332,0.00005829513,0.00043237788,0.00017487424,0.00048697586,0.0006238259,0.000260615,4.1524976e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006408686,0.000071113056,0.0010861022,0.00007298789,0.000015369465,0.000008148858,0.00006677475,0.000015891834,0.1393361,0.0030808765,0.00014807351,0.85603446],"study_design_scores_gemma":[0.0020068737,0.00009103019,0.0034843879,0.00032210964,0.000007784509,0.000025009835,0.0000035547114,0.9745825,0.014697041,0.0028734242,0.0016975331,0.00020875449],"about_ca_topic_score_codex":0.000032192216,"about_ca_topic_score_gemma":0.000007863538,"teacher_disagreement_score":0.9745666,"about_ca_system_score_codex":0.000030832176,"about_ca_system_score_gemma":0.00011811822,"threshold_uncertainty_score":0.64590925},"labels":[],"label_agreement":null},{"id":"W2527794637","doi":"10.1016/j.compmedimag.2016.08.004","title":"WITHDRAWN: Improving classification of protein binders for virtual drug screening by novel swarm-based feature selection techniques","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Feature selection; Computer science; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence","score_opus":0.005779229238930653,"score_gpt":0.24733961668204324,"score_spread":0.2415603874431126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527794637","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08672089,0.000093021255,0.9102337,0.0025319355,0.000053812684,0.000282688,0.000019189287,0.000054809327,0.000009946269],"genre_scores_gemma":[0.84943604,0.000028759567,0.14951187,0.000590203,0.00013772724,0.00004900643,0.0001418186,0.000026850646,0.000077713165],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990756,0.00004355294,0.00023583297,0.00024564436,0.00021446058,0.00018489998],"domain_scores_gemma":[0.9993567,0.00005752429,0.00019667309,0.00014960462,0.00013326877,0.00010625045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048086751,0.00014673677,0.0001547186,0.00008534787,0.000107982676,0.000027592187,0.00015005676,0.00015214014,0.0000010679008],"category_scores_gemma":[0.00030099432,0.00010946437,0.00006371611,0.00010447082,0.0002504524,0.000011368134,0.00006166191,0.00015561596,7.001724e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012023135,0.000041776977,0.0013183919,0.000117726246,0.000022778106,1.4589259e-7,0.000021973701,0.0000022556274,0.85525745,0.00018967585,0.0017759794,0.14113162],"study_design_scores_gemma":[0.003771806,0.00048487118,0.0009569493,0.00069625315,0.000044688382,0.000026903286,0.000056154884,0.4091534,0.55098695,0.000080213125,0.03324415,0.0004976566],"about_ca_topic_score_codex":0.00001022051,"about_ca_topic_score_gemma":0.0000025069498,"teacher_disagreement_score":0.76271516,"about_ca_system_score_codex":0.0000071520462,"about_ca_system_score_gemma":0.00009013427,"threshold_uncertainty_score":0.44638273},"labels":[],"label_agreement":null},{"id":"W2527922796","doi":"10.1016/j.compmedimag.2016.09.004","title":"Spine labeling in axial magnetic resonance imaging via integral kernels","year":2016,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University; École de Technologie Supérieure; McGill University; University of Toronto; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Integral imaging; Computer science; Kernel (algebra); Artificial intelligence; Computation; Pattern recognition (psychology); Medical imaging; Prior probability; Classifier (UML); Computer vision; Mathematics; Algorithm; Image (mathematics); Bayesian probability","score_opus":0.005805778086409533,"score_gpt":0.2253541850637323,"score_spread":0.21954840697732278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527922796","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17218317,0.034464717,0.7785777,0.011224461,0.0019315201,0.00018881707,0.000010647195,0.0010165994,0.00040240897],"genre_scores_gemma":[0.98945916,0.0032893855,0.0052749165,0.0013927172,0.00043513454,0.000014850303,0.000008365963,0.000055189237,0.00007028321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978836,0.00008149849,0.0005244298,0.00042269938,0.0004974532,0.0005903019],"domain_scores_gemma":[0.99901664,0.00017000452,0.00003609081,0.00026599463,0.00005052686,0.0004607432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006473252,0.00028981236,0.00044482294,0.00033154327,0.000073381,0.000069748196,0.00030668525,0.000085527005,0.000089735564],"category_scores_gemma":[0.00026543325,0.00021197944,0.00010153306,0.0004957272,0.0004443818,0.00017262383,0.00013144035,0.000495394,0.000011671803],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047562544,0.000032569737,0.020974372,0.000057308196,0.000010819841,0.0002452943,0.0001000667,0.0000053325602,0.003500275,0.00025485584,0.000943115,0.97387123],"study_design_scores_gemma":[0.0030988494,0.000015520476,0.01132825,0.0016547501,0.00003728966,0.00015762393,0.000027447195,0.9614802,0.0002276245,0.0027068285,0.018721346,0.0005442905],"about_ca_topic_score_codex":0.000058920243,"about_ca_topic_score_gemma":0.000008611973,"teacher_disagreement_score":0.9733269,"about_ca_system_score_codex":0.000033964065,"about_ca_system_score_gemma":0.000033403838,"threshold_uncertainty_score":0.86442703},"labels":[],"label_agreement":null},{"id":"W2587023207","doi":"10.1016/j.compmedimag.2017.01.001","title":"Early identification of mild cognitive impairment using incomplete random forest-robust support vector machine and FDG-PET imaging","year":2017,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Fundamental Research Funds for the Central Universities; National Institutes of Health; Servier; U.S. Department of Defense; Eli Lilly and Company; Lundbeckfonden; Genentech; Takeda Pharmaceutical Company; IXICO; National Natural Science Foundation of China; DoD Alzheimer's Disease Neuroimaging Initiative; Pfizer; Biogen; BioClinica; Natural Science Foundation of Shanghai; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; Roche; Merck; Alzheimer's Drug Discovery Foundation; GE Healthcare; Alzheimer's Disease Neuroimaging Initiative; Johnson and Johnson; Meso Scale Diagnostics; AbbVie; Fujirebio Europe; Alzheimer's Association","keywords":"Random forest; Dementia; Artificial intelligence; Support vector machine; Prodromal Stage; Pattern recognition (psychology); Identification (biology); Cognitive impairment; Computer science; Population; Positron emission tomography; Transformation (genetics); Cognition; Neuroimaging; Machine learning; Disease; Medicine; Nuclear medicine; Pathology; Psychiatry","score_opus":0.02645681319219882,"score_gpt":0.3303718699412996,"score_spread":0.30391505674910074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587023207","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94948864,0.0005756481,0.04682524,0.0020601884,0.00022787026,0.0006435659,0.00004042983,0.000044999044,0.00009342838],"genre_scores_gemma":[0.99776644,0.00043409027,0.0010002808,0.00050645246,0.00013567838,0.000020288808,0.000077056735,0.000027405511,0.000032283635],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99763334,0.00012978833,0.0005590371,0.00047314353,0.0007883932,0.0004162806],"domain_scores_gemma":[0.9983121,0.00021929211,0.0003094896,0.00032414234,0.0003484698,0.0004864806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013006844,0.0002448436,0.0005321237,0.00028552528,0.00052217866,0.00022629114,0.00019623147,0.000048226364,0.000047324866],"category_scores_gemma":[0.00038325676,0.00021148712,0.00012364949,0.00011856826,0.0012221787,0.00027075323,0.00038564423,0.00037067465,0.0000018369707],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009362651,0.00024936814,0.96843433,0.00045452412,0.00021262823,0.0004912482,0.00032268662,2.9123976e-7,0.002810159,0.00013639267,0.00010023581,0.025851859],"study_design_scores_gemma":[0.013280996,0.00017327444,0.8150727,0.00079970085,0.0002747127,0.00048649817,0.00008231682,0.16882426,0.00037807607,0.00037136133,0.00006145584,0.00019465647],"about_ca_topic_score_codex":0.00027246607,"about_ca_topic_score_gemma":0.000007053277,"teacher_disagreement_score":0.16882396,"about_ca_system_score_codex":0.000019358647,"about_ca_system_score_gemma":0.0001485,"threshold_uncertainty_score":0.8624194},"labels":[],"label_agreement":null},{"id":"W2591708314","doi":"10.1016/j.compmedimag.2017.02.003","title":"Performance of leading artifact removal algorithms assessed across microwave breast imaging prototype scan configurations","year":2017,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Microwave Imaging and Scattering Analysis","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Irish Research Council; Science Foundation Ireland; European Cooperation in Science and Technology","keywords":"Microwave imaging; Artifact (error); Computer science; Subtraction; Breast imaging; Algorithm; Imaging phantom; Artificial intelligence; Microwave; Modality (human–computer interaction); Computer vision; Breast cancer; Mammography; Radiology; Mathematics; Medicine; Telecommunications; Cancer","score_opus":0.012516654981509836,"score_gpt":0.27397489817572146,"score_spread":0.2614582431942116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591708314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.905356,0.0004724415,0.091021,0.0014032813,0.0005826306,0.00019123594,0.000033554352,0.000307052,0.0006328121],"genre_scores_gemma":[0.99550724,0.00032173097,0.0037561208,0.00012701796,0.00017945135,0.00001285673,0.000026851443,0.000043512042,0.000025235953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982208,0.000046338537,0.000490594,0.00036945083,0.00036796572,0.0005048265],"domain_scores_gemma":[0.99871814,0.000077463126,0.00016719596,0.0006135856,0.00013980562,0.0002838288],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006500584,0.0002911791,0.0005083607,0.00016056119,0.00062939484,0.00041309514,0.00048955384,0.00007635312,0.00001787157],"category_scores_gemma":[0.00007775284,0.00028546,0.0001394267,0.0001622869,0.0007089356,0.00036040897,0.00015666039,0.00045148222,0.0000056757985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004932342,0.00009817794,0.06935459,0.00081256847,0.00030341896,0.00021574623,0.0010235157,0.000240845,0.19694543,0.00010274063,0.0009226122,0.72993106],"study_design_scores_gemma":[0.0009023404,0.000014314724,0.028816694,0.000648814,0.000058715974,0.0009086283,0.00006270294,0.9614743,0.005519755,0.000057635953,0.0011459404,0.000390141],"about_ca_topic_score_codex":0.00008479571,"about_ca_topic_score_gemma":0.000008535526,"teacher_disagreement_score":0.9612335,"about_ca_system_score_codex":0.000025701844,"about_ca_system_score_gemma":0.000057069792,"threshold_uncertainty_score":0.99995977},"labels":[],"label_agreement":null},{"id":"W2599622777","doi":"10.1016/j.compmedimag.2017.03.004","title":"Graph cut-based method for segmenting the left ventricle from MRI or echocardiographic images","year":2017,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Voxel; Cut; Artificial intelligence; Segmentation; Computer vision; Bézier curve; Computer science; Euclidean space; Coordinate system; Mathematics; Image segmentation; Geometry; Combinatorics","score_opus":0.021461030411814904,"score_gpt":0.33601303611788275,"score_spread":0.31455200570606784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599622777","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059114135,0.0005376468,0.9811036,0.015944166,0.00081335846,0.00049145485,0.00002105289,0.00045838946,0.000039161936],"genre_scores_gemma":[0.03464253,0.0006550979,0.9540058,0.010148672,0.00036535182,0.000094596486,0.000027917384,0.000035163066,0.00002490072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99697065,0.00032935318,0.000507858,0.0007757425,0.0008799179,0.00053645275],"domain_scores_gemma":[0.99595976,0.0017120467,0.0003653702,0.001339826,0.00018291478,0.00044006447],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002401356,0.0003043501,0.0004469723,0.00025407324,0.0014196923,0.0012790755,0.002438035,0.00012380951,0.000024206569],"category_scores_gemma":[0.0009368845,0.00020428232,0.00028814757,0.00029366338,0.0008126436,0.00056665094,0.0007413698,0.00046584825,0.0000017880482],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007384113,0.00017425873,0.0057752198,0.00013253182,0.00022284787,0.00021034057,0.00040851053,0.000005328532,0.0019273355,0.0020657645,0.02023114,0.9687729],"study_design_scores_gemma":[0.0046764943,0.0001203943,0.008310433,0.0004950024,0.00014332384,0.0000885543,0.000062084335,0.9374132,0.015806194,0.024841031,0.007358946,0.0006843536],"about_ca_topic_score_codex":0.00016021614,"about_ca_topic_score_gemma":0.000009423697,"teacher_disagreement_score":0.9680885,"about_ca_system_score_codex":0.000013331096,"about_ca_system_score_gemma":0.00015122595,"threshold_uncertainty_score":0.9998803},"labels":[],"label_agreement":null},{"id":"W2624881194","doi":"10.1016/j.compmedimag.2017.06.003","title":"A level-set approach to joint image segmentation and registration with application to CT lung imaging","year":2017,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Cancer Research UK","keywords":"Segmentation; Artificial intelligence; Computer science; Image registration; Computer vision; Scale-space segmentation; Initialization; Image segmentation; Segmentation-based object categorization; Medical imaging; Pattern recognition (psychology); Image (mathematics)","score_opus":0.03369783428052336,"score_gpt":0.333251858610384,"score_spread":0.2995540243298606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624881194","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06454888,0.000076892684,0.884377,0.049300645,0.000041661522,0.0009867798,0.000009981061,0.00016481755,0.0004933408],"genre_scores_gemma":[0.72477347,0.00010047234,0.26885036,0.0056631,0.000182761,0.00025168483,0.00010647577,0.0000298851,0.00004179648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825376,0.000034402456,0.0003232061,0.00059285015,0.0005191378,0.00027666098],"domain_scores_gemma":[0.99824417,0.000038050017,0.00014878885,0.0006327179,0.00014333118,0.0007929473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006366226,0.00021275668,0.00031437454,0.00016970755,0.0004960247,0.00028056832,0.00019588937,0.000037231926,0.0000035467824],"category_scores_gemma":[0.00022835503,0.00017500756,0.00003928871,0.00016250608,0.0004133246,0.00015069198,0.00021413059,0.00028918765,0.0000021517644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049213995,0.00073643465,0.074863635,0.0016153556,0.00020185599,0.00027489953,0.002133423,0.0000052014357,0.10837335,0.018512886,0.0886464,0.7041444],"study_design_scores_gemma":[0.005712776,0.00021072126,0.11878824,0.0016151669,0.00031776977,0.0025255356,0.0002882749,0.8438974,0.0032716647,0.0016624578,0.020770328,0.0009396588],"about_ca_topic_score_codex":0.00016617235,"about_ca_topic_score_gemma":0.000003921805,"teacher_disagreement_score":0.8438922,"about_ca_system_score_codex":0.000027642205,"about_ca_system_score_gemma":0.00008336181,"threshold_uncertainty_score":0.7136601},"labels":[],"label_agreement":null},{"id":"W2667718598","doi":"10.1016/j.compmedimag.2017.06.005","title":"Abdominal parametric perfusion imaging with respiratory motion-compensation based on contrast-enhanced ultrasound: In-vivo validation","year":2017,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Ultrasound and Hyperthermia Applications","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Contrast (vision); Perfusion; Parametric statistics; Ultrasound; Motion compensation; In vivo; Biomedical engineering; Microbubbles; Radiology; Medicine; Computer science; Nuclear medicine; Computer vision; Mathematics; Biology","score_opus":0.009682089098404486,"score_gpt":0.24043603880698308,"score_spread":0.2307539497085786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2667718598","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67108476,0.00011665642,0.3268775,0.0005599241,0.00021985758,0.000231258,0.0000071935797,0.00018441952,0.0007184349],"genre_scores_gemma":[0.99742323,0.00011433528,0.0016980307,0.0005442341,0.00012765834,0.000038876824,0.000020586025,0.000029308889,0.0000037187676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872315,0.000053789678,0.00026835574,0.00031537376,0.0003793459,0.00026001205],"domain_scores_gemma":[0.9987923,0.0004764515,0.000090350404,0.00039507163,0.0000689103,0.00017693824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040339766,0.00020628636,0.00024257854,0.0003003934,0.00038790563,0.00024975944,0.0002314387,0.00007214537,0.00004239341],"category_scores_gemma":[0.00021606711,0.00018399133,0.00004423409,0.0002086647,0.00025492912,0.000219767,0.00002025127,0.0003425316,0.0000033331053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033114187,0.00068274245,0.15142407,0.0003685844,0.0000775746,0.00013078602,0.0008800314,0.013059693,0.16904844,0.002955287,0.00067868014,0.66036296],"study_design_scores_gemma":[0.0035416102,0.000037962196,0.0789495,0.0003720848,0.00003306131,0.00003109682,0.000046570436,0.91019917,0.004420471,0.00035656046,0.001620317,0.00039158115],"about_ca_topic_score_codex":0.000032364234,"about_ca_topic_score_gemma":0.000013233231,"teacher_disagreement_score":0.8971395,"about_ca_system_score_codex":0.000035898058,"about_ca_system_score_gemma":0.00004207055,"threshold_uncertainty_score":0.75029486},"labels":[],"label_agreement":null},{"id":"W2775394473","doi":"10.1016/j.compmedimag.2019.101660","title":"Deep CNN ensembles and suggestive annotations for infant brain MRI segmentation","year":2019,"lang":"en","type":"preprint","venue":"Computerized Medical Imaging and Graphics","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Convolutional neural network; Computer science; Segmentation; Artificial intelligence; Pattern recognition (psychology); Partial volume; White matter; Image segmentation; Limiting; Machine learning; Magnetic resonance imaging; Medicine; Radiology","score_opus":0.013627076811645539,"score_gpt":0.29915351713747346,"score_spread":0.2855264403258279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775394473","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14878722,0.0059069046,0.8058236,0.036146108,0.001307696,0.0016432012,0.00011025372,0.00016292963,0.0001120676],"genre_scores_gemma":[0.80697906,0.008021671,0.13579641,0.04243817,0.0014632889,0.00047310925,0.004242243,0.00015942346,0.00042660453],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983094,0.00008876583,0.00038642893,0.00062753726,0.00030487354,0.00028300294],"domain_scores_gemma":[0.9982221,0.00087411,0.00015341319,0.00024017536,0.00017146993,0.0003387348],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045038186,0.00029156974,0.0006105037,0.00024889602,0.0001266462,0.000059775663,0.00010402304,0.00028884888,0.000008570565],"category_scores_gemma":[0.0004158753,0.00025314788,0.00012454792,0.00010745154,0.0005210636,0.000056182766,0.00041068046,0.00065412116,0.0000018680319],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001647357,0.00065341167,0.032416694,0.010623773,0.0010910959,0.0010679403,0.0092111295,0.000082138606,0.008456097,0.011609434,0.015776154,0.9073648],"study_design_scores_gemma":[0.015810583,0.0007155872,0.06410309,0.0033370673,0.00079377735,0.0022871112,0.00066964707,0.853735,0.0003435629,0.036351584,0.020576112,0.0012768536],"about_ca_topic_score_codex":0.000025901994,"about_ca_topic_score_gemma":0.000005090712,"teacher_disagreement_score":0.90608793,"about_ca_system_score_codex":0.000015933934,"about_ca_system_score_gemma":0.00016898033,"threshold_uncertainty_score":0.9999921},"labels":[],"label_agreement":null},{"id":"W2777683438","doi":"10.1016/j.compmedimag.2017.12.004","title":"Segmentation-free direct tumor volume and metabolic activity estimation from PET scans","year":2017,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia Hospital; University of British Columbia; Simon Fraser University","funders":"","keywords":"Segmentation; Imaging phantom; Positron emission tomography; Computer science; Image segmentation; Artificial intelligence; Standardized uptake value; Partial volume; Modality (human–computer interaction); Volume (thermodynamics); Nuclear medicine; Reproducibility; Data set; Pattern recognition (psychology); Computer vision; Mathematics; Medicine; Physics; Statistics","score_opus":0.01623796260948879,"score_gpt":0.3134328453741945,"score_spread":0.29719488276470574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2777683438","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69192684,0.00076440646,0.2417985,0.06389274,0.00026661772,0.00047428661,0.00006351898,0.00037739574,0.00043567928],"genre_scores_gemma":[0.90958077,0.00086533464,0.08661306,0.0025009762,0.0002406186,0.000053243493,0.00006313335,0.00002280949,0.00006005767],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864227,0.000051056744,0.00023231613,0.00040624783,0.00044572362,0.00022238566],"domain_scores_gemma":[0.9983912,0.00014779919,0.0001576167,0.0006988064,0.00007014639,0.0005344344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003934723,0.00018169447,0.00040094083,0.00009002562,0.00048244256,0.00019552524,0.00026190485,0.000048583734,0.000050033614],"category_scores_gemma":[0.0007200474,0.00015507829,0.00006311577,0.00007706565,0.0007786676,0.00019857379,0.00031374863,0.000352082,0.0000027000326],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015719025,0.0005688186,0.100105904,0.00031564504,0.0003147572,0.00049531733,0.00038939508,7.160622e-7,0.011561243,0.0040556914,0.035638444,0.84639686],"study_design_scores_gemma":[0.003346454,0.000042546337,0.22191647,0.00047250418,0.00033117904,0.00032828102,0.000017044278,0.75434566,0.0010458346,0.0053158463,0.012540514,0.00029766536],"about_ca_topic_score_codex":0.0005624849,"about_ca_topic_score_gemma":0.000008191605,"teacher_disagreement_score":0.8460992,"about_ca_system_score_codex":0.00001020299,"about_ca_system_score_gemma":0.00008282263,"threshold_uncertainty_score":0.6323909},"labels":[],"label_agreement":null},{"id":"W2783637515","doi":"10.1016/j.compmedimag.2018.01.007","title":"A novel contour-based registration of lateral cephalogram and profile photograph","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Peking University","keywords":"Artificial intelligence; Computer science; Computer vision; Cephalogram; Nasion; Iterative closest point; Landmark; Forehead; Robustness (evolution); Mathematics; Point cloud; Orthodontics; Malocclusion; Anatomy; Medicine","score_opus":0.015446419713489166,"score_gpt":0.28664991785636973,"score_spread":0.2712034981428806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783637515","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025191927,0.00013682302,0.9723122,0.0016248771,0.0001978871,0.00020447004,0.000004251897,0.00024571765,0.00008185645],"genre_scores_gemma":[0.5661475,0.000095182404,0.42985943,0.0037275008,0.00011018788,0.000022452803,0.000016075224,0.000010620539,0.000011023799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982805,0.00010337078,0.00038864548,0.00038761148,0.0006111576,0.0002286639],"domain_scores_gemma":[0.9988316,0.0002099283,0.00016480188,0.00029792974,0.00018434587,0.00031134783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009468482,0.00015240118,0.00024595176,0.0002119885,0.00010892978,0.00015100175,0.00043133795,0.00008766995,0.000016781172],"category_scores_gemma":[0.00019881477,0.00013256578,0.00005043234,0.00039248288,0.0012190689,0.0002421372,0.00019174367,0.0001897292,5.649903e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012243792,0.0006958375,0.011674955,0.0004452754,0.000083421146,0.00008477998,0.001127261,1.2577955e-7,0.07976077,0.01230146,0.006402136,0.88730156],"study_design_scores_gemma":[0.007433529,0.0006978432,0.027900357,0.0010482514,0.000048783426,0.00030428014,0.000035410067,0.90574163,0.04801704,0.0053399303,0.0026739573,0.0007590136],"about_ca_topic_score_codex":0.000079774596,"about_ca_topic_score_gemma":0.000005603191,"teacher_disagreement_score":0.90574145,"about_ca_system_score_codex":0.0000050612484,"about_ca_system_score_gemma":0.000086230524,"threshold_uncertainty_score":0.54058754},"labels":[],"label_agreement":null},{"id":"W2789256791","doi":"10.1016/j.compmedimag.2018.02.002","title":"Segmentation of white matter hyperintensities using convolutional neural networks with global spatial information in routine clinical brain MRI with none or mild vascular pathology","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":85,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Janssen Alzheimer Immunotherapy Research And Development; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; Lembaga Pengelola Dana Pendidikan; H. Lundbeck A/S; Servier; Eisai; Johnson and Johnson Pharmaceutical Research and Development; Mrs Gladys Row Fogo Charitable Trust; Northern California Institute for Research and Education; BioClinica; Biogen; Pfizer; Novartis Pharmaceuticals Corporation; Eli Lilly and Company; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; University of Southern California; Bristol-Myers Squibb; Alzheimer's Drug Discovery Foundation","keywords":"Artificial intelligence; Convolutional neural network; Boltzmann machine; Segmentation; Pattern recognition (psychology); Hyperintensity; Computer science; Deep learning; Support vector machine; Magnetic resonance imaging; Random forest; Similarity (geometry); White matter; Medicine; Radiology","score_opus":0.025708010811308784,"score_gpt":0.294413530707176,"score_spread":0.2687055198958672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789256791","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5117575,0.000006834088,0.4861824,0.0016882637,0.00022052787,0.00010517507,0.0000042226648,0.000023828825,0.000011302583],"genre_scores_gemma":[0.98881805,0.00002127358,0.004172558,0.006818658,0.00013881145,0.0000055762544,0.000015852691,0.000006865307,0.0000023756866],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985082,0.00027745604,0.0004371403,0.00025169054,0.00033092333,0.00019455957],"domain_scores_gemma":[0.99928534,0.00015556977,0.00019126353,0.00013007082,0.00012901158,0.00010877192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046000903,0.00012960225,0.00023289412,0.0001005559,0.00014257638,0.00003800636,0.00009516948,0.0000778166,0.000027543952],"category_scores_gemma":[0.000111366055,0.000093952985,0.000033613673,0.0003541478,0.001187044,0.0002431235,0.000073225005,0.00022919981,0.0000010195807],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005386278,0.00044561457,0.91937697,0.0001954085,0.00006449011,0.00019611784,0.0018251331,0.0019171069,0.0021930034,0.0009921317,0.0005982089,0.06680952],"study_design_scores_gemma":[0.0024764708,0.0001880457,0.19567925,0.00007717892,0.000012996121,0.00051571225,0.000104473576,0.8006675,0.00007215186,0.000025029696,0.000075237345,0.000105956264],"about_ca_topic_score_codex":0.00005977383,"about_ca_topic_score_gemma":0.000057452482,"teacher_disagreement_score":0.7987504,"about_ca_system_score_codex":0.000020847338,"about_ca_system_score_gemma":0.0000713316,"threshold_uncertainty_score":0.4373713},"labels":[],"label_agreement":null},{"id":"W2791612358","doi":"10.1016/j.compmedimag.2018.03.004","title":"Computer-aided diagnosis of cavernous malformations in brain MR images","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Vascular Malformations Diagnosis and Treatment","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Abnormality; Support vector machine; False positive paradox; CAD; Computer-aided diagnosis; Feature (linguistics); Computer vision; Medicine","score_opus":0.011829811452339098,"score_gpt":0.2795869138504252,"score_spread":0.26775710239808614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791612358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9517139,0.0010649404,0.031563066,0.014699461,0.00027185006,0.00037494703,0.00001760999,0.00008220668,0.00021201979],"genre_scores_gemma":[0.98610306,0.0012248254,0.009344184,0.0030502921,0.00015980678,0.000043077245,0.00005457759,0.000013512731,0.000006681525],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99864006,0.00006920562,0.0004647348,0.00021332595,0.00037500222,0.00023768315],"domain_scores_gemma":[0.9990108,0.00025664992,0.00009552654,0.00025539062,0.00014561723,0.00023600405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039418915,0.00015773461,0.00040020348,0.00034155638,0.00009776738,0.000029897265,0.00010161272,0.000075155716,0.000055498916],"category_scores_gemma":[0.00014891813,0.00013101894,0.000116610994,0.00039450827,0.00043871842,0.0001385052,0.000115478375,0.00018334104,0.0000076189576],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008402212,0.0019943558,0.6391199,0.0005479678,0.00030249805,0.00029854986,0.0022395672,0.0000056179347,0.00012639783,0.0039277556,0.016748147,0.3346052],"study_design_scores_gemma":[0.011925632,0.0007129441,0.80435854,0.0021278583,0.00020922675,0.00076796615,0.00016292391,0.16250674,0.0013959415,0.0009646171,0.014449706,0.0004178805],"about_ca_topic_score_codex":0.00013198286,"about_ca_topic_score_gemma":0.00001704484,"teacher_disagreement_score":0.3341873,"about_ca_system_score_codex":0.0000230642,"about_ca_system_score_gemma":0.00008106488,"threshold_uncertainty_score":0.5342797},"labels":[],"label_agreement":null},{"id":"W2791867717","doi":"10.1016/j.compmedimag.2018.01.008","title":"Automated analysis and classification of melanocytic tumor on skin whole slide images","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Dermis; Epidermis (zoology); Computer science; Artificial intelligence; Pattern recognition (psychology); Biopsy; Skin biopsy; Melanoma; Pathology; Medicine; Anatomy","score_opus":0.011945778884991492,"score_gpt":0.28250710437171256,"score_spread":0.27056132548672107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791867717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95678914,0.00020735056,0.036893092,0.004399708,0.00026496258,0.0002373835,0.0000073301517,0.00034976727,0.0008512857],"genre_scores_gemma":[0.99666756,0.0001170373,0.0015648272,0.0014166073,0.000108637534,0.0000048789757,0.000020918038,0.000010569892,0.00008893439],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889266,0.000058892314,0.00027684585,0.00028536914,0.00033290286,0.00015334843],"domain_scores_gemma":[0.99924886,0.000099373465,0.00009942802,0.00022215907,0.00010324259,0.00022696107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000294441,0.00012527638,0.00034261376,0.00047239094,0.00008489632,0.000031468073,0.000060518825,0.000045679888,0.00003254061],"category_scores_gemma":[0.00011831235,0.00010283469,0.00007725351,0.00055823417,0.0004435341,0.000029699193,0.00006422049,0.00014272223,0.0000055960586],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019109994,0.0016391893,0.08096148,0.0016005172,0.004589889,0.0014317068,0.0019641113,0.0000053337594,0.1113253,0.0062619275,0.031163394,0.7571461],"study_design_scores_gemma":[0.0028887074,0.00045584174,0.33617765,0.00028829815,0.0010241373,0.0004340427,0.00013672693,0.64308405,0.0026038417,0.00021197727,0.0124704875,0.00022423532],"about_ca_topic_score_codex":0.0000333264,"about_ca_topic_score_gemma":0.000008450845,"teacher_disagreement_score":0.7569219,"about_ca_system_score_codex":0.000013672064,"about_ca_system_score_gemma":0.00003096454,"threshold_uncertainty_score":0.4193477},"labels":[],"label_agreement":null},{"id":"W2801384393","doi":"10.1016/j.compmedimag.2018.04.008","title":"G4DARI: Geant4/GATE based Monte Carlo simulation interface for dosimetry calculation in radiotherapy","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Advanced Radiotherapy Techniques","field":"Physics and Astronomy","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Monte Carlo method; Dosimetry; Computer science; Interface (matter); Absorbed dose; DICOM; Tracking (education); Computational science; Medical physics; Physics; Nuclear medicine; Artificial intelligence; Medicine; Mathematics; Operating system","score_opus":0.00999339964603736,"score_gpt":0.326847580835895,"score_spread":0.31685418118985764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801384393","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10174903,0.00037458554,0.89677095,0.00048728814,0.00019515317,0.00029835326,0.0000095252035,0.000101371304,0.000013717737],"genre_scores_gemma":[0.9450684,0.000027571263,0.05373869,0.0006747289,0.00041478476,0.000024641375,0.000012574991,0.000029197547,0.000009395811],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989167,0.00006621119,0.00028350818,0.0003086586,0.00018037489,0.00024458562],"domain_scores_gemma":[0.999282,0.00025104766,0.0000942334,0.00017887578,0.00007541885,0.000118431206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031360367,0.00017387966,0.00025304675,0.0001733749,0.000110501285,0.00005169747,0.00013246796,0.0000639059,0.00002826824],"category_scores_gemma":[0.000019472081,0.00016261454,0.00007409411,0.00022451284,0.00024785526,0.00013979539,0.00002590572,0.00018825925,1.6856231e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051739835,0.0003277054,0.0967215,0.00010348839,0.00015383873,0.000007417818,0.0010919907,0.010951943,0.00608245,0.0026974753,0.0008822109,0.8804626],"study_design_scores_gemma":[0.0020893624,0.000061494015,0.0015669808,0.000117287556,0.000008439681,8.3552317e-7,0.000007241539,0.98637736,0.0009327924,0.00086450495,0.0077934805,0.00018024654],"about_ca_topic_score_codex":0.00007630073,"about_ca_topic_score_gemma":0.0000025260251,"teacher_disagreement_score":0.97542536,"about_ca_system_score_codex":0.000025826965,"about_ca_system_score_gemma":0.00004243362,"threshold_uncertainty_score":0.6631229},"labels":[],"label_agreement":null},{"id":"W2801459697","doi":"10.1016/j.compmedimag.2019.04.005","title":"Combo loss: Handling input and output imbalance in multi-organ segmentation","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Deep learning; Voxel; False positive paradox; Pattern recognition (psychology); False positives and false negatives; Image segmentation; Artificial neural network; Inference; Medical imaging; Leverage (statistics); Machine learning; Autoencoder; Cross entropy; Computer vision","score_opus":0.010698468367061762,"score_gpt":0.2887381605245697,"score_spread":0.2780396921575079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801459697","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93416446,0.0016417917,0.054883134,0.008356346,0.00046524574,0.00029388035,0.000001475743,0.00009659835,0.00009706609],"genre_scores_gemma":[0.98068446,0.0015763432,0.011778626,0.005674955,0.000119309145,0.000006279981,0.000032191074,0.000028352337,0.00009949508],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839854,0.000084852334,0.00036603,0.0004236751,0.00040109066,0.000325829],"domain_scores_gemma":[0.99908537,0.00019978314,0.000083110215,0.00018339722,0.0000498602,0.00039850108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072912156,0.00019555645,0.00045836525,0.00023721662,0.00007881365,0.000070530965,0.00010129861,0.00010146914,0.000016485728],"category_scores_gemma":[0.0002684037,0.00016992757,0.00004820757,0.00023324338,0.00033243536,0.0001064052,0.00013483656,0.0007633358,0.0000045966535],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006540472,0.00014051722,0.88535,0.00034733405,0.000037782032,0.00026085117,0.00073991576,0.000006805975,0.0019488838,0.0003093075,0.00017509749,0.110618114],"study_design_scores_gemma":[0.010608956,0.00007991639,0.23889281,0.0012479963,0.00004281099,0.00057222124,0.00014273204,0.74401414,0.00007670326,0.00025338042,0.0037932426,0.0002750916],"about_ca_topic_score_codex":0.000083443134,"about_ca_topic_score_gemma":0.0000037246248,"teacher_disagreement_score":0.74400735,"about_ca_system_score_codex":0.000022270282,"about_ca_system_score_gemma":0.00007457442,"threshold_uncertainty_score":0.6929445},"labels":[],"label_agreement":null},{"id":"W2801475611","doi":"10.1016/j.compmedimag.2018.04.005","title":"Retinal blood vessel segmentation using fully convolutional network with transfer learning","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":224,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; University of Saskatchewan","keywords":"Computer science; Segmentation; Artificial intelligence; Robustness (evolution); Transfer of learning; Retinal; Deep learning; Pattern recognition (psychology); Computer vision; Image segmentation; Convolutional neural network; Medical imaging; Computer-aided diagnosis; Medicine; Ophthalmology","score_opus":0.011906472963373263,"score_gpt":0.2724129232104857,"score_spread":0.26050645024711244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801475611","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63596,0.0005001355,0.36106354,0.0020459064,0.00011713535,0.00008617534,9.775888e-7,0.00010348061,0.00012266294],"genre_scores_gemma":[0.9752333,0.00023130716,0.021503791,0.0018152745,0.0010809219,0.0000038679927,0.00004965604,0.000026646801,0.000055235418],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998277,0.00011822271,0.0002880758,0.00036890365,0.00059258763,0.0003552246],"domain_scores_gemma":[0.99912244,0.00009462157,0.000056876466,0.00012952082,0.00024280025,0.00035375112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052199827,0.00019339213,0.00034611774,0.0001361454,0.0003734736,0.0000707171,0.00007541775,0.00006893422,0.00006443761],"category_scores_gemma":[0.000058794147,0.00015265906,0.00008689319,0.00045369673,0.00084462727,0.00009270403,0.000037364403,0.0004742187,0.0000024752344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018510363,0.000682405,0.88726515,0.0005687225,0.0016208662,0.0017717553,0.0014814636,0.0002312014,0.029676152,0.0025921094,0.0022226998,0.070036456],"study_design_scores_gemma":[0.009586185,0.00086186366,0.03391694,0.0025117674,0.0019172502,0.0054582483,0.00030480654,0.938258,0.0007942071,0.00042243997,0.0053291847,0.00063912955],"about_ca_topic_score_codex":0.000037599766,"about_ca_topic_score_gemma":0.000001537163,"teacher_disagreement_score":0.9380268,"about_ca_system_score_codex":0.000013017965,"about_ca_system_score_gemma":0.00014763931,"threshold_uncertainty_score":0.6225256},"labels":[],"label_agreement":null},{"id":"W2888163428","doi":"10.1016/j.compmedimag.2018.08.008","title":"Efficient multi-kernel multi-instance learning using weakly supervised and imbalanced data for diabetic retinopathy diagnosis","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Artificial intelligence; False positive paradox; Computer science; Diabetic retinopathy; Machine learning; Pattern recognition (psychology); Supervised learning; Semi-supervised learning; Kernel (algebra); Medicine; Diabetes mellitus; Mathematics","score_opus":0.044356302862242576,"score_gpt":0.3339190018480665,"score_spread":0.28956269898582393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888163428","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6797589,0.002277955,0.31541917,0.0018803409,0.00024522422,0.00026132105,0.000021380267,0.00012983564,0.0000058571395],"genre_scores_gemma":[0.91189975,0.0008877956,0.08539152,0.0013093888,0.0003146789,0.000019433088,0.00010030135,0.000046195015,0.000030955227],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976148,0.00013395764,0.00045271832,0.000852093,0.0004338109,0.00051263504],"domain_scores_gemma":[0.9981345,0.00038143777,0.00013896867,0.00054539123,0.0002593021,0.0005404247],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001034249,0.0002970296,0.000646143,0.00021287477,0.00043051882,0.00012075814,0.00027038326,0.00010552107,0.000009352566],"category_scores_gemma":[0.0012719393,0.0002530936,0.00010595231,0.00037983118,0.00097356713,0.00007455184,0.00037758102,0.00044417696,0.0000015077613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000497421,0.00097312726,0.8212805,0.0014813128,0.0004752713,0.00036005562,0.0016263656,0.00004671359,0.023442762,0.00009676515,0.00070105674,0.14901869],"study_design_scores_gemma":[0.0048296996,0.000101344085,0.017897876,0.0011038479,0.0003270966,0.00012611056,0.00014743216,0.97374964,0.00020410662,0.000015554782,0.0012169986,0.00028027483],"about_ca_topic_score_codex":0.000060361974,"about_ca_topic_score_gemma":0.000003943693,"teacher_disagreement_score":0.97370297,"about_ca_system_score_codex":0.00001998856,"about_ca_system_score_gemma":0.0000905503,"threshold_uncertainty_score":0.99999213},"labels":[],"label_agreement":null},{"id":"W2888248524","doi":"10.1016/j.compmedimag.2018.08.009","title":"Predictive connectome subnetwork extraction with anatomical and connectivity priors","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of British Columbia; BC Children's Hospital; SickKids Foundation; University of Toronto; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Connectome; Subnetwork; Prior probability; Computer science; Connectomics; Artificial intelligence; Diffusion MRI; Pattern recognition (psychology); Neuroimaging; Machine learning; Functional connectivity; Neuroscience; Magnetic resonance imaging; Bayesian probability; Psychology; Medicine","score_opus":0.01550207455365499,"score_gpt":0.2719393758273103,"score_spread":0.2564373012736553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888248524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9256977,0.00020858248,0.06425522,0.008434682,0.0006809472,0.00023047873,0.000008512579,0.00025476515,0.00022911694],"genre_scores_gemma":[0.9934997,0.00023262306,0.0005173184,0.005232518,0.00047086715,0.000015985801,0.0000017786451,0.000020077845,0.000009109555],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979669,0.00023819509,0.0001911929,0.0007501211,0.000509007,0.00034459622],"domain_scores_gemma":[0.9942177,0.0050830073,0.00009065612,0.00018381153,0.00011175008,0.0003130958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005070636,0.00022665036,0.000311883,0.00014608583,0.00053195097,0.00009731054,0.00012348706,0.00009151127,0.00001635301],"category_scores_gemma":[0.0031445576,0.00018233011,0.000036261514,0.00041763042,0.0024290467,0.00026754066,0.00020679709,0.000435109,0.0000029276032],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008614492,0.0020299524,0.48757213,0.00061000563,0.00073459325,0.0018812533,0.0070225354,0.000023346549,0.05585011,0.123200774,0.025580464,0.28688034],"study_design_scores_gemma":[0.0111401845,0.0021717602,0.33201525,0.0007825819,0.00019075819,0.0043689217,0.00046481888,0.59071237,0.008537097,0.017699812,0.030244388,0.0016720364],"about_ca_topic_score_codex":0.00002459112,"about_ca_topic_score_gemma":0.000023877887,"teacher_disagreement_score":0.59068906,"about_ca_system_score_codex":0.000023107174,"about_ca_system_score_gemma":0.00007276681,"threshold_uncertainty_score":0.89499235},"labels":[],"label_agreement":null},{"id":"W2889354701","doi":"10.1016/j.compmedimag.2018.08.005","title":"A wavelet gradient sparsity based algorithm for reconstruction of reduced-view tomography datasets obtained with a monochromatic synchrotron-based X-ray source","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal University Hospital; University of Saskatchewan","funders":"Western Economic Diversification Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Tomography; Synchrotron; Wavelet; Synchrotron radiation; Image quality; Computer science; Iterative reconstruction; Reconstruction algorithm; Reduction (mathematics); Biomedical engineering; Monochromatic color; Nuclear medicine; Algorithm; Artificial intelligence; Materials science; Computer vision; Physics; Radiology; Medicine; Optics; Mathematics; Image (mathematics)","score_opus":0.014286782213674501,"score_gpt":0.2783632079033535,"score_spread":0.264076425689679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889354701","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07164187,0.00021485827,0.92033744,0.0064575593,0.00010339494,0.00091567764,0.00009572365,0.00022323578,0.000010263553],"genre_scores_gemma":[0.31433374,0.0000684543,0.6821234,0.00265098,0.00020965283,0.0001449148,0.00043330571,0.00003227671,0.0000032300773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806154,0.00008148914,0.0004955957,0.0005044362,0.0004973387,0.0003595864],"domain_scores_gemma":[0.9981616,0.0002697564,0.00022277643,0.0005274943,0.00026607024,0.00055229536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006782317,0.0002561447,0.00058798696,0.0002972625,0.00024144186,0.000038426424,0.00019875358,0.000107404376,0.000027693608],"category_scores_gemma":[0.00014247149,0.00019894162,0.00014519603,0.00056439836,0.0018381912,0.000056676494,0.000056791185,0.00028522304,6.082876e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023498814,0.00066246866,0.0011250811,0.0011115791,0.00016099519,0.00003094148,0.00009988187,7.4858525e-7,0.0027818445,0.000256148,0.0066164644,0.98691887],"study_design_scores_gemma":[0.0043526446,0.0005878844,0.0008802352,0.002340845,0.00030502104,0.00021482853,0.00002344327,0.97776324,0.0022673917,0.00037552495,0.010632589,0.00025633903],"about_ca_topic_score_codex":0.0000493807,"about_ca_topic_score_gemma":0.0000021114568,"teacher_disagreement_score":0.9866625,"about_ca_system_score_codex":0.000022232294,"about_ca_system_score_gemma":0.000315461,"threshold_uncertainty_score":0.8112604},"labels":[],"label_agreement":null},{"id":"W2893114893","doi":"10.1016/j.compmedimag.2018.09.006","title":"3D imaging system for respiratory monitoring in pediatric intensive care environment","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Non-Invasive Vital Sign Monitoring","field":"Engineering","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire Sainte-Justine; Université TÉLUQ; École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Respiratory monitoring; Intensive care; Respiratory system; Intensive care medicine; Respiratory care; Computer science; Medicine; Medical physics; Medical emergency; Internal medicine","score_opus":0.012128037487746162,"score_gpt":0.2393271674921282,"score_spread":0.22719913000438205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893114893","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73563915,0.01499212,0.24193646,0.00012833002,0.005889614,0.0005692309,0.000012956566,0.00066717446,0.00016496661],"genre_scores_gemma":[0.99267405,0.00037797083,0.0042489762,0.0001337954,0.0024400847,0.000058234924,0.000004422102,0.00006166172,8.1472996e-7],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836767,0.000046001296,0.00038642823,0.00038296796,0.00033579158,0.0004811242],"domain_scores_gemma":[0.99906045,0.00021296236,0.00004919269,0.00023309862,0.00016540212,0.00027888885],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031952094,0.0002633727,0.00031533834,0.00033395985,0.00013961489,0.00007082796,0.00021984425,0.00008941076,0.0000016863429],"category_scores_gemma":[0.000120313045,0.00027555707,0.000069461516,0.00023488386,0.00019255234,0.00014881878,0.00015899022,0.00033946143,0.000005028041],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005911867,0.00003204377,0.82678217,0.0027338478,0.00007059949,0.0004364551,0.004492014,0.00014176778,0.017239725,0.00020237752,0.0005699228,0.14723995],"study_design_scores_gemma":[0.034748066,0.00083025923,0.2380153,0.013406071,0.00082840596,0.0007054743,0.030403769,0.5547589,0.07573894,0.0013186309,0.040704347,0.00854183],"about_ca_topic_score_codex":0.000011091837,"about_ca_topic_score_gemma":0.0000010893255,"teacher_disagreement_score":0.5887669,"about_ca_system_score_codex":0.00014609829,"about_ca_system_score_gemma":0.000032716132,"threshold_uncertainty_score":0.99996966},"labels":[],"label_agreement":null},{"id":"W2894049115","doi":"10.1016/j.compmedimag.2018.09.008","title":"Automatic localization of normal active organs in 3D PET scans","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Computer vision; Artificial intelligence; Nuclear medicine; Medicine","score_opus":0.010781589195538442,"score_gpt":0.2987564076991433,"score_spread":0.28797481850360485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894049115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4112794,0.0000877372,0.5765227,0.010849335,0.00014883724,0.000364556,0.000007470932,0.00024143851,0.00049850007],"genre_scores_gemma":[0.9705529,0.00021306144,0.026248764,0.0027561423,0.00014947739,0.000016555372,0.000034706365,0.00001671349,0.0000116739175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874187,0.00004904068,0.0003722986,0.00023625095,0.00038475395,0.00021581257],"domain_scores_gemma":[0.9991543,0.00010389615,0.0000859837,0.00022619934,0.00014551198,0.0002840846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003496359,0.00012370881,0.0003181074,0.00021027763,0.00006748176,0.000012369061,0.00012050119,0.00006185197,0.00016052922],"category_scores_gemma":[0.00024552052,0.00010498717,0.00004209074,0.00053183787,0.0008875339,0.00006271207,0.00009691378,0.00027500768,0.0000026238974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023527241,0.0017887766,0.10437587,0.0014664172,0.00016320625,0.00044399715,0.0031881586,0.0000020420457,0.0066527915,0.010346466,0.019546768,0.85179025],"study_design_scores_gemma":[0.0018138731,0.00011304086,0.012389819,0.000933405,0.000055415894,0.00033220818,0.00006251855,0.97732884,0.0010591068,0.0009952605,0.0047733313,0.00014318335],"about_ca_topic_score_codex":0.00008447987,"about_ca_topic_score_gemma":0.000008888497,"teacher_disagreement_score":0.9773268,"about_ca_system_score_codex":0.00001698524,"about_ca_system_score_gemma":0.0001408608,"threshold_uncertainty_score":0.42812526},"labels":[],"label_agreement":null},{"id":"W2896083617","doi":"10.1016/j.compmedimag.2018.10.004","title":"Evaluation of accuracy of automatic out-of-plane respiratory gating for DCEUS-based quantification using principal component analysis","year":2018,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Ultrasound and Hyperthermia Applications","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China","keywords":"Gating; Principal component analysis; Respiratory system; Parametric statistics; Distortion (music); Robustness (evolution); Medicine; Computer science; Biomedical engineering; Mathematics; Internal medicine; Artificial intelligence; Chemistry; Statistics","score_opus":0.06748973858324665,"score_gpt":0.3482423049209397,"score_spread":0.2807525663376931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896083617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5856693,0.0001817439,0.41383132,0.00002681694,0.00008126634,0.00015543168,0.000013398176,0.000032638975,0.000008122093],"genre_scores_gemma":[0.9822645,0.000011779811,0.017569475,0.000030161526,0.000054385197,0.000015652176,0.00004292042,0.000010972959,1.0841672e-7],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987254,0.00007866397,0.000495545,0.00013768242,0.0004530353,0.00010964941],"domain_scores_gemma":[0.99862903,0.00046398718,0.0002058739,0.00021445911,0.00041990832,0.000066708184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013667649,0.0000939448,0.0002932098,0.00023569152,0.00006182164,0.000010494192,0.00011645983,0.000053380696,0.0000111561685],"category_scores_gemma":[0.00029962565,0.000090231646,0.00008718976,0.00036276376,0.00024503827,0.00004352167,0.000014864965,0.00006829796,1.6026016e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032925043,0.00030440436,0.011018682,0.0015646447,0.0010573416,4.3401377e-7,0.0016753918,0.011509723,0.79053974,0.0014679984,0.000039487026,0.18078923],"study_design_scores_gemma":[0.0006867532,0.000020648336,0.0075058592,0.00015647373,0.0006395219,5.939948e-7,0.000027772687,0.98236334,0.008208655,0.00019201271,0.00011689576,0.00008147392],"about_ca_topic_score_codex":0.000013924125,"about_ca_topic_score_gemma":0.000009124946,"teacher_disagreement_score":0.9708536,"about_ca_system_score_codex":0.000014474247,"about_ca_system_score_gemma":0.0000906034,"threshold_uncertainty_score":0.367954},"labels":[],"label_agreement":null},{"id":"W2912553012","doi":"10.1016/j.compmedimag.2019.01.004","title":"Layer-based visualization and biomedical information exploration of multi-channel large histological data","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Illinois State University","keywords":"Computer science; Software; Visualization; Volume rendering; Scalability; Clipping (morphology); Computer vision; Digital pathology; Process (computing); Rendering (computer graphics); Artificial intelligence; Data visualization; Computer graphics (images); Database","score_opus":0.025650986903780496,"score_gpt":0.3131518845660638,"score_spread":0.2875008976622833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912553012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1061282,0.00044453514,0.89284664,0.00035403436,0.000049017097,0.00012045049,0.000013065801,0.00003191384,0.000012119903],"genre_scores_gemma":[0.9924842,0.00064409804,0.0035676335,0.0010952526,0.00004018635,0.000004636984,0.0021519358,0.000007052394,0.0000049739633],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999059,0.000073670475,0.00027724568,0.00024295444,0.00022403359,0.00012305538],"domain_scores_gemma":[0.99934185,0.000027737648,0.000115387855,0.00031416488,0.00009282982,0.00010801095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051084155,0.000101940204,0.00017411029,0.00012015094,0.00004104135,0.000026822307,0.00017712705,0.00013112203,0.0000074071363],"category_scores_gemma":[0.00023173293,0.00008935577,0.000029968523,0.00012667454,0.00018823889,0.000048395195,0.00030427353,0.000088904926,8.599945e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011547909,0.00427387,0.055524103,0.0029094233,0.0007715206,0.000074071446,0.002238303,0.000056140812,0.5906759,0.0069302884,0.05643359,0.278958],"study_design_scores_gemma":[0.0021363436,0.00013933642,0.0009007235,0.000073032126,0.00003921364,0.000013958964,0.00007403665,0.9561678,0.0059723,0.00011597745,0.034179658,0.0001875907],"about_ca_topic_score_codex":0.0000110438195,"about_ca_topic_score_gemma":0.000003195937,"teacher_disagreement_score":0.95611167,"about_ca_system_score_codex":0.0000029131124,"about_ca_system_score_gemma":0.000045733213,"threshold_uncertainty_score":0.36438227},"labels":[],"label_agreement":null},{"id":"W2913982995","doi":"10.1016/j.compmedimag.2019.01.006","title":"Novel lymph node segmentation and proliferation index measurement for skin melanoma biopsy images","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Higher Education and Scientific Research","keywords":"Lymph; Lymph node; Melanoma; Lymphatic system; Biopsy; Medicine; Histogram; Pathology; Computer science; Artificial intelligence; Cancer research; Image (mathematics)","score_opus":0.015208840713368189,"score_gpt":0.25964896830090106,"score_spread":0.24444012758753286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913982995","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35678092,0.00043541924,0.63461024,0.006033964,0.00068439,0.0011276266,0.0000075200337,0.00013558152,0.0001843579],"genre_scores_gemma":[0.9867863,0.00018270576,0.009925083,0.0026877376,0.00020217003,0.0000557009,0.000039872833,0.000021819715,0.00009862374],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987123,0.000025679814,0.000252287,0.0003294092,0.00048961444,0.00019069336],"domain_scores_gemma":[0.9993811,0.00005082008,0.00007360638,0.00014320141,0.00013863343,0.00021258795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047203232,0.00015350395,0.0002454324,0.00017570119,0.000100404024,0.00007671732,0.000045916335,0.000068411005,0.000017712178],"category_scores_gemma":[0.000069242946,0.00013253988,0.00005612833,0.00011344144,0.000092051385,0.0000705263,0.000060053928,0.000111579495,0.0000022562847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015962168,0.00089963194,0.13030966,0.0027559875,0.00061993895,0.00011980155,0.00090051844,0.000011643902,0.21536216,0.002783245,0.0026803915,0.6419608],"study_design_scores_gemma":[0.038233954,0.0006110576,0.25444615,0.001311861,0.0005063929,0.0046721455,0.00061877473,0.67204404,0.0066023055,0.00092529255,0.019046325,0.000981698],"about_ca_topic_score_codex":0.00002287874,"about_ca_topic_score_gemma":0.0000018717341,"teacher_disagreement_score":0.6720324,"about_ca_system_score_codex":0.00003758594,"about_ca_system_score_gemma":0.000058213525,"threshold_uncertainty_score":0.5404819},"labels":[],"label_agreement":null},{"id":"W2920834488","doi":"10.1016/j.compmedimag.2019.03.003","title":"Special issue on machine learning in medical imaging","year":2019,"lang":"en","type":"editorial","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Pattern recognition (psychology); Encoder; Discriminative model; Ground truth; Deep learning; Similarity (geometry); Computer vision; Encoding (memory); Noise (video); Set (abstract data type); Backpropagation; Artificial neural network; Image (mathematics)","score_opus":0.006347021992782732,"score_gpt":0.2697452148390441,"score_spread":0.26339819284626137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920834488","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000036208003,0.0014750785,0.109611325,0.00902867,0.8775748,0.0002798528,0.000011217757,0.0005080526,0.0014748222],"genre_scores_gemma":[0.00031287794,0.0034654057,0.0017505095,0.0025793365,0.9913961,0.000024622828,0.000112510505,0.00009128434,0.00026733635],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921349,0.0005426903,0.00087930536,0.0015851718,0.004005183,0.00085274724],"domain_scores_gemma":[0.99548554,0.0024982875,0.00034847547,0.0007944379,0.00018355151,0.00068970956],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002537468,0.0006699969,0.0010214441,0.0008857829,0.00026289237,0.0004715193,0.0021262267,0.00089650945,0.00016254265],"category_scores_gemma":[0.0023154847,0.0006453791,0.00020097675,0.00085390324,0.00045864854,0.00036897926,0.001419949,0.0059940796,0.000064707594],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038156788,0.00004712113,0.00033709273,0.00013097534,0.000021272945,0.00057760166,0.00017499496,0.000008483559,9.2528825e-7,0.0002666444,0.6200646,0.37833214],"study_design_scores_gemma":[0.0015750516,0.00005255663,0.000054859313,0.00095474964,0.000009965241,0.000057886202,0.000004608463,0.38844606,0.0000017727207,0.00038211705,0.6080592,0.00040117025],"about_ca_topic_score_codex":0.00025026465,"about_ca_topic_score_gemma":0.000050985167,"teacher_disagreement_score":0.38843757,"about_ca_system_score_codex":0.0001976949,"about_ca_system_score_gemma":0.0011029672,"threshold_uncertainty_score":0.99959975},"labels":[],"label_agreement":null},{"id":"W2944278013","doi":"10.1016/j.compmedimag.2019.04.007","title":"Muscle segmentation in axial computed tomography (CT) images at the lumbar (L3) and thoracic (T4) levels for body composition analysis","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Nutrition and Health in Aging","field":"Medicine","cited_by":105,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Simon Fraser University","funders":"National Cancer Institute","keywords":"Sarcopenia; Skeletal muscle; Lumbar; Segmentation; Medicine; Cachexia; Computer science; Radiology; Cancer; Anatomy; Artificial intelligence; Internal medicine","score_opus":0.020867833366241772,"score_gpt":0.34056369060933805,"score_spread":0.3196958572430963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944278013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93739176,0.0013995925,0.04920436,0.010748455,0.00029276774,0.0008167083,0.000032926844,0.00008074418,0.000032705713],"genre_scores_gemma":[0.9884148,0.00048257117,0.0055989563,0.005028003,0.00013495177,0.000033719738,0.00027347574,0.000016340242,0.00001718693],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983925,0.0001495325,0.0004082297,0.00038958073,0.00036674627,0.00029336844],"domain_scores_gemma":[0.9990591,0.0002781099,0.00011032131,0.00019318081,0.00009799025,0.00026133913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078684237,0.0001712398,0.00045320307,0.00049186096,0.00024004054,0.00006873683,0.00008141507,0.000059802274,0.000040507064],"category_scores_gemma":[0.00002403831,0.00013572838,0.00013786112,0.000722814,0.00027462325,0.00009755079,0.000092057366,0.00029692412,0.0000016094053],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082454144,0.00086022407,0.73890746,0.0031941424,0.0008358201,0.00018809258,0.0015777553,0.000023613915,0.05036573,0.0014169454,0.0034238494,0.19838181],"study_design_scores_gemma":[0.0071525145,0.00013053797,0.7606349,0.0005718988,0.0004274368,0.00015514898,0.0001553162,0.22754268,0.00064577576,0.0006654567,0.0016642307,0.0002541276],"about_ca_topic_score_codex":0.000037269067,"about_ca_topic_score_gemma":0.000014046729,"teacher_disagreement_score":0.22751907,"about_ca_system_score_codex":0.000032188946,"about_ca_system_score_gemma":0.00004051647,"threshold_uncertainty_score":0.55348426},"labels":[],"label_agreement":null},{"id":"W2946638670","doi":"10.1016/j.compmedimag.2019.04.006","title":"Model-free prostate cancer segmentation from dynamic contrast-enhanced MRI with recurrent convolutional networks: A feasibility study","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Capital District Health Authority; Health Research Foundation; Nova Scotia Health Authority; Izaak Walton Killam Health Centre; Dalhousie University","funders":"Research Nova Scotia","keywords":"Computer science; Segmentation; Dynamic contrast; Magnetic resonance imaging; Convolutional neural network; Artificial intelligence; Dynamic contrast-enhanced MRI; Prostate cancer; Image segmentation; Deep learning; Contrast (vision); Pattern recognition (psychology); Computer vision; Cancer; Medicine; Radiology","score_opus":0.013175463918487047,"score_gpt":0.2949795890372595,"score_spread":0.28180412511877245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946638670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9326831,0.003602494,0.05810334,0.003017725,0.00041342468,0.001956399,0.00011798913,0.0000931602,0.000012378666],"genre_scores_gemma":[0.99321634,0.0028952353,0.0021008125,0.0011379407,0.00007766893,0.0002717997,0.00025899225,0.000023596836,0.000017595316],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802905,0.00008323863,0.0003446636,0.00062933203,0.000594197,0.00031948977],"domain_scores_gemma":[0.9988349,0.00013064183,0.0001286996,0.00036571085,0.00017949687,0.00036052475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002442825,0.00025861492,0.0004930365,0.00006884394,0.00008521687,0.00005145918,0.000110620975,0.000058736114,0.000050128318],"category_scores_gemma":[0.000021483396,0.00018860029,0.0000662326,0.00018243211,0.0002181501,0.000113608585,0.00010519297,0.00032306413,0.0000014793771],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034775988,0.002844079,0.91938704,0.0001816376,0.00084514974,0.00012741119,0.0018744653,0.001209555,0.0005995827,0.000113252354,0.00068101403,0.068659194],"study_design_scores_gemma":[0.020976441,0.0007421909,0.20126192,0.0008002662,0.00028162735,0.000013634757,0.00020651307,0.77483726,0.000035325113,0.0005529673,0.00005460271,0.00023724811],"about_ca_topic_score_codex":0.00013882258,"about_ca_topic_score_gemma":0.00019404152,"teacher_disagreement_score":0.7736277,"about_ca_system_score_codex":0.0001576522,"about_ca_system_score_gemma":0.00028692957,"threshold_uncertainty_score":0.76908964},"labels":[],"label_agreement":null},{"id":"W2972134583","doi":"10.1016/j.compmedimag.2019.101658","title":"Dense pooling layers in fully convolutional network for skin lesion segmentation","year":2019,"lang":"en","type":"preprint","venue":"Computerized Medical Imaging and Graphics","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Segmentation; Pooling; Artificial intelligence; Computer science; Convolutional neural network; Skin lesion; Lesion; Pattern recognition (psychology); Image segmentation; Computer vision; Medicine; Pathology","score_opus":0.020681138087428063,"score_gpt":0.2951487750917912,"score_spread":0.27446763700436316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972134583","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30034998,0.0019909935,0.6830576,0.0072501795,0.004796155,0.0021582113,0.000023434515,0.00020453979,0.00016889327],"genre_scores_gemma":[0.9547722,0.0031222745,0.031058215,0.007951715,0.0017689683,0.00015447568,0.0008350715,0.00007228903,0.0002648113],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815714,0.000081947925,0.00045769205,0.0005203735,0.00045510937,0.00032772185],"domain_scores_gemma":[0.999063,0.00022026912,0.00015332567,0.00022365621,0.000103723774,0.00023601663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068280427,0.00024629312,0.00049268035,0.00028931457,0.00009236659,0.00006238256,0.00010350134,0.00024075524,0.00002024684],"category_scores_gemma":[0.000100551406,0.00024045093,0.00016725287,0.00014685138,0.00012153448,0.000028867238,0.0003087327,0.0006584863,0.0000030750705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0063165952,0.001358951,0.053969406,0.012651088,0.0014924792,0.0021583452,0.0020449911,0.011432652,0.0020799334,0.009247895,0.07964294,0.8176047],"study_design_scores_gemma":[0.007544335,0.00015204091,0.011901815,0.0026654152,0.00023764692,0.0005260263,0.00014369981,0.9491975,0.000035797224,0.003375847,0.023748977,0.0004709422],"about_ca_topic_score_codex":0.00006165685,"about_ca_topic_score_gemma":0.000018652257,"teacher_disagreement_score":0.9377648,"about_ca_system_score_codex":0.00008629048,"about_ca_system_score_gemma":0.0002081671,"threshold_uncertainty_score":0.98053044},"labels":[],"label_agreement":null},{"id":"W2980262056","doi":"10.1016/j.compmedimag.2019.101657","title":"Glaucoma detection using image processing techniques: A literature review","year":2019,"lang":"en","type":"review","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":80,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Glaucoma; Computer science; Image processing; Computer vision; Artificial intelligence; Image (mathematics); Medicine; Ophthalmology","score_opus":0.027267979652517222,"score_gpt":0.3657248206469345,"score_spread":0.3384568409944173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980262056","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007745936,0.97101516,0.026896153,0.0006230314,0.00021536846,0.00082039787,0.000009118649,0.0003212864,0.000091746275],"genre_scores_gemma":[0.000005323264,0.98721623,0.009346799,0.0024351263,0.0006021904,0.000037122285,0.00018473601,0.00010518265,0.00006727239],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964435,0.0003126221,0.0010508472,0.0009130751,0.00079808483,0.0004818695],"domain_scores_gemma":[0.9978758,0.00014151001,0.0005431398,0.0005993334,0.00033383368,0.00050636573],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001032358,0.0007207636,0.003281237,0.00072640163,0.00019246167,0.00026551634,0.0002829812,0.00042537964,0.000015140183],"category_scores_gemma":[0.00034170883,0.0005222388,0.0009805055,0.0017063757,0.00036444038,0.00019618371,0.00022442138,0.0019454617,0.00000745752],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005112585,0.0000411248,0.000011359388,0.18677,0.00010982594,0.0005348498,0.000012142103,6.7452804e-10,0.000010469388,0.0000033725407,0.00026410335,0.8122376],"study_design_scores_gemma":[0.00025240774,0.000027579934,0.0000020587217,0.44094667,0.0035508182,0.0076528653,0.0000026777084,0.0070005883,0.0000022020147,0.000015505258,0.5401901,0.00035651066],"about_ca_topic_score_codex":0.000010116234,"about_ca_topic_score_gemma":2.15619e-7,"teacher_disagreement_score":0.8118811,"about_ca_system_score_codex":0.00007201159,"about_ca_system_score_gemma":0.00048040508,"threshold_uncertainty_score":0.9997229},"labels":[],"label_agreement":null},{"id":"W2983168987","doi":"10.1016/j.compmedimag.2019.101662","title":"Automated detection of focal cortical dysplasia using a deep convolutional neural network","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Epilepsy research and treatment","field":"Medicine","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cortical dysplasia; Convolutional neural network; Artificial intelligence; Computer science; Pattern recognition (psychology); Deep learning; Computer vision; Magnetic resonance imaging; Radiology; Medicine","score_opus":0.014419657154023567,"score_gpt":0.29685515747684954,"score_spread":0.282435500322826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983168987","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96674865,0.00082951935,0.031020075,0.00057916273,0.00036432274,0.00026003364,0.0000024490428,0.00015678132,0.00003898405],"genre_scores_gemma":[0.99656826,0.000092167975,0.002726558,0.00039814072,0.00016729331,0.000004484378,0.000024098186,0.00001361924,0.0000053950603],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998412,0.000113761416,0.0003029796,0.0002547198,0.00056233985,0.00035421108],"domain_scores_gemma":[0.9989679,0.00024365199,0.000060910057,0.00015475065,0.000120707446,0.0004520829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031564842,0.00013793919,0.00036277954,0.00010839717,0.00009359385,0.000017606542,0.00006095194,0.0000986852,0.0000454425],"category_scores_gemma":[0.00011536611,0.00011102598,0.00009724164,0.00027099575,0.0003847446,0.000052791813,0.000087277265,0.00038924598,0.000004294908],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002018472,0.0008683218,0.9042568,0.0006845865,0.00066318375,0.00086701167,0.00015658308,0.00020475351,0.025373772,0.0025117344,0.0003571161,0.06203763],"study_design_scores_gemma":[0.003143386,0.00025198748,0.1465351,0.00019795026,0.00006754903,0.00066470803,0.000011710547,0.8486751,0.000108156906,0.00015720821,0.00010752292,0.00007965144],"about_ca_topic_score_codex":0.00003463718,"about_ca_topic_score_gemma":0.000003338135,"teacher_disagreement_score":0.84847033,"about_ca_system_score_codex":0.00002836492,"about_ca_system_score_gemma":0.0001354111,"threshold_uncertainty_score":0.4527508},"labels":[],"label_agreement":null},{"id":"W2987676269","doi":"10.1016/j.compmedimag.2019.101659","title":"Texture classification of MR images of the brain in ALS using M-CoHOG: A multi-center study","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Neurological Disease Mechanisms and Treatments","field":"Neuroscience","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; University of Calgary; McGill University; Health Sciences Centre; Montreal Neurological Institute and Hospital; University of Toronto; University of Alberta","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; Canadian Institutes of Health Research","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Feature extraction; Histogram; Normalization (sociology); Classifier (UML); Support vector machine; Computer vision; Image (mathematics)","score_opus":0.043006793324434266,"score_gpt":0.317528405676093,"score_spread":0.27452161235165873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987676269","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99573445,0.0000428645,0.0027698437,0.00081129017,0.00019394522,0.00040649815,0.000013872547,0.0000145963495,0.000012646358],"genre_scores_gemma":[0.9987124,0.000021998192,0.00016276914,0.0010743466,0.000008739564,0.0000047487497,9.706603e-7,0.000007202984,0.000006810837],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986316,0.00030053075,0.0002665205,0.0003128009,0.0003411024,0.00014743047],"domain_scores_gemma":[0.99930984,0.00022903399,0.00012700063,0.00023028166,0.000025245354,0.00007858291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022144853,0.00011077454,0.00022870487,0.0000818506,0.00004319701,0.000016734259,0.00022522108,0.00004165638,0.000009820051],"category_scores_gemma":[0.0002457477,0.00006836794,0.00006562956,0.00027959814,0.00020618131,0.00005855095,0.00017716512,0.00017550896,6.32618e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098200486,0.0037897779,0.4677002,0.00009866822,0.000017259928,0.00007505559,0.0003512942,0.000006138723,0.5165987,0.0012332895,0.000029670233,0.010001752],"study_design_scores_gemma":[0.010257183,0.00019856228,0.7369065,0.00028038616,0.000038410413,0.000036379708,0.00011021859,0.24147178,0.009171083,0.001260785,0.00007549587,0.00019316676],"about_ca_topic_score_codex":0.000016986216,"about_ca_topic_score_gemma":0.0000016199842,"teacher_disagreement_score":0.5074276,"about_ca_system_score_codex":0.0000047544154,"about_ca_system_score_gemma":0.000026501983,"threshold_uncertainty_score":0.27879634},"labels":[],"label_agreement":null},{"id":"W2991340843","doi":"10.1016/j.compmedimag.2019.101685","title":"Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images","year":2019,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"DoD Alzheimer's Disease Neuroimaging Initiative; National Institute on Aging; Mrs Gladys Row Fogo Charitable Trust; Canadian Institutes of Health Research; Biogen","keywords":"Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Deep learning; Voxel; Convolutional neural network; Hyperintensity; Support vector machine; Unsupervised learning; Magnetic resonance imaging; Medicine","score_opus":0.04199116770319934,"score_gpt":0.27956249173300596,"score_spread":0.23757132402980663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991340843","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98415816,0.0002088803,0.007720054,0.007150863,0.00021598447,0.00042309696,0.000030196656,0.000078164456,0.000014581756],"genre_scores_gemma":[0.9881092,0.000079372694,0.009477928,0.0022092327,0.000023586204,0.000019066618,0.000009717247,0.00001889985,0.000053021176],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9984296,0.00018756604,0.00038076603,0.00044442358,0.00030755074,0.0002500919],"domain_scores_gemma":[0.9985208,0.00094944774,0.000099212695,0.000231021,0.000067767076,0.0001317566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039874407,0.00016599559,0.00033856215,0.00019956003,0.00019639377,0.000081697624,0.00015691119,0.00007122109,0.000049340706],"category_scores_gemma":[0.00031071107,0.00015688087,0.00005861248,0.00024032012,0.00046476244,0.00014090328,0.00015467823,0.00024089146,0.000001485614],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013689592,0.00020138072,0.18646336,0.0010823774,0.000012826655,0.0000080921045,0.0010991885,0.000017404414,0.7064668,0.0012108141,0.00032521476,0.10297569],"study_design_scores_gemma":[0.0013405618,0.000038146525,0.52580315,0.0002930904,0.000007140774,0.000019296169,0.00005721388,0.47099456,0.0008835482,0.0003539783,0.00009149681,0.00011783762],"about_ca_topic_score_codex":0.000023616372,"about_ca_topic_score_gemma":0.0000039204947,"teacher_disagreement_score":0.7055832,"about_ca_system_score_codex":0.000017218044,"about_ca_system_score_gemma":0.000040992807,"threshold_uncertainty_score":0.6397416},"labels":[],"label_agreement":null},{"id":"W3018269092","doi":"10.1016/j.compmedimag.2020.101718","title":"Early detection of ankylosing spondylitis using texture features and statistical machine learning, and deep learning, with some patient age analysis","year":2020,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Spondyloarthritis Studies and Treatments","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Science and ICT, South Korea; National Research Foundation of Korea","keywords":"Artificial intelligence; Random forest; Receiver operating characteristic; Cross-validation; Deep learning; Computer science; Machine learning; Classifier (UML); Pattern recognition (psychology); Cross entropy; Binary classification; Ankylosing spondylitis; Recall; Support vector machine; Medicine; Surgery","score_opus":0.007484875278572186,"score_gpt":0.2478185041883662,"score_spread":0.240333628909794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018269092","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95956236,0.011919479,0.02775551,0.00049211987,0.00003375073,0.00014610817,0.00002643953,0.00005374949,0.000010508094],"genre_scores_gemma":[0.9938226,0.0022124008,0.0034274934,0.00037568717,0.000060832666,0.0000027343208,0.00007581349,0.000018464045,0.0000039707734],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987058,0.0001055277,0.00023538289,0.00037244218,0.00036018,0.00022068176],"domain_scores_gemma":[0.9992302,0.00013175647,0.00010638228,0.000066515415,0.00006390637,0.0004012257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010221947,0.00020109046,0.0005566606,0.00016312368,0.00022805967,0.000051313335,0.000025945825,0.00007747873,0.000015663498],"category_scores_gemma":[0.00015466768,0.00015424976,0.00005681954,0.0003545777,0.00047960487,0.00006343045,0.00010242515,0.00047990165,8.6952966e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013653447,0.00017478167,0.6246608,0.00046429993,0.0018436668,0.0027298846,0.0038006888,0.000012581106,0.0020538669,0.00033859382,0.000009947497,0.36254555],"study_design_scores_gemma":[0.012102712,0.0037624442,0.69691616,0.00072658836,0.003714165,0.0016676143,0.00068264303,0.27592987,0.00017913032,0.00021065677,0.0035309976,0.0005769992],"about_ca_topic_score_codex":0.00024119047,"about_ca_topic_score_gemma":0.000025954934,"teacher_disagreement_score":0.36196858,"about_ca_system_score_codex":0.00000947944,"about_ca_system_score_gemma":0.00001670483,"threshold_uncertainty_score":0.6290123},"labels":[],"label_agreement":null},{"id":"W3044795413","doi":"10.1016/j.compmedimag.2020.101765","title":"Automatic skin lesion classification based on mid-level feature learning","year":2020,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":73,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Discriminative model; Computer science; Pattern recognition (psychology); Convolutional neural network; Feature (linguistics); Segmentation; Deep learning; Similarity (geometry); Metric (unit); Class (philosophy); Skin lesion; Feature learning; Feature extraction; Image (mathematics)","score_opus":0.03587550213371445,"score_gpt":0.28184518489544047,"score_spread":0.245969682761726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044795413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26931557,0.00040941825,0.45133308,0.27326652,0.0010839354,0.00093630224,0.000005521027,0.0014606188,0.0021890048],"genre_scores_gemma":[0.97702867,0.00010092304,0.0037668995,0.018671349,0.00025210783,0.000008441479,0.000046038364,0.00002151,0.00010404611],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872,0.000090804475,0.0001936939,0.0003250144,0.0004934854,0.00017700187],"domain_scores_gemma":[0.999186,0.00012206705,0.00007012529,0.00014572729,0.000047414476,0.0004286738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002179152,0.00015336186,0.00024787136,0.00014023455,0.00014291662,0.000050013532,0.00007685352,0.00009278656,0.00007581523],"category_scores_gemma":[0.00028703813,0.00012860767,0.00008250309,0.000275211,0.000102939346,0.000027460748,0.00005094516,0.0005348435,0.000014234587],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000318246,0.00022499077,0.0028976225,0.00064258237,0.00006233009,0.00055151025,0.00039778822,0.000027573344,0.0040986473,0.0005717574,0.015440418,0.97476655],"study_design_scores_gemma":[0.0021142357,0.0002040642,0.015728204,0.00030077586,0.000054773376,0.0001122557,0.00006854357,0.9396278,0.00012864496,0.0000325703,0.041495394,0.00013270314],"about_ca_topic_score_codex":0.000003971114,"about_ca_topic_score_gemma":5.165908e-7,"teacher_disagreement_score":0.9746338,"about_ca_system_score_codex":0.000019287723,"about_ca_system_score_gemma":0.00005325511,"threshold_uncertainty_score":0.5244469},"labels":[],"label_agreement":null},{"id":"W3049224424","doi":"10.1016/j.compmedimag.2020.101776","title":"Deep learning method for localization and segmentation of abdominal CT","year":2020,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Body Composition Measurement Techniques","field":"Medicine","cited_by":71,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Simon Fraser University","funders":"National Cancer Institute","keywords":"Jaccard index; Segmentation; Convolutional neural network; Adipose tissue; Computer science; Lumbar; Artificial intelligence; Lumbar vertebrae; Pattern recognition (psychology); Medicine; Nuclear medicine; Anatomy","score_opus":0.02254913733744719,"score_gpt":0.3235346784254246,"score_spread":0.3009855410879774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049224424","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00832788,0.000503971,0.98656213,0.0041746437,0.000038458118,0.00026608963,8.3812796e-7,0.000105304294,0.000020665273],"genre_scores_gemma":[0.58123153,0.00043268327,0.41326487,0.00483092,0.00013531809,0.00001754705,0.00006661139,0.000018206945,0.0000023008995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914336,0.00008170335,0.00022958209,0.00018508676,0.00026494238,0.00009530697],"domain_scores_gemma":[0.99942434,0.00013403743,0.00008120743,0.000048552556,0.00011667667,0.0001951917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044402923,0.00008708644,0.00023056181,0.0000740591,0.00006984107,0.000016512211,0.00003497317,0.000030536306,0.0000066186603],"category_scores_gemma":[0.00021398976,0.00008015428,0.00004056783,0.0001327862,0.00012052982,0.000050771807,0.000036151956,0.00014814587,9.58371e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055837265,0.00012095154,0.024072692,0.0016998886,0.00012896322,0.000041340136,0.0009918223,0.000024461164,0.09117741,0.0023375526,0.0008660103,0.87798053],"study_design_scores_gemma":[0.0024814745,0.0002256809,0.0012030723,0.00024086442,0.00011223922,0.00009729064,0.0000666597,0.9869928,0.00597297,0.00043566313,0.0020853782,0.000085957705],"about_ca_topic_score_codex":0.0000053976114,"about_ca_topic_score_gemma":2.337181e-7,"teacher_disagreement_score":0.9869683,"about_ca_system_score_codex":0.0000060889993,"about_ca_system_score_gemma":0.000023136352,"threshold_uncertainty_score":0.32685965},"labels":[],"label_agreement":null},{"id":"W3092474017","doi":"10.1016/j.compmedimag.2020.101795","title":"Multislice left ventricular ejection fraction prediction from cardiac MRIs without segmentation using shared SptDenNet","year":2020,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Chongqing; National Natural Science Foundation of China","keywords":"Ejection fraction; Segmentation; Computer science; Softmax function; Artificial intelligence; Pattern recognition (psychology); Fraction (chemistry); Image segmentation; Deep learning; Heart failure; Medicine; Cardiology","score_opus":0.0172539242376901,"score_gpt":0.2797746010280586,"score_spread":0.2625206767903685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092474017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.64960027,0.0017721597,0.34377813,0.0027418486,0.0012745132,0.0003608145,0.000090892674,0.00034126514,0.000040080446],"genre_scores_gemma":[0.97825044,0.00094170123,0.01389089,0.0039336253,0.002089315,0.000009819903,0.00083390716,0.00004665313,0.0000036506729],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981136,0.00013576573,0.00036459867,0.00048972806,0.00064239505,0.00025393366],"domain_scores_gemma":[0.99877465,0.00020648193,0.00012835945,0.00018002327,0.00016472988,0.00054576754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024460282,0.00022531195,0.00045789793,0.00013712872,0.0001847794,0.0001185539,0.000059649374,0.00014184504,0.000033469434],"category_scores_gemma":[0.0005042496,0.00022451443,0.00017112959,0.00027975152,0.00014007166,0.00025254174,0.00007846625,0.00048270647,0.0000070835767],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022960255,0.00012731146,0.95568305,0.0001643886,0.0002772732,0.00023192483,0.0006237658,0.000060117272,0.015113748,0.0000110793435,0.004587104,0.022890644],"study_design_scores_gemma":[0.004449307,0.000096063384,0.18234447,0.00052040693,0.00082800613,0.00019562514,0.00038514438,0.8021934,0.0011632874,0.00006172552,0.007449553,0.00031299228],"about_ca_topic_score_codex":0.000322252,"about_ca_topic_score_gemma":7.688552e-7,"teacher_disagreement_score":0.8021333,"about_ca_system_score_codex":0.00006430537,"about_ca_system_score_gemma":0.000089400004,"threshold_uncertainty_score":0.91554326},"labels":[],"label_agreement":null},{"id":"W3093396211","doi":"10.1016/j.compmedimag.2020.101797","title":"Atlas-based score for automatic glaucoma risk stratification","year":2020,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Glaucoma and retinal disorders","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St Mary's Hospital; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Glaucoma; Optic disc; Atlas (anatomy); Artificial intelligence; Optic nerve; Computer science; Optic disk; Linear discriminant analysis; Optic cup (embryology); Receiver operating characteristic; Ophthalmology; Pattern recognition (psychology); Medicine; Machine learning; Anatomy; Biology","score_opus":0.016663361728733526,"score_gpt":0.2716730077404185,"score_spread":0.255009646011685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093396211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68723136,0.00079848175,0.2721195,0.038828656,0.00017538696,0.0005376253,0.000010679338,0.00024373272,0.00005460052],"genre_scores_gemma":[0.9794626,0.00016045655,0.0120006725,0.007982249,0.00020586386,0.000030766474,0.00012607052,0.000025009675,0.000006299252],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873054,0.000060137743,0.00030758465,0.00032327,0.0003467648,0.00023171859],"domain_scores_gemma":[0.9988835,0.00023040532,0.00009921124,0.00016095083,0.00009262025,0.000533353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023363912,0.00016570202,0.0003204961,0.00007471047,0.00014896628,0.00004330718,0.00010976464,0.00009103617,0.000025218036],"category_scores_gemma":[0.0004533372,0.00013200573,0.00013429557,0.00022888245,0.00027249384,0.000040206225,0.000029830888,0.00029309647,0.000004069864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077067764,0.0005567889,0.5252579,0.0033490248,0.00022894323,0.00018542525,0.00086728635,0.0000012418086,0.002775558,0.00620082,0.016839242,0.4429671],"study_design_scores_gemma":[0.004033565,0.0002626105,0.12849864,0.00029782596,0.00017042317,0.00003909294,0.000058214267,0.8603074,0.0001254054,0.0008958406,0.0051432108,0.00016775033],"about_ca_topic_score_codex":0.000012699009,"about_ca_topic_score_gemma":0.0000015243676,"teacher_disagreement_score":0.8603062,"about_ca_system_score_codex":0.00000649193,"about_ca_system_score_gemma":0.00014196949,"threshold_uncertainty_score":0.53830373},"labels":[],"label_agreement":null},{"id":"W3115704871","doi":"10.1016/j.compmedimag.2020.101850","title":"MR and ultrasound cardiac image dynamic visualization and synchronization over Internet for distributed heart function diagnosis","year":2020,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"School of Information Technology, King Mongkut's University of Technology Thonburi; Robarts Research Institute; Center for Advanced Surgical Technology, University of Nebraska Medical Center; College of Arts and Sciences, Boston University; Illinois State University","keywords":"Computer science; Visualization; Rendering (computer graphics); The Internet; Synchronizing; Software; Web application; Computer vision; Multimedia; Computer graphics (images); Artificial intelligence; World Wide Web","score_opus":0.008927153646253664,"score_gpt":0.28010444509971305,"score_spread":0.27117729145345937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115704871","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0147521,0.0007946073,0.9797136,0.0037895502,0.00025122028,0.00034352162,0.000024854311,0.00032829493,0.0000022051515],"genre_scores_gemma":[0.89175224,0.0031344257,0.09271478,0.011532178,0.00020844747,0.00013117945,0.0004837056,0.00003721483,0.0000058506052],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984982,0.00012754832,0.00030284215,0.0005116423,0.00035036835,0.00020940491],"domain_scores_gemma":[0.99879575,0.00045461138,0.00009136661,0.00013889324,0.00011189135,0.00040749973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003801607,0.00017810406,0.00026817687,0.00011582546,0.00013066885,0.0003645179,0.00016584256,0.00008945544,0.00001004621],"category_scores_gemma":[0.0005544242,0.00017087306,0.00004556176,0.00039345727,0.00030686866,0.0005292947,0.00022485966,0.00016200873,5.4990534e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016938602,0.00029106165,0.06641534,0.0018258974,0.00031265197,0.000045777262,0.0040173256,0.0000027581066,0.017738633,0.030798823,0.07444282,0.8039395],"study_design_scores_gemma":[0.0012547633,0.000163265,0.009663144,0.00014966913,0.000050092705,0.00002453818,0.000034714452,0.9827521,0.0009081116,0.0015167986,0.0032121122,0.00027067852],"about_ca_topic_score_codex":0.000012989949,"about_ca_topic_score_gemma":8.012637e-7,"teacher_disagreement_score":0.98274934,"about_ca_system_score_codex":0.000017977029,"about_ca_system_score_gemma":0.000036678382,"threshold_uncertainty_score":0.6968001},"labels":[],"label_agreement":null},{"id":"W3118362352","doi":"10.1016/j.compmedimag.2020.101845","title":"A deep learning approach to the screening of malaria infection: Automated and rapid cell counting, object detection and instance segmentation using Mask R-CNN","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Singapore University of Technology and Design","keywords":"Computer science; Artificial intelligence; Segmentation; Deep learning; Minimum bounding box; Object detection; Visualization; Blood smear; Bounding overwatch; Machine learning; Pattern recognition (psychology); Standardization; Cell counting; Feature (linguistics); Computer vision; Object (grammar); Malaria; Image (mathematics); Pathology; Medicine","score_opus":0.011543403577875958,"score_gpt":0.24423613880119457,"score_spread":0.23269273522331863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118362352","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24573065,0.001676594,0.7517082,0.00028835572,0.00016167099,0.00011923988,0.0000010722108,0.00022084912,0.00009338028],"genre_scores_gemma":[0.9188184,0.00024969564,0.08032238,0.000529096,0.00004822947,0.000007241781,0.000007459069,0.0000133191525,0.0000041697704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848443,0.00017348124,0.0002753067,0.00044408604,0.00039151133,0.0002311836],"domain_scores_gemma":[0.999181,0.00013992563,0.0001384183,0.00019707199,0.0001396784,0.00020393409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049085135,0.00016732562,0.00021926545,0.00015719626,0.0003262908,0.00051767397,0.00015808812,0.0000482308,9.2417713e-7],"category_scores_gemma":[0.00017066608,0.00014822946,0.000043105727,0.00071297,0.00021278222,0.0005287551,0.00043205475,0.00023515777,2.030425e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005857593,0.00038288397,0.044861287,0.00091887824,0.00017086203,0.00010008429,0.0041754697,0.003268659,0.013735901,0.0024600239,0.00008931499,0.92977804],"study_design_scores_gemma":[0.00076845376,0.000030866275,0.013150501,0.00015876959,0.000036545145,0.00026682526,0.0001111967,0.9840184,0.0007834719,0.00014193774,0.00036982377,0.00016324765],"about_ca_topic_score_codex":0.00006115123,"about_ca_topic_score_gemma":0.0000048725033,"teacher_disagreement_score":0.9807497,"about_ca_system_score_codex":0.000010866095,"about_ca_system_score_gemma":0.000060999995,"threshold_uncertainty_score":0.6044622},"labels":[],"label_agreement":null},{"id":"W3134090113","doi":"10.1016/j.compmedimag.2021.101897","title":"Automatic MR image quality evaluation using a Deep CNN: A reference-free method to rate motion artifacts in neuroimaging","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Artifact (error); Computer vision; Deep learning; Image quality; Motion (physics); Pattern recognition (psychology); Transfer of learning; Neuroimaging; Artificial neural network; Image (mathematics)","score_opus":0.08627831177713087,"score_gpt":0.4421554781936364,"score_spread":0.3558771664165055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134090113","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21316639,0.00018127564,0.7776117,0.008334218,0.000059000835,0.00039995008,0.0000030126791,0.00015163662,0.00009284239],"genre_scores_gemma":[0.2822073,0.0001207283,0.71303314,0.0043971185,0.00008168015,0.00006767723,0.00006040198,0.00002579698,0.000006144068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997651,0.00047326752,0.0005297113,0.0005170384,0.0005283331,0.00030067246],"domain_scores_gemma":[0.9984288,0.00027201365,0.00011599064,0.00049897505,0.0003246843,0.00035950282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020961198,0.00018212433,0.00041021922,0.0002266235,0.00011823084,0.0000671512,0.00012517751,0.00007876703,0.000052528503],"category_scores_gemma":[0.0012887573,0.0001765008,0.00006510525,0.0007498618,0.000106543186,0.00014863095,0.00022808583,0.0004303403,0.0000021655462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051357067,0.00033346418,0.0025156054,0.00028221024,0.000017184631,0.00023239254,0.000489457,0.00012811885,0.101459794,0.0033131824,0.00015189435,0.89102536],"study_design_scores_gemma":[0.0018087468,0.000021095544,0.02436207,0.00047491907,0.000073844996,0.00022112604,0.00009155634,0.95613116,0.0018040958,0.014330783,0.00049362826,0.00018697038],"about_ca_topic_score_codex":0.00006153312,"about_ca_topic_score_gemma":0.000014004978,"teacher_disagreement_score":0.95600307,"about_ca_system_score_codex":0.000066264525,"about_ca_system_score_gemma":0.00020364896,"threshold_uncertainty_score":0.7197494},"labels":[],"label_agreement":null},{"id":"W3134143614","doi":"10.1016/j.compmedimag.2021.101893","title":"Automated proliferation index calculation for skin melanoma biopsy images using machine learning","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cutaneous Melanoma Detection and Management","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Higher Education and Scientific Research","keywords":"Artificial intelligence; Convolutional neural network; Region of interest; Computer science; Pattern recognition (psychology); Melanoma; Image (mathematics); Ki-67; Skin cancer; Computer vision; Cancer; Pathology; Medicine; Immunohistochemistry","score_opus":0.01417279708166868,"score_gpt":0.287529039098716,"score_spread":0.27335624201704734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134143614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39209116,0.00067058334,0.6022695,0.0033753493,0.00051169674,0.00042474913,0.0000057710427,0.00058091484,0.00007030241],"genre_scores_gemma":[0.98142314,0.00014381118,0.016480166,0.0012280548,0.00029121753,0.00001668403,0.00020984128,0.000029406096,0.00017766083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987834,0.00008375586,0.00028906472,0.00031832876,0.00031426954,0.00021119553],"domain_scores_gemma":[0.99931216,0.00008295151,0.000081869,0.00013029335,0.00017989447,0.00021284392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029860166,0.00015050652,0.00027252594,0.00017993206,0.00022373049,0.000089290406,0.000038105492,0.00009164808,0.000024555522],"category_scores_gemma":[0.00023744444,0.00013957632,0.00009214215,0.00026877742,0.00008900778,0.00006327735,0.00007338282,0.00023722193,0.0000010002514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019641514,0.0015057907,0.2538834,0.0035842108,0.0014211962,0.0054946253,0.0015739738,0.000677342,0.17706923,0.0041762255,0.0046143406,0.5440355],"study_design_scores_gemma":[0.0025715407,0.000056629742,0.007463379,0.0001672545,0.000099854326,0.0025159982,0.00003108122,0.9788401,0.0012260102,0.00010352878,0.0067778085,0.00014681366],"about_ca_topic_score_codex":0.000037169477,"about_ca_topic_score_gemma":0.00000570261,"teacher_disagreement_score":0.97816277,"about_ca_system_score_codex":0.000029248304,"about_ca_system_score_gemma":0.000096526026,"threshold_uncertainty_score":0.5691757},"labels":[],"label_agreement":null},{"id":"W3152852152","doi":"10.1016/j.compmedimag.2021.101924","title":"Learnable image histograms-based deep radiomics for renal cell carcinoma grading and staging","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Nvidia","keywords":"Renal cell carcinoma; Computer science; Artificial intelligence; Grading (engineering); Histogram; Convolutional neural network; Radiology; Image histogram; Pattern recognition (psychology); Medicine; Image processing; Image texture; Image (mathematics); Pathology","score_opus":0.009041228140708143,"score_gpt":0.2655155306184199,"score_spread":0.2564743024777118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152852152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31601104,0.0061088842,0.6598964,0.016559456,0.00056908256,0.00032469255,0.000008176717,0.00018574035,0.0003365351],"genre_scores_gemma":[0.787858,0.0010675223,0.19768208,0.011999013,0.0007098975,0.000035712175,0.0002475362,0.00012356976,0.00027664757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99758476,0.00011858777,0.00047150307,0.0006943276,0.00050959556,0.00062119646],"domain_scores_gemma":[0.99789566,0.00052861054,0.00012992068,0.00031984464,0.00021062781,0.0009153576],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009352758,0.00031720052,0.0006498627,0.00025511242,0.00039703582,0.00019728807,0.00014601497,0.00013788385,0.000027718046],"category_scores_gemma":[0.0006882811,0.0003024271,0.00019172831,0.00032850658,0.0006375559,0.00011250578,0.00015186158,0.00088130427,7.7032195e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006882451,0.000945839,0.093062244,0.0050939764,0.00026143133,0.0054610455,0.0014974041,0.000055295874,0.11119182,0.004584006,0.011412296,0.7657464],"study_design_scores_gemma":[0.009102609,0.00012863913,0.002200211,0.00044630072,0.00025558335,0.0009251913,0.00014253912,0.9270763,0.0016472205,0.0008929544,0.056746487,0.0004359941],"about_ca_topic_score_codex":0.000050919603,"about_ca_topic_score_gemma":0.000001918938,"teacher_disagreement_score":0.92702097,"about_ca_system_score_codex":0.00004949124,"about_ca_system_score_gemma":0.00034340966,"threshold_uncertainty_score":0.9999428},"labels":[],"label_agreement":null},{"id":"W3158390318","doi":"10.1016/j.compmedimag.2021.101928","title":"Recent advances in artificial intelligence for cardiac imaging","year":2021,"lang":"en","type":"editorial","venue":"Computerized Medical Imaging and Graphics","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"H2020 European Research Council; Innovative Medicines Initiative; British Heart Foundation","keywords":"Computer science; Artificial intelligence","score_opus":0.014404003518200486,"score_gpt":0.3245315387070613,"score_spread":0.3101275351888608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158390318","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007395951,0.24553809,0.05852798,0.006368987,0.6883244,0.0006277004,0.00018260458,0.00017296513,0.0001833512],"genre_scores_gemma":[0.0005838518,0.2727136,0.0058012935,0.0019243209,0.7162227,0.00017188178,0.0023850023,0.00015841353,0.000038915852],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99595416,0.00016175643,0.0009019209,0.0010145216,0.0012651959,0.00070242357],"domain_scores_gemma":[0.9941626,0.0038481043,0.00019096497,0.0004912701,0.0007218008,0.00058523554],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013992246,0.0005201066,0.0014375445,0.00044172528,0.00015395273,0.00019685755,0.00021935774,0.0004401209,0.000017007635],"category_scores_gemma":[0.008766282,0.0005137401,0.00041755772,0.00053567404,0.0005417507,0.00012886421,0.00026240476,0.0017171934,0.0000025266625],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013611787,0.000109653214,0.0013586761,0.00067873666,0.000058015165,0.00046005385,0.000100907266,0.0000020962705,0.000007212379,0.00028638946,0.38492212,0.61188],"study_design_scores_gemma":[0.00095156505,0.000041709744,0.000108798966,0.0029216476,0.00028823756,0.000045144134,0.000112932474,0.017884778,0.000030077377,0.0023601567,0.9747498,0.0005051729],"about_ca_topic_score_codex":0.000026186855,"about_ca_topic_score_gemma":0.000009590293,"teacher_disagreement_score":0.61137486,"about_ca_system_score_codex":0.00009506158,"about_ca_system_score_gemma":0.0011429527,"threshold_uncertainty_score":0.9997314},"labels":[],"label_agreement":null},{"id":"W3161143900","doi":"10.1016/j.compmedimag.2021.101937","title":"Assessing the speed-accuracy trade-offs of popular convolutional neural networks for single-crop rib fracture classification","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Trauma Management and Diagnosis","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Research Foundation of Korea; Ministry of Science, ICT and Future Planning; University of Saskatchewan","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Deep learning; Receiver operating characteristic; Macro; Contextual image classification; Precision and recall; F1 score; Inference; Binary classification; Block (permutation group theory); Pattern recognition (psychology); Machine learning; Image (mathematics); Mathematics","score_opus":0.052316228791221546,"score_gpt":0.32942119166292183,"score_spread":0.2771049628717003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161143900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3199775,0.0070753763,0.54283446,0.12774478,0.0013550462,0.0006684324,0.00001174884,0.00015739359,0.00017527994],"genre_scores_gemma":[0.990129,0.00027309556,0.002371173,0.006455674,0.0004891655,0.000009479446,0.00024439773,0.000017747996,0.000010276512],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998588,0.000093195944,0.00037328288,0.00030007106,0.0004023277,0.00024308122],"domain_scores_gemma":[0.99874425,0.0005581326,0.00015355798,0.0002384636,0.00012892256,0.00017666662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038144222,0.00015728356,0.0003211342,0.000074001626,0.00019371288,0.00012530004,0.00012021616,0.00010722924,0.000020765361],"category_scores_gemma":[0.00048140058,0.00011554741,0.00016393942,0.0002783871,0.00036134906,0.00016329583,0.00006763427,0.00034142297,1.7297434e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043465913,0.0023899954,0.21848421,0.0016601015,0.0008482075,0.00052896247,0.00087818695,0.0003690017,0.011464706,0.028082259,0.044319957,0.6905398],"study_design_scores_gemma":[0.0029609322,0.000056433513,0.1909563,0.00035656814,0.00028894705,0.00018967869,0.0002359045,0.7840763,0.00012973139,0.00067109003,0.01990672,0.00017143093],"about_ca_topic_score_codex":0.000006492824,"about_ca_topic_score_gemma":0.0000011258076,"teacher_disagreement_score":0.78370726,"about_ca_system_score_codex":0.000013847247,"about_ca_system_score_gemma":0.000071347444,"threshold_uncertainty_score":0.47118866},"labels":[],"label_agreement":null},{"id":"W3183334770","doi":"10.1016/j.compmedimag.2022.102056","title":"Improved-Mask R-CNN: Towards an accurate generic MSK MRI instance segmentation platform (data from the Osteoarthritis Initiative)","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary; Alberta Bone and Joint Health Institute","funders":"Alberta Innovates","keywords":"Segmentation; Computer science; Osteoarthritis; Block (permutation group theory); Artificial intelligence; Magnetic resonance imaging; Header; Pattern recognition (psychology); Convolutional neural network; Cartilage; Computer vision; Medicine; Radiology; Anatomy; Pathology; Mathematics","score_opus":0.041461329686932356,"score_gpt":0.2969954400120702,"score_spread":0.25553411032513784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183334770","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93661946,0.0098913815,0.037585206,0.010858581,0.0022119153,0.0012575146,0.0009424328,0.00035829918,0.0002751826],"genre_scores_gemma":[0.9691245,0.0024426305,0.008104647,0.014454224,0.000719239,0.0001519341,0.004902116,0.0000575358,0.000043173426],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997771,0.00017251229,0.00038599398,0.0006115151,0.00070297095,0.00035598798],"domain_scores_gemma":[0.99860007,0.00016658203,0.00014654954,0.0006580577,0.00006811946,0.0003605959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005380546,0.00025990434,0.0003746863,0.00008908942,0.0006136599,0.00011484359,0.00043345522,0.00006798367,0.00021875834],"category_scores_gemma":[0.000067690366,0.0002031635,0.00007297149,0.00033401963,0.00025770653,0.00041742585,0.0006759464,0.00056261773,0.0000030562758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044446878,0.0003112993,0.0017217828,0.000034480374,0.000110528235,0.00060189475,0.0019453847,0.000001549975,0.0046493937,0.00052749243,0.0017660582,0.98788565],"study_design_scores_gemma":[0.112292305,0.012619064,0.015700264,0.001660663,0.0018316001,0.00353786,0.017120387,0.62607473,0.004945634,0.013619015,0.18737724,0.003221215],"about_ca_topic_score_codex":0.00010144682,"about_ca_topic_score_gemma":0.00006760249,"teacher_disagreement_score":0.98466444,"about_ca_system_score_codex":0.00004371697,"about_ca_system_score_gemma":0.00026240377,"threshold_uncertainty_score":0.82847667},"labels":[],"label_agreement":null},{"id":"W3186077304","doi":"10.1016/j.compmedimag.2021.101957","title":"MSDS-UNet: A multi-scale deeply supervised 3D U-Net for automatic segmentation of lung tumor in CT","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Beijing Science and Technology Planning Project; National University's Basic Research Foundation of China; National Natural Science Foundation of China","keywords":"Computer science; Scale (ratio); Artificial intelligence; Segmentation; Computer vision; Nuclear medicine; Pattern recognition (psychology); Medicine; Cartography; Geography","score_opus":0.011006501930095686,"score_gpt":0.3016983485890285,"score_spread":0.29069184665893283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186077304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6907326,0.0016303419,0.30095774,0.005687019,0.00040188732,0.0004448789,0.000008827002,0.00009068026,0.000045990728],"genre_scores_gemma":[0.65740466,0.0006282979,0.3331157,0.008151289,0.00024339817,0.00007226193,0.000246945,0.00006760266,0.0000698503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981353,0.00012604173,0.00058623415,0.00038328816,0.00043517697,0.00033395045],"domain_scores_gemma":[0.99880475,0.00038832723,0.0001157491,0.00021888889,0.00012554624,0.00034673852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077409873,0.00019018279,0.00058795454,0.00022131414,0.000076782264,0.000037847538,0.00011399179,0.000048981987,0.000043002223],"category_scores_gemma":[0.0007053333,0.00017255043,0.0001273669,0.00036516876,0.000278351,0.00007507542,0.00009151875,0.00043725714,5.5174456e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019196859,0.0013502286,0.29720622,0.0047979103,0.00026308128,0.0016809189,0.0025432466,0.000039010833,0.02619139,0.00037509328,0.0020734167,0.6632875],"study_design_scores_gemma":[0.008718239,0.00004948711,0.020330302,0.0010785809,0.00010512456,0.000515281,0.00014667588,0.9670242,0.00045907655,0.00014022128,0.0012684322,0.0001643774],"about_ca_topic_score_codex":0.00007276982,"about_ca_topic_score_gemma":0.00001156836,"teacher_disagreement_score":0.96698517,"about_ca_system_score_codex":0.00002745324,"about_ca_system_score_gemma":0.00023105714,"threshold_uncertainty_score":0.7036402},"labels":[],"label_agreement":null},{"id":"W3193532867","doi":"10.1016/j.compmedimag.2021.101974","title":"An unsupervised method for histological image segmentation based on tissue cluster level graph cut","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Cancer Institute; Fundamental Research Funds for the Central Universities; Natural Science Foundation of Shaanxi Province; National Natural Science Foundation of China; U.S. Department of Defense","keywords":"Jaccard index; Artificial intelligence; Computer science; Pattern recognition (psychology); Segmentation; Voronoi diagram; Cut; Cluster analysis; Image segmentation; Adjacency list; Graph partition; Graph; Computer vision; Mathematics","score_opus":0.03159187053559112,"score_gpt":0.33819063203238725,"score_spread":0.3065987614967961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193532867","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015850094,0.00016078143,0.9852048,0.01137837,0.001081964,0.0002579302,0.000011836133,0.0002720598,0.000047261863],"genre_scores_gemma":[0.042289555,0.00006687134,0.94212615,0.015097219,0.00023579119,0.00007766536,0.00006606937,0.00002376141,0.000016889433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974975,0.00043463966,0.0003431952,0.0008111197,0.00056534156,0.0003482041],"domain_scores_gemma":[0.99813205,0.0006532734,0.000097625336,0.0005346847,0.00022700614,0.00035537308],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089441915,0.00023303425,0.0003164871,0.00020558975,0.00028028197,0.00025499146,0.0004965821,0.00014241524,0.000020741683],"category_scores_gemma":[0.00016865216,0.00021480588,0.00010861377,0.000495353,0.00018569757,0.0003572134,0.00014374303,0.00031923642,0.0000019097852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013671095,0.0003979317,0.00021744832,0.00017742834,0.000041964766,0.00017992819,0.00043844152,0.00017042333,0.020357028,0.007278151,0.0041376203,0.9664669],"study_design_scores_gemma":[0.0025265093,0.00021018255,0.00060771214,0.00007408397,0.000023572296,0.00011626023,0.000019999728,0.978437,0.0068151946,0.006715902,0.0041776067,0.0002759714],"about_ca_topic_score_codex":0.000017925177,"about_ca_topic_score_gemma":0.000008758407,"teacher_disagreement_score":0.9782666,"about_ca_system_score_codex":0.000047540634,"about_ca_system_score_gemma":0.00018353066,"threshold_uncertainty_score":0.87595296},"labels":[],"label_agreement":null},{"id":"W3194481096","doi":"10.1016/j.compmedimag.2021.101971","title":"TSU-net: Two-stage multi-scale cascade and multi-field fusion U-net for right ventricular segmentation","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Phonocardiography and Auscultation Techniques","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Segmentation; Decoding methods; Computer science; Convolution (computer science); Algorithm; Artificial intelligence; Block (permutation group theory); Ventricle; Scale (ratio); Pattern recognition (psychology); Mathematics; Artificial neural network; Physics; Geometry; Medicine; Internal medicine","score_opus":0.015624133615633416,"score_gpt":0.3142769791922891,"score_spread":0.29865284557665567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194481096","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2107605,0.0034263092,0.7820783,0.0026919437,0.00032539852,0.00048190515,0.00002922097,0.00018550389,0.000020906078],"genre_scores_gemma":[0.54448694,0.008231308,0.43370295,0.011911701,0.00050115027,0.00016152383,0.00068791443,0.000064524196,0.00025201697],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986822,0.000083400984,0.00030212125,0.00039827242,0.0002942187,0.00023977792],"domain_scores_gemma":[0.9990809,0.00019877587,0.00008009371,0.00016651105,0.0001463328,0.00032738855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034767215,0.00018117121,0.0003466383,0.00017709182,0.0001979471,0.00005380657,0.000060399667,0.00012397044,0.000021075319],"category_scores_gemma":[0.00014212665,0.00015570312,0.00016129338,0.0002987357,0.00019123014,0.0000962802,0.000082686034,0.00027244535,4.6245827e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007478062,0.0024749713,0.08218856,0.0032480615,0.0010498383,0.0051612593,0.0038640983,0.000011385581,0.22894615,0.0015123201,0.012990531,0.657805],"study_design_scores_gemma":[0.041168373,0.00049110025,0.027049549,0.0021298514,0.0008245327,0.0022063497,0.0011042713,0.6315389,0.22364663,0.0011335899,0.067519315,0.0011875274],"about_ca_topic_score_codex":0.000027884695,"about_ca_topic_score_gemma":0.000008735536,"teacher_disagreement_score":0.65661746,"about_ca_system_score_codex":0.0000099535855,"about_ca_system_score_gemma":0.000055433953,"threshold_uncertainty_score":0.6349389},"labels":[],"label_agreement":null},{"id":"W3207698969","doi":"10.1016/j.compmedimag.2021.101988","title":"LF-UNet – A novel anatomical-aware dual-branch cascaded deep neural network for segmentation of retinal layers and fluid from optical coherence tomography images","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Optical coherence tomography; Computer science; Artificial intelligence; Convolutional neural network; Segmentation; Computer vision; Network architecture; Pattern recognition (psychology); Deep learning; Artificial neural network; Radiology; Medicine","score_opus":0.013114441275648864,"score_gpt":0.2806330781246108,"score_spread":0.26751863684896193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207698969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.685283,0.0038190857,0.30346742,0.006854308,0.00021238238,0.00021679008,0.000055319433,0.00007278656,0.000018919505],"genre_scores_gemma":[0.9271244,0.00054755225,0.069598444,0.0019884983,0.000334555,0.000018197952,0.0003515739,0.00002687813,0.000009899292],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979665,0.00009301632,0.0005145665,0.0005588342,0.00049670064,0.00037033262],"domain_scores_gemma":[0.99828655,0.00059451064,0.00013426559,0.00023088668,0.0002906525,0.000463169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039302977,0.000248297,0.00067573733,0.00014413492,0.00014266877,0.00008493842,0.0000912049,0.00011810885,0.000020655652],"category_scores_gemma":[0.00025345795,0.00021973909,0.00021570676,0.0005210364,0.0006666934,0.0000930859,0.000119472876,0.0003623642,2.2825155e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020334097,0.0012528694,0.45048055,0.002038545,0.0020491388,0.0015579975,0.001315634,0.00010303256,0.2540537,0.0015837756,0.007875966,0.27565536],"study_design_scores_gemma":[0.011549543,0.0002716994,0.06087068,0.0014478108,0.0014211715,0.0013771737,0.00053473166,0.9102804,0.008744848,0.0021729853,0.0006894579,0.0006394995],"about_ca_topic_score_codex":0.000076555734,"about_ca_topic_score_gemma":0.0000061606156,"teacher_disagreement_score":0.91017735,"about_ca_system_score_codex":0.000009654501,"about_ca_system_score_gemma":0.00008139338,"threshold_uncertainty_score":0.89607},"labels":[],"label_agreement":null},{"id":"W3209439384","doi":"10.1016/j.compmedimag.2021.102000","title":"3D hemisphere-based convolutional neural network for whole-brain MRI segmentation","year":2021,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"National Institute of Mental Health; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; McDonnell Center for Systems Neuroscience; Genentech; National Institutes of Health; National Institute of Neurological Disorders and Stroke; IXICO; H. Lundbeck A/S; Servier; Eisai; National Institute on Aging; Alzheimer Society Research Program; Commonwealth Scientific and Industrial Research Organisation; Fondation pour la Recherche sur Alzheimer; Alzheimer Society; Alzheimer's Society; Michael Smith Health Research BC; U.S. Department of Defense; Eli Lilly and Company; Compute Canada; Northern California Institute for Research and Education; University of Southern California; Natural Sciences and Engineering Research Council of Canada; Pfizer; BioClinica; Biogen; GlaxoSmithKline; Bristol-Myers Squibb; Fondation Brain Canada; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Alzheimer's Association","keywords":"Segmentation; Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology); Hausdorff distance; Minimum bounding box; Computer vision","score_opus":0.013862995202094126,"score_gpt":0.2867066519836771,"score_spread":0.272843656781583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209439384","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000536467,0.0009204344,0.9524482,0.044723812,0.00071637885,0.0002402338,0.000010441205,0.0003806718,0.00002338608],"genre_scores_gemma":[0.005193375,0.00007033116,0.95311433,0.04073824,0.00043613004,0.00009337794,0.0002372807,0.000020600404,0.00009630393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99765694,0.00021479337,0.00043104796,0.0005810353,0.00069476705,0.00042143543],"domain_scores_gemma":[0.99799675,0.00089550944,0.00012688889,0.00033036852,0.00021482828,0.0004356869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007900707,0.00020652098,0.00027867567,0.00007175954,0.0002654235,0.0002619493,0.0004410961,0.00010341657,0.000051336654],"category_scores_gemma":[0.0003069564,0.00020383901,0.00011263889,0.00046296464,0.00032554087,0.00030361518,0.0002363646,0.00028717943,0.0000022576282],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047267942,0.00026608745,0.001523889,0.00027649992,0.000078580284,0.00025821588,0.00022556355,0.00022956649,0.006627873,0.013383292,0.18501458,0.7920686],"study_design_scores_gemma":[0.0023799024,0.000046896937,0.00041283347,0.00017397528,0.000015369635,0.000089089626,0.000012673559,0.9758996,0.0024600045,0.0055188867,0.012728126,0.00026266853],"about_ca_topic_score_codex":0.000007367073,"about_ca_topic_score_gemma":0.000002785309,"teacher_disagreement_score":0.97567,"about_ca_system_score_codex":0.000027474693,"about_ca_system_score_gemma":0.0003188334,"threshold_uncertainty_score":0.83123136},"labels":[],"label_agreement":null},{"id":"W4210993709","doi":"10.1016/j.compmedimag.2022.102038","title":"Weak lesion feature extraction by dual-branch separation and enhancement network for safe hemorrhagic transformation prediction","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Transformation (genetics); Dual (grammatical number); Pattern recognition (psychology); Contrast (vision); Residual; Algorithm","score_opus":0.010320517315325534,"score_gpt":0.28257947461269356,"score_spread":0.27225895729736804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210993709","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12800094,0.0030490907,0.84469503,0.021475663,0.001019604,0.0011420179,0.000044824857,0.00013759134,0.00043521362],"genre_scores_gemma":[0.9730371,0.0026737137,0.012865931,0.006171254,0.00095032965,0.00043348307,0.0028202333,0.000046911726,0.0010010104],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998522,0.00006383079,0.00031094174,0.0003285441,0.0005337267,0.00024095071],"domain_scores_gemma":[0.9994432,0.000089098365,0.00011112383,0.00012882118,0.00005219096,0.00017559715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063817296,0.0001661458,0.00025052996,0.000102857404,0.00041968358,0.00003831699,0.00004700767,0.0000756372,0.000038770235],"category_scores_gemma":[0.000027182401,0.00015987728,0.000060977007,0.00019872132,0.00008115423,0.00014827958,0.000071611365,0.0003727333,4.2244923e-7],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010029055,0.00030455194,0.0017360685,0.00072237436,0.00016970666,0.00001862928,0.00069810275,0.000052251846,0.02589125,0.0007719312,0.6294037,0.33922854],"study_design_scores_gemma":[0.0061820406,0.00042813795,0.002493289,0.00017129107,0.00027360843,0.0004440467,0.00023293178,0.44192436,0.0007107481,0.00031375737,0.5465939,0.00023189564],"about_ca_topic_score_codex":0.000006329629,"about_ca_topic_score_gemma":5.4814467e-7,"teacher_disagreement_score":0.8450362,"about_ca_system_score_codex":0.000058948135,"about_ca_system_score_gemma":0.000037832833,"threshold_uncertainty_score":0.6519606},"labels":[],"label_agreement":null},{"id":"W4221039672","doi":"10.1016/j.compmedimag.2022.102054","title":"Two-stage segmentation network with feature aggregation and multi-level attention mechanism for multi-modality heart images","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Anhui Province","keywords":"Segmentation; Computer science; Feature (linguistics); Artificial intelligence; Encoder; Modality (human–computer interaction); Pattern recognition (psychology); Image segmentation; Decoding methods; Fuse (electrical); Computer vision; Representation (politics); Algorithm","score_opus":0.03477640809921554,"score_gpt":0.31463725622931193,"score_spread":0.2798608481300964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221039672","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008323071,0.0003197819,0.97924054,0.010987682,0.0002675917,0.0006298515,0.00002950188,0.00020053286,0.0000014609892],"genre_scores_gemma":[0.12746222,0.00012910551,0.8687532,0.0030505825,0.0001222015,0.00029513365,0.000100633646,0.000021094862,0.000065835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832225,0.00015458668,0.00022243074,0.00059280585,0.0003953382,0.0003125772],"domain_scores_gemma":[0.99905735,0.00018752246,0.00015648823,0.00028197453,0.000114507624,0.00020214333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005072124,0.00019095637,0.00021590738,0.00008442321,0.0008781422,0.00014204583,0.000284737,0.0000402243,0.0000016707775],"category_scores_gemma":[0.000029017967,0.0001772098,0.000049863836,0.0004337573,0.00015642829,0.00034167102,0.00039894573,0.00033864137,2.2343038e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028739497,0.0008462361,0.011455011,0.0003874129,0.0001965467,0.00009122307,0.0011119269,0.0045829844,0.014607359,0.37774205,0.005224664,0.5834672],"study_design_scores_gemma":[0.0030373384,0.000066406596,0.0046754335,0.000045609468,0.00001878983,0.0001139701,0.000044621906,0.9847408,0.00015293901,0.0061587403,0.0007137545,0.00023160745],"about_ca_topic_score_codex":0.000014019402,"about_ca_topic_score_gemma":0.00001103746,"teacher_disagreement_score":0.9801578,"about_ca_system_score_codex":0.000027513846,"about_ca_system_score_gemma":0.00004403271,"threshold_uncertainty_score":0.72264063},"labels":[],"label_agreement":null},{"id":"W4240987819","doi":"10.1016/j.compmedimag.2016.12.001","title":"Preface","year":2017,"lang":"en","type":"editorial","venue":"Computerized Medical Imaging and Graphics","topic":"Glaucoma and retinal disorders","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Optical coherence tomography; Segmentation; Computer science; Artificial intelligence; Glaucoma; Optic disk; Computer vision; Vector flow; Bruch's membrane; Optic nerve; Optic cup (embryology); Image segmentation; Optics; Retina; Physics; Ophthalmology; Medicine","score_opus":0.008064923020170105,"score_gpt":0.29179190175570713,"score_spread":0.28372697873553704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240987819","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001092883,0.010919753,0.0023818132,0.0079598455,0.9745226,0.00038972197,0.00003432213,0.0002613036,0.002437784],"genre_scores_gemma":[0.0018734519,0.01789648,0.0012963818,0.0016349975,0.9738465,0.00002586536,0.000789963,0.00013180735,0.0025045522],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971954,0.00006738085,0.00035663653,0.00060095947,0.0013546811,0.00042493286],"domain_scores_gemma":[0.9978408,0.0003990921,0.00020036015,0.00062925415,0.00022842345,0.00070207485],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004765899,0.00039084922,0.00084781373,0.00018264432,0.0002856996,0.00014344716,0.0003804565,0.0008222822,0.00004027702],"category_scores_gemma":[0.0017232422,0.00030617055,0.00023311579,0.00007698645,0.00090192736,0.00005660446,0.00030939418,0.0019452473,0.0000135855735],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009697579,0.00007974113,0.0008539893,0.0006572703,0.000099567435,0.0005758553,0.000044144723,3.1614587e-9,0.000007926117,0.00008827509,0.96920025,0.028295983],"study_design_scores_gemma":[0.0027698718,0.00009398434,0.0017778768,0.0020457322,0.0002575289,0.0001471281,0.00000961551,0.0019471305,0.0000021191925,0.0003597931,0.9902754,0.00031381458],"about_ca_topic_score_codex":0.00006685622,"about_ca_topic_score_gemma":0.000004851487,"teacher_disagreement_score":0.027982168,"about_ca_system_score_codex":0.000015783926,"about_ca_system_score_gemma":0.0006423557,"threshold_uncertainty_score":0.999939},"labels":[],"label_agreement":null},{"id":"W4281650581","doi":"10.1016/j.compmedimag.2022.102086","title":"Volumetric quantification of choroid and Haller's sublayer using OCT scans: An accurate and unified approach based on stratified smoothing","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Eye Institute; National Institutes of Health; Research to Prevent Blindness; Eye and Ear Foundation of Pittsburgh","keywords":"Choroid; Smoothing; Artificial intelligence; Computer science; Optical coherence tomography; Segmentation; Smoothing spline; Computer vision; Macular degeneration; Mathematics; Medicine; Retina; Radiology; Ophthalmology; Spline interpolation","score_opus":0.04004730291114486,"score_gpt":0.31028422902186026,"score_spread":0.27023692611071537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281650581","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86304677,0.0010729886,0.13337547,0.0020631447,0.00009533607,0.00019605344,0.000009257256,0.00006808851,0.0000728784],"genre_scores_gemma":[0.9895194,0.00020852123,0.009018309,0.0010707569,0.000057564997,0.000007447413,0.00008537898,0.000022319618,0.000010293513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997931,0.0002650029,0.0004173266,0.0005135485,0.0006437349,0.00022941083],"domain_scores_gemma":[0.9988631,0.00018518188,0.00018212857,0.00029946037,0.00013172456,0.0003384238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012750967,0.00019857446,0.00046738746,0.0006198165,0.0003503392,0.00009662522,0.00011940153,0.000058533442,0.000011841135],"category_scores_gemma":[0.00021080773,0.00017910697,0.000070034075,0.000804021,0.00037383536,0.00011816031,0.00009456372,0.00051017245,6.365099e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033040256,0.0052706064,0.26275477,0.0044570058,0.0012404764,0.00081855775,0.0047740797,0.007389786,0.09410197,0.0069890153,0.000996311,0.60790336],"study_design_scores_gemma":[0.0018675859,0.00015959458,0.015198929,0.00014849892,0.00018048538,0.0001474285,0.0004424847,0.9813301,0.00009351466,0.00010690143,0.00014864924,0.0001758136],"about_ca_topic_score_codex":0.00024093722,"about_ca_topic_score_gemma":0.0000012985478,"teacher_disagreement_score":0.9739403,"about_ca_system_score_codex":0.000018717987,"about_ca_system_score_gemma":0.00012404333,"threshold_uncertainty_score":0.73037696},"labels":[],"label_agreement":null},{"id":"W4283020131","doi":"10.1016/j.compmedimag.2022.102092","title":"A contrastive consistency semi-supervised left atrium segmentation model","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Atrial Fibrillation Management and Outcomes","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Science, Technology and Innovation Commission of Shenzhen Municipality; National Natural Science Foundation of China","keywords":"Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Hausdorff distance; Jaccard index; Leverage (statistics); Semi-supervised learning","score_opus":0.03366524962674061,"score_gpt":0.30827967132246137,"score_spread":0.27461442169572076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283020131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4762643,0.0024694204,0.4573299,0.058970705,0.0015246504,0.0013850974,0.00004410367,0.0005435652,0.0014682683],"genre_scores_gemma":[0.98794997,0.0002775944,0.0040584793,0.00694288,0.00028277902,0.000006976586,0.00013967362,0.000019688403,0.00032198784],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848884,0.00009438343,0.0003145702,0.00028146608,0.0006089631,0.00021178619],"domain_scores_gemma":[0.999297,0.00017175876,0.000077693054,0.0001386537,0.000069913855,0.0002449699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042586878,0.00014543103,0.0003234644,0.00017655216,0.00032355697,0.00003363841,0.00007993418,0.000036907524,0.00018585137],"category_scores_gemma":[0.00010749494,0.00013475925,0.00012896219,0.00019873485,0.00017127016,0.00007726651,0.00020819818,0.00027740162,0.0000019068902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029781875,0.00035423238,0.63673985,0.0010838207,0.0014052045,0.0011770444,0.0069446433,0.0015029382,0.019139247,0.03734415,0.034140587,0.2571901],"study_design_scores_gemma":[0.006141239,0.00008580169,0.009783413,0.000049066537,0.00019056929,0.00015861634,0.00043092118,0.9751323,0.00003207985,0.0013068101,0.006492666,0.00019651823],"about_ca_topic_score_codex":0.000009890812,"about_ca_topic_score_gemma":6.4020765e-7,"teacher_disagreement_score":0.97362936,"about_ca_system_score_codex":0.000030132556,"about_ca_system_score_gemma":0.00012636467,"threshold_uncertainty_score":0.54953223},"labels":[],"label_agreement":null},{"id":"W4303437883","doi":"10.1016/j.compmedimag.2022.102127","title":"Active deep learning from a noisy teacher for semi-supervised 3D image segmentation: Application to COVID-19 pneumonia infection in CT","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Simon Fraser University","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Annotation; Machine learning; Deep learning; Stochastic gradient descent; Weighting; Segmentation; Supervised learning; Benchmark (surveying); Semi-supervised learning; Pattern recognition (psychology); Artificial neural network","score_opus":0.018825997847899303,"score_gpt":0.3276309247283866,"score_spread":0.30880492688048733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303437883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45495558,0.00015015401,0.49811012,0.045279205,0.00022867927,0.0010384622,0.000015193282,0.00021400681,0.000008628522],"genre_scores_gemma":[0.91336405,0.0002386932,0.012586625,0.07118183,0.00039431726,0.0014450144,0.0006984636,0.00006887579,0.00002213446],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979729,0.0002519886,0.00036036258,0.0006081456,0.00051574555,0.0002908387],"domain_scores_gemma":[0.99828255,0.0008061398,0.0001092816,0.00022124339,0.00007467517,0.00050609093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007349619,0.00020321316,0.00036993768,0.00039762742,0.0003832605,0.000056714598,0.00012123538,0.000051771327,0.00009094281],"category_scores_gemma":[0.0008600377,0.00022107793,0.00009238459,0.00065061724,0.00011515592,0.00010732313,0.00022574267,0.0006690435,0.0000026678633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016683365,0.0016692786,0.24435258,0.0008280106,0.00025790153,0.00039516462,0.013795183,0.0027796284,0.05327528,0.00012388839,0.0057212655,0.67513347],"study_design_scores_gemma":[0.008716177,0.00026068752,0.048821803,0.00016624876,0.00015058582,0.00011669955,0.00051724364,0.8448184,0.0002506306,0.0004951565,0.095300995,0.0003853485],"about_ca_topic_score_codex":0.0015305488,"about_ca_topic_score_gemma":0.000081031714,"teacher_disagreement_score":0.8420388,"about_ca_system_score_codex":0.00036971256,"about_ca_system_score_gemma":0.00025995355,"threshold_uncertainty_score":0.90152967},"labels":[],"label_agreement":null},{"id":"W4308102317","doi":"10.1016/j.compmedimag.2022.102139","title":"Blockchain and homomorphic encryption based privacy-preserving model aggregation for medical images","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Homomorphic encryption; Encryption; Blockchain; Scheme (mathematics); Data sharing; Raw data; Data mining; Computer security; Artificial intelligence","score_opus":0.01992482034253225,"score_gpt":0.27255622895035464,"score_spread":0.2526314086078224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308102317","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024471203,0.0009543493,0.8564071,0.11650673,0.0003651304,0.00031322287,0.00002868899,0.00094359665,0.000009981369],"genre_scores_gemma":[0.49405187,0.0004321654,0.5003615,0.0047111767,0.00011208298,0.00022425018,0.000055570712,0.000043279088,0.000008078038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965662,0.00024066062,0.000466702,0.00088190776,0.0013339403,0.0005105863],"domain_scores_gemma":[0.9958178,0.0009087409,0.00017953843,0.0025913585,0.000111561,0.00039104454],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002629927,0.00026602694,0.0003514196,0.00040133257,0.00076010934,0.0002444385,0.0099802315,0.00015210427,0.00002021596],"category_scores_gemma":[0.01360326,0.00026880618,0.00008280975,0.00059022283,0.0004991919,0.00030786684,0.048220612,0.00079212256,4.7242497e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015913774,0.0006616315,0.0043539647,0.0008144272,0.00014312916,0.00044050117,0.00068837084,0.00069779163,0.0021965716,0.03538969,0.21235356,0.74210125],"study_design_scores_gemma":[0.0014850236,0.000054696087,0.00016475483,0.00011409718,0.000012351755,0.00013440952,0.000015786565,0.84000635,0.000114014794,0.15656814,0.0010802587,0.00025010057],"about_ca_topic_score_codex":0.000025930956,"about_ca_topic_score_gemma":0.0000013983806,"teacher_disagreement_score":0.83930856,"about_ca_system_score_codex":0.000043977532,"about_ca_system_score_gemma":0.00029361708,"threshold_uncertainty_score":0.9999764},"labels":[],"label_agreement":null},{"id":"W4313254423","doi":"10.1016/j.compmedimag.2022.102165","title":"Real-time simulation of viscoelastic tissue behavior with physics-guided deep learning","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Elasticity and Material Modeling","field":"Engineering","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; National Research Council Canada","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Council Canada; Compute Canada","keywords":"Hyperelastic material; Viscoelasticity; Finite element method; Deep learning; Computer science; Artificial intelligence; Function (biology); Simulation; Physics","score_opus":0.008998307910624528,"score_gpt":0.24352556551425605,"score_spread":0.23452725760363152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313254423","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51241624,0.000058113223,0.48701534,0.000021715608,0.00017657317,0.000079058176,0.000002721798,0.000187192,0.000043028183],"genre_scores_gemma":[0.99677736,0.00006303436,0.0029613173,0.000027194503,0.0000905141,0.000017029863,0.000028525095,0.000028962348,0.0000060957545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990698,0.000059600083,0.00022385153,0.00015399996,0.00031535508,0.00017737423],"domain_scores_gemma":[0.99955887,0.00015750842,0.000046664467,0.00008947087,0.00003870749,0.000108776425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017578283,0.00012573082,0.00022917752,0.00007508784,0.0001579249,0.00002515235,0.0000976492,0.000031547497,0.000050317263],"category_scores_gemma":[0.000025504416,0.00012385285,0.000025313508,0.0001699874,0.000095291274,0.00007207265,0.00010085781,0.00027171738,0.0000010191363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002988679,0.000052246134,0.00034864858,0.00014847405,0.00002997668,0.00004524159,0.00047338777,0.94433606,0.030207288,0.0003102772,0.000017188468,0.024001326],"study_design_scores_gemma":[0.0006240897,0.000069428774,0.00027703246,0.00007212492,0.000049745453,0.000031526666,0.000024099914,0.99798167,0.00035576356,0.00014952518,0.00022194357,0.0001430465],"about_ca_topic_score_codex":0.000020371506,"about_ca_topic_score_gemma":4.990404e-7,"teacher_disagreement_score":0.48436105,"about_ca_system_score_codex":0.000013640142,"about_ca_system_score_gemma":0.000017150025,"threshold_uncertainty_score":0.5050573},"labels":[],"label_agreement":null},{"id":"W4313530895","doi":"10.1016/j.compmedimag.2022.102161","title":"Synchronous Medical Image Augmentation framework for deep learning-based image segmentation","year":2022,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Focus (optics); Image (mathematics); Image segmentation; Sample (material); Transformation (genetics); Deep learning; Medical imaging; Pattern recognition (psychology); Computer vision","score_opus":0.008452284627012663,"score_gpt":0.28564876436989484,"score_spread":0.2771964797428822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313530895","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037971379,0.00039572062,0.9831642,0.01016897,0.0016355414,0.00037025285,0.0000048675556,0.00044538316,0.000017907128],"genre_scores_gemma":[0.28497103,0.00024003412,0.7040425,0.00942856,0.0005484658,0.00056737685,0.00013011975,0.00005960197,0.000012336161],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967778,0.000360588,0.0004227358,0.0006487841,0.0013813452,0.0004087706],"domain_scores_gemma":[0.998123,0.0008583075,0.00020956254,0.00031163034,0.00011971984,0.00037780518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014246193,0.00022018499,0.00026480982,0.0002510765,0.00088749087,0.00025303956,0.00072350714,0.000103154365,0.000147933],"category_scores_gemma":[0.00044305026,0.0002363714,0.00012025351,0.00058009726,0.00029872876,0.0003738104,0.0004712354,0.0008646993,0.0000031897323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017505656,0.00035420613,0.000781743,0.00030074953,0.00008912742,0.00021119871,0.0016601275,0.000506319,0.0015605476,0.014361526,0.0020019913,0.9779974],"study_design_scores_gemma":[0.0021834136,0.00023241906,0.00032605807,0.00006754388,0.000021722657,0.0001202527,0.00012157363,0.9814962,0.00044893057,0.010965739,0.003740606,0.00027550609],"about_ca_topic_score_codex":0.000026010277,"about_ca_topic_score_gemma":0.0000030662616,"teacher_disagreement_score":0.98098993,"about_ca_system_score_codex":0.00014294997,"about_ca_system_score_gemma":0.00028057184,"threshold_uncertainty_score":0.9638946},"labels":[],"label_agreement":null},{"id":"W4313591971","doi":"10.1016/j.compmedimag.2022.102171","title":"Towards better interpretable and generalizable AD detection using collective artificial intelligence","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Centre National de la Recherche Scientifique; Eisai; Agence Nationale de la Recherche; Pfizer; Novartis Pharmaceuticals Corporation; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Interpretability; Artificial intelligence; Computer science; Machine learning; Deep learning; Generalizability theory; Neuroimaging; Convolutional neural network; Classifier (UML); Ensemble learning; Dementia; Graph; Disease; Medicine; Psychology","score_opus":0.03706426654043213,"score_gpt":0.3408039305231152,"score_spread":0.30373966398268304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313591971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69638896,0.00028588335,0.30031544,0.0023229292,0.0002401041,0.0002095004,0.0000026449275,0.00010760725,0.00012692304],"genre_scores_gemma":[0.99487936,0.0006616972,0.002528933,0.0016148526,0.00016895426,0.00001893466,0.000014419367,0.000018808885,0.00009405149],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998541,0.0000907112,0.00023059767,0.00033798648,0.0004475883,0.00035214785],"domain_scores_gemma":[0.9993307,0.00008986457,0.00003436609,0.00010447805,0.00013243721,0.0003081712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058502983,0.00014015971,0.00024733008,0.0003401187,0.00022051191,0.00010400546,0.00006199316,0.00007245667,0.000053150707],"category_scores_gemma":[0.00016818098,0.00012183029,0.000054143537,0.0006878399,0.00034750634,0.00009832861,0.000207511,0.00030298377,0.000005273542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031607228,0.00014223684,0.016140163,0.00024919395,0.00016704938,0.00041187982,0.00071718905,0.000002889081,0.018862104,0.000218788,0.0003810439,0.9623914],"study_design_scores_gemma":[0.0007161243,0.00020157266,0.020099279,0.00033281563,0.000094957526,0.00031591408,0.00022872211,0.9634523,0.0053182156,0.007850541,0.0011988967,0.00019069586],"about_ca_topic_score_codex":0.000059515478,"about_ca_topic_score_gemma":0.000005146922,"teacher_disagreement_score":0.96344936,"about_ca_system_score_codex":0.000029126764,"about_ca_system_score_gemma":0.00014255823,"threshold_uncertainty_score":0.4968095},"labels":[],"label_agreement":null},{"id":"W4321487431","doi":"10.1016/j.compmedimag.2023.102206","title":"Dual-domain accelerated MRI reconstruction using transformers with learning-based undersampling","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ted Rogers Centre for Heart Research; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canada Foundation for Innovation","keywords":"Undersampling; Computer science; Artificial intelligence; Biomedical engineering; Medicine","score_opus":0.03325050218821922,"score_gpt":0.3249790250672212,"score_spread":0.291728522879002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321487431","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15856962,0.000052208496,0.83543485,0.0050138733,0.00007025176,0.00023048633,0.0000020881064,0.000574118,0.00005248341],"genre_scores_gemma":[0.7977336,0.0008343438,0.19911367,0.0017747162,0.00023389694,0.000042965985,0.00017222152,0.0000676379,0.000026917554],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989002,0.000031282623,0.00022144946,0.0003012059,0.00027491845,0.00027098774],"domain_scores_gemma":[0.9993766,0.000100840385,0.000063599284,0.0001128337,0.00008384923,0.00026229036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026229903,0.00015267398,0.00024734053,0.00022853093,0.00027346957,0.000033583437,0.000043162254,0.00008633971,0.000013460748],"category_scores_gemma":[0.000026889742,0.00012581208,0.00005426824,0.00078632566,0.00035241587,0.00007292041,0.00002049358,0.00043432225,0.000001280086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015529253,0.00061292044,0.039777756,0.0012522915,0.00035702126,0.001304601,0.0015264853,0.012656073,0.046421934,0.006757871,0.0018394691,0.8859407],"study_design_scores_gemma":[0.003007573,0.000116738374,0.0009673717,0.00066924683,0.00007256599,0.0006848278,0.0003934201,0.98584354,0.00048386838,0.0014824778,0.0060370453,0.00024132557],"about_ca_topic_score_codex":0.00001581016,"about_ca_topic_score_gemma":0.0000020658924,"teacher_disagreement_score":0.97318745,"about_ca_system_score_codex":0.000024240015,"about_ca_system_score_gemma":0.00013711638,"threshold_uncertainty_score":0.5130468},"labels":[],"label_agreement":null},{"id":"W4364356397","doi":"10.1016/j.compmedimag.2023.102232","title":"Semantically preserving adversarial unsupervised domain adaptation network for improving disease recognition from chest x-rays","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council; National Science Foundation; U.S. Department of Transportation; Amazon Web Services; Toyota USA; National Sleep Foundation","keywords":"Computer science; Artificial intelligence; Domain (mathematical analysis); Deep learning; Labeled data; Domain adaptation; Adaptation (eye); ENCODE; Pattern recognition (psychology); Adversarial system; Machine learning","score_opus":0.0339811903640427,"score_gpt":0.29224186617885284,"score_spread":0.25826067581481016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364356397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38824472,0.00058746827,0.52553004,0.08170351,0.0017405364,0.0011847985,0.00010521516,0.0008946724,0.000009013751],"genre_scores_gemma":[0.8040774,0.0011309119,0.13182262,0.050498456,0.007378772,0.00036825705,0.0044885133,0.00020524816,0.000029844483],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977452,0.00012851537,0.00044081593,0.000608285,0.00058428675,0.00049286406],"domain_scores_gemma":[0.99694985,0.0017425293,0.000103261824,0.00030902264,0.00018066479,0.00071464817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009493328,0.00023816283,0.00041137572,0.00019946705,0.00029153298,0.000113703005,0.00015942547,0.0001364649,0.000024830117],"category_scores_gemma":[0.0017692252,0.0002323262,0.00016685427,0.00052857754,0.00020640991,0.00015481454,0.00020605834,0.00032707394,0.0000072057446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0061360504,0.0011750484,0.055403564,0.0061716726,0.0007711857,0.0018811176,0.004353516,0.0006480308,0.0074028084,0.0013227422,0.05382713,0.86090714],"study_design_scores_gemma":[0.006714697,0.00007967479,0.05233569,0.0013937592,0.00034497643,0.000007579338,0.000100245634,0.91775566,0.000016332247,0.011999066,0.008955743,0.00029658334],"about_ca_topic_score_codex":0.00018488504,"about_ca_topic_score_gemma":0.000017620927,"teacher_disagreement_score":0.91710764,"about_ca_system_score_codex":0.00003731448,"about_ca_system_score_gemma":0.00031653504,"threshold_uncertainty_score":0.9473988},"labels":[],"label_agreement":null},{"id":"W4379202866","doi":"10.1016/j.compmedimag.2023.102249","title":"DC-cycleGAN: Bidirectional CT-to-MR synthesis from unpaired data","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Windsor","funders":"","keywords":"Computer science; Image synthesis; Artificial intelligence; Similarity (geometry); Image (mathematics); Source code; Contrast (vision); Modality (human–computer interaction); Computer vision; Pattern recognition (psychology)","score_opus":0.03202701701348586,"score_gpt":0.27327719362327857,"score_spread":0.2412501766097927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379202866","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015135967,0.00039335262,0.9561632,0.025445094,0.0018266137,0.00014154075,0.00007378172,0.00072353706,0.000096860604],"genre_scores_gemma":[0.828833,0.0012911778,0.15864444,0.008706159,0.002014142,0.000049451744,0.00026247906,0.000060222985,0.00013891628],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973318,0.00020325171,0.00033934347,0.00096964516,0.00069449685,0.0004614933],"domain_scores_gemma":[0.997261,0.0010327145,0.00007105332,0.00099686,0.000078565805,0.0005597987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009290948,0.00024697525,0.00036529396,0.0002932227,0.00035221368,0.00036917103,0.0016758011,0.000055938268,0.00003840926],"category_scores_gemma":[0.00048284722,0.00022250744,0.0000793619,0.0012678794,0.00020448322,0.0004974014,0.0019716744,0.00026122452,0.00006328862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022292483,0.000109573266,0.0022260786,0.000024202194,0.00019109754,0.00051648787,0.00031366,0.00013615296,0.0013568824,0.003013296,0.1230749,0.8690154],"study_design_scores_gemma":[0.00036820793,0.000010815392,0.0063795946,0.00012674397,0.000022508275,0.000033117452,0.000018999228,0.92638975,0.0003938479,0.0016313201,0.064328335,0.00029675325],"about_ca_topic_score_codex":0.0002662694,"about_ca_topic_score_gemma":0.000020808324,"teacher_disagreement_score":0.9262536,"about_ca_system_score_codex":0.000012751497,"about_ca_system_score_gemma":0.00012083145,"threshold_uncertainty_score":0.907359},"labels":[],"label_agreement":null},{"id":"W4385376394","doi":"10.1016/j.compmedimag.2023.102279","title":"SF2Former: Amyotrophic lateral sclerosis identification from multi-center MRI data using spatial and frequency fusion transformer","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Amyotrophic Lateral Sclerosis Research","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; Health Sciences Centre; Sunnybrook Health Science Centre; University of Toronto; Montreal Neurological Institute and Hospital; University of Alberta; Université Laval; University of British Columbia; McGill University; University of Calgary","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Neuroimaging; Discriminative model; Deep learning; Pattern recognition (psychology); Machine learning; Amyotrophic lateral sclerosis; Medicine; Neuroscience; Psychology; Pathology","score_opus":0.08610590573759444,"score_gpt":0.33907987055024763,"score_spread":0.2529739648126532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385376394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9397103,0.0004747974,0.051763956,0.006845012,0.00046083168,0.00039133284,0.00014320521,0.00020466148,0.0000059084614],"genre_scores_gemma":[0.98584306,0.0066521894,0.004947445,0.0008730143,0.0003950821,0.000011510482,0.0012118283,0.00004768811,0.000018178402],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970554,0.00013429784,0.00056315836,0.00081109116,0.0008910807,0.00054497685],"domain_scores_gemma":[0.99846405,0.00011286807,0.000091400536,0.0006074906,0.000115511866,0.0006086666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006690067,0.00027295554,0.0004528344,0.00031688393,0.00031515278,0.00017119967,0.00034238686,0.00018920921,0.000077850826],"category_scores_gemma":[0.00012243252,0.00022226767,0.000077818004,0.00048779265,0.000561231,0.0003912716,0.00041341246,0.000584523,0.000016748661],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046841847,0.0007226038,0.29368275,0.00052656897,0.0003826914,0.00046783072,0.0013467123,0.0000022316965,0.38709807,0.000087262124,0.001539451,0.3136754],"study_design_scores_gemma":[0.0054791146,0.00003970204,0.43677554,0.00068653614,0.00008996582,0.00007427381,0.000021619375,0.5558945,0.00011057031,0.00022711587,0.00037374563,0.00022731107],"about_ca_topic_score_codex":0.0014884481,"about_ca_topic_score_gemma":0.00004900251,"teacher_disagreement_score":0.5558923,"about_ca_system_score_codex":0.000034155797,"about_ca_system_score_gemma":0.000106602216,"threshold_uncertainty_score":0.90638125},"labels":[],"label_agreement":null},{"id":"W4385431541","doi":"10.1016/j.compmedimag.2023.102276","title":"Invasion depth estimation of carcinoma cells using adaptive stain normalization to improve epidermis segmentation accuracy","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"AI in cancer detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Normalization (sociology); Epidermis (zoology); Stain; Segmentation; Artificial intelligence; Computer science; Pattern recognition (psychology); Pathology; Computer vision; Biology; Anatomy; Medicine; Staining","score_opus":0.02803492667397791,"score_gpt":0.3012182966454943,"score_spread":0.27318336997151643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385431541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25360528,0.000041803956,0.7447636,0.0005863728,0.0006088678,0.00023402418,0.0000026088878,0.00015153136,0.0000059136787],"genre_scores_gemma":[0.9099604,0.00008091152,0.0893191,0.0005190938,0.000075265234,0.000014908682,0.000014139161,0.000013416239,0.0000027881729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820745,0.00015378984,0.00039933817,0.0004123019,0.0005745484,0.00025256968],"domain_scores_gemma":[0.9988118,0.0003262364,0.00020733163,0.00028012277,0.00016237669,0.00021214782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007280762,0.00015323126,0.00021696054,0.00042112416,0.00016804949,0.000092629045,0.00030003715,0.000072014336,0.0000014907553],"category_scores_gemma":[0.00020785652,0.00015489511,0.00004862254,0.0012672124,0.00009259358,0.00061226956,0.00035294527,0.0001488226,0.0000029348234],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048649123,0.000106909545,0.0011916093,0.0002211359,0.000027739256,0.000038365117,0.0025723302,0.006750562,0.03504993,0.002347808,0.0005064839,0.9511385],"study_design_scores_gemma":[0.0010560147,0.00007555385,0.00213173,0.00012972238,0.000012476286,0.000016859049,0.0000739346,0.97135615,0.023136698,0.0018221429,0.00003756377,0.0001511248],"about_ca_topic_score_codex":0.00016743176,"about_ca_topic_score_gemma":0.0000073172805,"teacher_disagreement_score":0.9646056,"about_ca_system_score_codex":0.000065270266,"about_ca_system_score_gemma":0.00014874696,"threshold_uncertainty_score":0.63164395},"labels":[],"label_agreement":null},{"id":"W4386485397","doi":"10.1016/j.compmedimag.2023.102294","title":"End to end vision transformer architecture for brain stroke assessment based on multi-slice classification and localization using computed tomography","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Stroke (engine); Convolutional neural network; Artificial intelligence; Computer science; Infarction; Medicine; Myocardial infarction; Cardiology","score_opus":0.02621081124519379,"score_gpt":0.3371987411944149,"score_spread":0.3109879299492211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386485397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.068197966,0.000051784293,0.91426355,0.016000744,0.00022411607,0.00095857226,0.000038924165,0.00020657807,0.00005776221],"genre_scores_gemma":[0.87642115,0.000059584232,0.10826488,0.014402161,0.0001965694,0.0000657378,0.00051044737,0.00005310526,0.00002634935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998045,0.000083552455,0.0003537545,0.0005564132,0.00061729434,0.00034397942],"domain_scores_gemma":[0.99871606,0.00044302215,0.00007811053,0.00024125859,0.00010165702,0.00041990698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006971849,0.00024996256,0.00035617032,0.00073322374,0.00020271096,0.00007146009,0.00010690654,0.00011902359,0.0000078336125],"category_scores_gemma":[0.00010840419,0.00021927731,0.0001059884,0.0006972761,0.00021239609,0.00005258477,0.000060166905,0.00028815985,6.104749e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011422214,0.00093600043,0.038853083,0.0021525123,0.00044601885,0.00013596177,0.0012992548,0.0020925566,0.08489495,0.001316753,0.026377587,0.84035313],"study_design_scores_gemma":[0.00456875,0.0002310169,0.046169553,0.00052469946,0.00010458939,0.000019426068,0.0000751797,0.9287078,0.0002276016,0.000032552573,0.019142855,0.00019597347],"about_ca_topic_score_codex":0.000014391084,"about_ca_topic_score_gemma":0.000003443996,"teacher_disagreement_score":0.92661524,"about_ca_system_score_codex":0.000034543435,"about_ca_system_score_gemma":0.00007402366,"threshold_uncertainty_score":0.8941869},"labels":[],"label_agreement":null},{"id":"W4386565663","doi":"10.1016/j.compmedimag.2023.102297","title":"Self-supervised-RCNN for medical image segmentation with limited data annotation","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Alberta Bone and Joint Health Institute; University of Calgary","funders":"","keywords":"Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); Annotation; Supervised learning; Medical imaging; Semi-supervised learning; Machine learning; Pixel; Labeled data; Image segmentation; Computer vision; Artificial neural network","score_opus":0.03640291502629789,"score_gpt":0.34794957274133465,"score_spread":0.31154665771503676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386565663","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18895766,0.00058943796,0.4367752,0.36865,0.00093933806,0.0017367152,0.00012616291,0.0021935888,0.000031890515],"genre_scores_gemma":[0.23091486,0.011504674,0.45641604,0.27507463,0.004017199,0.0006174558,0.02086036,0.00047455588,0.00012021204],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730754,0.0000944741,0.000400948,0.000662569,0.0011430819,0.00039140115],"domain_scores_gemma":[0.99732363,0.0011791969,0.000086977554,0.00055768574,0.00023299034,0.0006194953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012855437,0.00022670164,0.00039413763,0.00035785517,0.00019869111,0.000103190905,0.0003153841,0.000143527,0.000029836225],"category_scores_gemma":[0.0012275515,0.00018539761,0.000059287053,0.0008538697,0.00031295142,0.00024637842,0.00029421563,0.00035051865,0.000008715519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012529523,0.0014861305,0.023902522,0.005208099,0.000843666,0.0021997204,0.0029022314,0.000006331441,0.0029167323,0.0010625856,0.29073778,0.66748124],"study_design_scores_gemma":[0.008035916,0.00019156255,0.0064807152,0.0008355962,0.000254773,0.00021352536,0.00011450804,0.9439153,0.00009580994,0.00018920554,0.039421596,0.00025148157],"about_ca_topic_score_codex":0.000032672946,"about_ca_topic_score_gemma":0.000009577685,"teacher_disagreement_score":0.943909,"about_ca_system_score_codex":0.000031649826,"about_ca_system_score_gemma":0.0004953217,"threshold_uncertainty_score":0.75602955},"labels":[],"label_agreement":null},{"id":"W4386574969","doi":"10.1016/j.compmedimag.2023.102295","title":"HViT: Hybrid vision inspired transformer for the assessment of carotid artery plaque by addressing the cross-modality domain adaptation problem in MRI","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Transformer; Convolutional neural network; Machine learning; Embedding; Pattern recognition (psychology); Ensemble learning","score_opus":0.03066686220423237,"score_gpt":0.3628223133177379,"score_spread":0.33215545111350553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386574969","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4403891,0.0004906289,0.502161,0.055889226,0.00017687268,0.00071927294,0.000036259815,0.00008749667,0.000050130864],"genre_scores_gemma":[0.9943842,0.0007043405,0.0035806664,0.0010045519,0.00009106441,0.000069412534,0.00012926584,0.000018955521,0.000017486722],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981464,0.00015823529,0.0005230546,0.00030989735,0.0005697001,0.00029267263],"domain_scores_gemma":[0.99869686,0.0006896422,0.00013007874,0.0002378202,0.0001136494,0.00013197273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021376985,0.00016742283,0.00038883978,0.0001625744,0.00027613653,0.00009380446,0.00016590617,0.000054547745,0.000003366718],"category_scores_gemma":[0.00007786946,0.000096592754,0.0001737954,0.00051753747,0.0006263874,0.00010550844,0.000039997572,0.00039519038,2.8352002e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012519043,0.001973552,0.41090253,0.0050019515,0.0014552401,0.00037333276,0.013496848,0.0014507391,0.06341004,0.003592527,0.01857152,0.4785198],"study_design_scores_gemma":[0.004377794,0.000100453544,0.083621405,0.0010161351,0.00015548323,0.0000759628,0.0005014705,0.9050795,0.00036342494,0.0025272202,0.0020150465,0.0001661205],"about_ca_topic_score_codex":0.00011466716,"about_ca_topic_score_gemma":0.00000880766,"teacher_disagreement_score":0.90362877,"about_ca_system_score_codex":0.000020702624,"about_ca_system_score_gemma":0.00013544595,"threshold_uncertainty_score":0.3938938},"labels":[],"label_agreement":null},{"id":"W4388947967","doi":"10.1016/j.compmedimag.2023.102315","title":"Image reconstruction using UNET-transformer network for fast and low-dose PET scans","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal","funders":"Alliance de recherche numérique du Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Artificial intelligence; Computer science; Mean squared error; Image quality; Ground truth; Iterative reconstruction; Residual; Imaging phantom; Maximum a posteriori estimation; Pattern recognition (psychology); Computer vision; Mathematics; Nuclear medicine; Algorithm; Image (mathematics); Statistics; Medicine","score_opus":0.0210033796698915,"score_gpt":0.31613679658168725,"score_spread":0.29513341691179573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388947967","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3080506,0.00027990207,0.6647123,0.024828387,0.0004709664,0.00082956697,0.0000308795,0.00068783324,0.00010957177],"genre_scores_gemma":[0.22994258,0.0069204113,0.7506586,0.009450053,0.0021403884,0.00022981876,0.0003785568,0.00014131176,0.00013834047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853534,0.000033078944,0.0003451905,0.00038813092,0.00028609307,0.0004121474],"domain_scores_gemma":[0.99892694,0.00019379037,0.000065041786,0.00020024015,0.000098552846,0.00051546603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006101071,0.00018470692,0.0003561994,0.00015989771,0.00028141306,0.000062140716,0.000087932756,0.00008147916,0.00001845096],"category_scores_gemma":[0.00011812889,0.00016074831,0.00009166074,0.0004826932,0.0006933043,0.00009180565,0.00006219291,0.00034038618,0.0000016321114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027270732,0.00023249339,0.011461201,0.0019079163,0.00022176307,0.00031791034,0.0004083098,0.000007146836,0.030996777,0.00661939,0.05870722,0.8888472],"study_design_scores_gemma":[0.0022901068,0.000050181112,0.0018993973,0.0009363215,0.00012722424,0.0014095491,0.00006418595,0.9782161,0.00008959966,0.00440742,0.010291257,0.00021865065],"about_ca_topic_score_codex":0.00003283777,"about_ca_topic_score_gemma":0.000001656645,"teacher_disagreement_score":0.97820896,"about_ca_system_score_codex":0.000013290542,"about_ca_system_score_gemma":0.000104514205,"threshold_uncertainty_score":0.65551263},"labels":[],"label_agreement":null},{"id":"W4389720626","doi":"10.1016/j.compmedimag.2023.102320","title":"Deep learning for report generation on chest X-ray images","year":2023,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Deep learning; Convolutional neural network; Artificial intelligence; Computer science; Medical imaging; Segmentation; Focus (optics); Computer-aided diagnosis; Radiology; Medicine; Medical physics","score_opus":0.036367761237304466,"score_gpt":0.3390442609720547,"score_spread":0.30267649973475025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389720626","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21670659,0.0008693909,0.49210855,0.28518865,0.0023759825,0.0009869385,0.0000045546153,0.0016627662,0.00009658629],"genre_scores_gemma":[0.9216893,0.0022099672,0.014216547,0.05709993,0.0031545456,0.00018306974,0.00082232384,0.00012817126,0.0004961979],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983422,0.00006223034,0.00033064553,0.00047201425,0.00048029877,0.0003125826],"domain_scores_gemma":[0.9985072,0.00070209196,0.00009357931,0.00024361337,0.00013677178,0.0003167297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010056959,0.00017379533,0.00032742388,0.0002991343,0.00024794607,0.00007525739,0.00008158308,0.0001020158,0.000013899501],"category_scores_gemma":[0.0021122503,0.00015528323,0.00011476505,0.00039863904,0.00019174558,0.000056047513,0.00007988577,0.0003771076,0.000008389298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002710347,0.00054121355,0.025910435,0.0013080103,0.00026562868,0.0050059357,0.0010414222,0.00074896816,0.018893987,0.0010070655,0.22407791,0.7209284],"study_design_scores_gemma":[0.0026509033,0.00017079496,0.020324627,0.00044684613,0.000094452786,0.00027544182,0.000036622638,0.7968082,0.00044609822,0.0002121736,0.17830873,0.00022516494],"about_ca_topic_score_codex":0.000015806172,"about_ca_topic_score_gemma":0.0000014648202,"teacher_disagreement_score":0.7960592,"about_ca_system_score_codex":0.000022670705,"about_ca_system_score_gemma":0.000110606874,"threshold_uncertainty_score":0.63322663},"labels":[],"label_agreement":null},{"id":"W4391867830","doi":"10.1016/j.compmedimag.2024.102346","title":"SCANED: Siamese collateral assessment network for evaluation of collaterals from ischemic damage","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston Health Sciences Centre; Queen's University; Kingston General Hospital; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Collateral; Medicine; Artificial intelligence; Similarity (geometry); Computer science; Computed tomography; Radiology; Pattern recognition (psychology); Image (mathematics)","score_opus":0.018712775242574402,"score_gpt":0.3397471606932634,"score_spread":0.32103438545068896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391867830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.911589,0.0039293244,0.070827894,0.008768264,0.0015018472,0.001350417,0.00008157531,0.00019188979,0.0017597447],"genre_scores_gemma":[0.9680733,0.000357415,0.028276972,0.0018530881,0.0008031553,0.00009116801,0.0004009925,0.000039044364,0.00010483256],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978286,0.00008616873,0.0004581455,0.00043013872,0.0009051004,0.0002918158],"domain_scores_gemma":[0.99884605,0.00035783055,0.00008560952,0.00027109677,0.00020179588,0.00023760443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014161705,0.0002005391,0.0004578077,0.0001452296,0.00006320625,0.00007301217,0.00012800276,0.00010430368,0.00010596324],"category_scores_gemma":[0.000091646056,0.0001702911,0.00013341983,0.0003106758,0.00020949621,0.00007842232,0.00015610077,0.00024273054,0.0000011772909],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005001155,0.00029086717,0.03290937,0.0020229493,0.0020362134,0.00028118503,0.0007669718,0.000088545974,0.022090664,0.0015428689,0.669972,0.26749825],"study_design_scores_gemma":[0.005237261,0.00008692752,0.008096202,0.0016762975,0.0008662813,0.000041572916,0.00004983586,0.92405343,0.00037701434,0.0010356674,0.058285575,0.00019390414],"about_ca_topic_score_codex":0.00003605528,"about_ca_topic_score_gemma":0.0000020225684,"teacher_disagreement_score":0.9239649,"about_ca_system_score_codex":0.000061632236,"about_ca_system_score_gemma":0.00030877854,"threshold_uncertainty_score":0.6944269},"labels":[],"label_agreement":null},{"id":"W4393029186","doi":"10.1016/j.compmedimag.2024.102373","title":"A novel center-based deep contrastive metric learning method for the detection of polymicrogyria in pediatric brain MRI","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Polymicrogyria; Computer science; Deep learning; Magnetic resonance imaging; Artificial intelligence; Metric (unit); Medicine; Radiology","score_opus":0.012324269159233096,"score_gpt":0.2900185064092529,"score_spread":0.27769423725001985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393029186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006784942,0.0039231395,0.98919994,0.005135095,0.00068982324,0.00021878879,0.0000025440024,0.00013905125,0.000013126069],"genre_scores_gemma":[0.843845,0.0003201491,0.15388802,0.0016976472,0.00017588632,0.00003470776,0.000007852562,0.00002074603,0.000009963145],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840134,0.00022906765,0.00035776093,0.00039525185,0.0003373478,0.0002792161],"domain_scores_gemma":[0.99510384,0.0044389493,0.000103316816,0.0001441123,0.000080450474,0.00012931658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002007202,0.00015121422,0.00024150727,0.00064606924,0.00015231958,0.00019067497,0.0003570176,0.0000743597,0.0000022061865],"category_scores_gemma":[0.00070982176,0.0001170923,0.00011919012,0.0015278981,0.000114311624,0.00015233441,0.000116020645,0.000496894,5.80293e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051813207,0.00010761971,0.0011179271,0.00021817572,0.00005134915,0.00002457797,0.0012131395,0.0007994193,0.0042318157,0.009363663,0.000057311307,0.9827632],"study_design_scores_gemma":[0.0017035161,0.000058476482,0.0024145269,0.0000859261,0.000022378603,0.00004306808,0.00005728867,0.98958766,0.000113526345,0.00039998154,0.0053903367,0.00012333527],"about_ca_topic_score_codex":0.00004555945,"about_ca_topic_score_gemma":0.000011420514,"teacher_disagreement_score":0.98878825,"about_ca_system_score_codex":0.000019211666,"about_ca_system_score_gemma":0.00011491398,"threshold_uncertainty_score":0.47748855},"labels":[],"label_agreement":null},{"id":"W4393114969","doi":"10.1016/j.compmedimag.2024.102376","title":"Annotation-free prediction of treatment-specific tissue outcome from 4D CT perfusion imaging in acute ischemic stroke","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotchkiss Brain Institute; Alberta Children's Hospital; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Calgary Foundation","keywords":"Perfusion; Thrombolysis; Artificial intelligence; Computer science; Stroke (engine); Perfusion scanning; Medicine; Binary classification; Radiology; Probabilistic logic; Pattern recognition (psychology); Machine learning; Myocardial infarction; Cardiology","score_opus":0.015049153045670498,"score_gpt":0.2823902842144167,"score_spread":0.2673411311687462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393114969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9275499,0.0075866114,0.055190705,0.006946164,0.0010865608,0.0004540693,0.0002257272,0.0002763532,0.0006838966],"genre_scores_gemma":[0.98622406,0.003871487,0.008175021,0.0005974663,0.00039890216,0.000029899353,0.00044753263,0.00004656731,0.00020908605],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979278,0.00004822694,0.00063090224,0.0005578632,0.0005338649,0.00030137305],"domain_scores_gemma":[0.99896705,0.00022080536,0.000083737286,0.00043543952,0.0000559782,0.00023699847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002895298,0.00027323913,0.00050151657,0.0004596988,0.00006432022,0.00007504789,0.0001843449,0.00006337385,0.0000858345],"category_scores_gemma":[0.00007256674,0.00022992592,0.00012440495,0.00036401962,0.0003137567,0.00015636976,0.00022354013,0.0003691933,0.0000043474665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002392011,0.00032856304,0.21863681,0.0003861756,0.00040814292,0.002710232,0.0014256596,0.0000033351819,0.10728363,0.00036397428,0.040818166,0.6273961],"study_design_scores_gemma":[0.018308336,0.00040806032,0.084620915,0.0035530753,0.0011714722,0.00096575764,0.0006730751,0.58059365,0.009566469,0.00038726802,0.299047,0.0007049171],"about_ca_topic_score_codex":0.00018326924,"about_ca_topic_score_gemma":0.0000030558049,"teacher_disagreement_score":0.62669116,"about_ca_system_score_codex":0.00011878306,"about_ca_system_score_gemma":0.0001042442,"threshold_uncertainty_score":0.9376107},"labels":[],"label_agreement":null},{"id":"W4393204089","doi":"10.1016/j.compmedimag.2024.102372","title":"Unsupervised classification of multi-contrast magnetic resonance histology of peripheral arterial disease lesions using a convolutional variational autoencoder with a Gaussian mixture model in latent space: A technical feasibility study","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Peripheral Artery Disease Management","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; Sunnybrook Health Science Centre","funders":"Jerold B. Katz Foundation","keywords":"Autoencoder; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Mixture model; Contrast (vision); Magnetic resonance imaging; Computer science; Gaussian; Mathematics; Deep learning; Computer vision; Physics; Medicine; Radiology","score_opus":0.03333688675085013,"score_gpt":0.30445559710996856,"score_spread":0.27111871035911844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393204089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7841792,0.0016476634,0.2098586,0.003275272,0.00011952397,0.00079799205,0.000055368528,0.000060632658,0.0000057519874],"genre_scores_gemma":[0.98198885,0.000037756978,0.01760909,0.0001937295,0.000048381906,0.000047921585,0.000047932328,0.000016125,0.000010210058],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807125,0.00016040225,0.0005128295,0.0004926478,0.0005425723,0.00022027278],"domain_scores_gemma":[0.9992034,0.00006613687,0.000070238035,0.00024959084,0.00011548113,0.0002951504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000334479,0.00019189245,0.00043007638,0.00021728585,0.00005553128,0.000020676907,0.00010437804,0.000074720694,0.000034778812],"category_scores_gemma":[0.00007687835,0.00015255607,0.000085426924,0.00034016802,0.0005853306,0.00008184103,0.000083092185,0.00028207587,1.6556795e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012810912,0.021109171,0.87364477,0.0034174863,0.00042147233,0.0021332188,0.004248326,0.003664421,0.036384527,0.019859798,0.0004508826,0.021855017],"study_design_scores_gemma":[0.0031263179,0.00009609799,0.4467706,0.0003652585,0.00010734081,0.000028479475,0.000030008057,0.54918617,4.6042834e-7,0.00019732703,0.00001627068,0.00007566582],"about_ca_topic_score_codex":0.00004075559,"about_ca_topic_score_gemma":0.00004077466,"teacher_disagreement_score":0.54552174,"about_ca_system_score_codex":0.00011455638,"about_ca_system_score_gemma":0.0006452588,"threshold_uncertainty_score":0.6221056},"labels":[],"label_agreement":null},{"id":"W4399998587","doi":"10.1016/j.compmedimag.2024.102413","title":"Radiomic-based prediction of lesion-specific systemic treatment response in metastatic disease","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; Public Health Ontario; Ontario Institute for Cancer Research; University of Toronto; University Health Network","funders":"Center for Scientific Review; National Cancer Institute; National Institutes of Health","keywords":"Medicine; Radiomics; Lesion; Radiology; Pathology","score_opus":0.02187002177830999,"score_gpt":0.3037242018003519,"score_spread":0.28185418002204193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399998587","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87107486,0.022114737,0.09447064,0.010887695,0.0007800949,0.0004186515,0.000028344632,0.00020510146,0.000019867677],"genre_scores_gemma":[0.9938666,0.003001413,0.0022806276,0.00055197824,0.00014422437,0.00002716469,0.000061030256,0.000034032557,0.000032892323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794775,0.00029677083,0.0005476489,0.0004303075,0.0005132185,0.00026431878],"domain_scores_gemma":[0.9983074,0.00076981774,0.00006017869,0.0002653637,0.00004508899,0.0005521231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012447275,0.00021438021,0.00050784135,0.00062872143,0.000055583492,0.000051043095,0.000093875824,0.000047986163,0.000023172224],"category_scores_gemma":[0.00033183343,0.00016315094,0.00015930817,0.00046620175,0.00037887503,0.00006413356,0.000035684756,0.00041078494,0.0000021801054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008213736,0.0015002561,0.05722298,0.0045263837,0.00047596882,0.015972735,0.0016510481,0.00038868893,0.021392273,0.0035984279,0.0031340823,0.88192344],"study_design_scores_gemma":[0.0045992862,0.0002367176,0.021507295,0.0047489568,0.00016143924,0.0005956717,0.000048310358,0.95602435,0.000060453844,0.00022247618,0.011652186,0.00014285403],"about_ca_topic_score_codex":0.000035737572,"about_ca_topic_score_gemma":3.2167452e-7,"teacher_disagreement_score":0.95563567,"about_ca_system_score_codex":0.00009504947,"about_ca_system_score_gemma":0.0004654192,"threshold_uncertainty_score":0.6653102},"labels":[],"label_agreement":null},{"id":"W4401383183","doi":"10.1016/j.compmedimag.2024.102422","title":"Evidence modeling for reliability learning and interpretable decision-making under multi-modality medical image segmentation","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Modality (human–computer interaction); Artificial intelligence; Reliability (semiconductor); Computer science; Segmentation; Image segmentation; Image (mathematics); Machine learning; Medical decision making; Medical imaging; Pattern recognition (psychology); Computer vision; Medicine","score_opus":0.037670357995041884,"score_gpt":0.3738711265333765,"score_spread":0.33620076853833464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401383183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031260043,0.003455683,0.9559226,0.00788106,0.0008019786,0.0002718168,0.0000014116154,0.0003950054,0.000010377902],"genre_scores_gemma":[0.7820655,0.0012558479,0.21566166,0.0008543487,0.000104784354,0.0000310771,0.0000025944385,0.000018170016,0.0000060095977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692553,0.00023678191,0.0005991777,0.0009477672,0.00083369244,0.00045707205],"domain_scores_gemma":[0.9954292,0.0035667976,0.00006764204,0.0003100263,0.00022040297,0.0004059223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038419475,0.00023910546,0.00032063643,0.00021110395,0.00041114836,0.00088452303,0.0005733365,0.00014800446,0.000018144367],"category_scores_gemma":[0.003645609,0.00021230879,0.000104922336,0.00047320384,0.00037916464,0.0012961231,0.0007673668,0.000656609,0.0000036218294],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006291551,0.00009921512,0.00072407036,0.0005946656,0.00004587826,0.00013819114,0.0019411884,0.0013767353,0.00089346594,0.022080434,0.00017683905,0.9718664],"study_design_scores_gemma":[0.00022033475,0.000038338298,0.0000567357,0.0024250625,0.000016583072,0.00008302077,0.00016382917,0.9489591,0.00008595395,0.047532737,0.00019788141,0.00022041467],"about_ca_topic_score_codex":0.00006271036,"about_ca_topic_score_gemma":0.000014260843,"teacher_disagreement_score":0.971646,"about_ca_system_score_codex":0.000055843542,"about_ca_system_score_gemma":0.00025481192,"threshold_uncertainty_score":0.86577016},"labels":[],"label_agreement":null},{"id":"W4402294280","doi":"10.1016/j.compmedimag.2024.102429","title":"RibFractureSys: A gem in the face of acute rib fracture diagnoses","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Trauma Management and Diagnosis","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Jeonbuk National University","keywords":"Rib cage; False positive paradox; Medicine; Fracture (geology); Medical diagnosis; Radiology; Voxel; Artificial intelligence; Computer science; Anatomy","score_opus":0.012474359352015244,"score_gpt":0.30308699145948875,"score_spread":0.2906126321074735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402294280","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7849789,0.024422003,0.037689403,0.15005308,0.0009384986,0.0008372766,0.000024401386,0.00032259696,0.000733801],"genre_scores_gemma":[0.9847254,0.0040162904,0.00037750762,0.01061765,0.00017726384,0.000021214424,0.000032711974,0.000014137235,0.00001781867],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986821,0.00007055117,0.00026703262,0.00027193336,0.0004912408,0.00021717859],"domain_scores_gemma":[0.99887973,0.0006962781,0.000035664973,0.00022890886,0.000026430595,0.00013296312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046473733,0.00015993137,0.00030798416,0.00023353612,0.00004519222,0.000082850725,0.0001863788,0.00009109016,0.000038578604],"category_scores_gemma":[0.00012011402,0.00009614613,0.000117988435,0.00045255185,0.00025196857,0.0000937182,0.000083977764,0.00052621734,0.0000028907425],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039858258,0.0016100195,0.17859372,0.003508363,0.0015466568,0.01229974,0.013393095,0.000011117217,0.0003046621,0.018433508,0.2575657,0.5123348],"study_design_scores_gemma":[0.0058152513,0.00029118024,0.59038174,0.004526736,0.0011644858,0.00065427186,0.00089270325,0.052554686,0.00022258562,0.005594008,0.33737504,0.0005272787],"about_ca_topic_score_codex":0.000053727555,"about_ca_topic_score_gemma":0.0000046242194,"teacher_disagreement_score":0.51180756,"about_ca_system_score_codex":0.0000068119366,"about_ca_system_score_gemma":0.000048637925,"threshold_uncertainty_score":0.3920725},"labels":[],"label_agreement":null},{"id":"W4403147824","doi":"10.1016/j.compmedimag.2024.102437","title":"MultiNet 2.0: A lightweight attention-based deep learning network for stenosis measurement in carotid ultrasound scans and cardiovascular risk assessment","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cerebrovascular and Carotid Artery Diseases","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Stenosis; Ultrasound; Radiology; Deep learning; Computer science; Artificial intelligence; Medicine; Cardiology; Internal medicine","score_opus":0.009978911662491624,"score_gpt":0.25265334774060344,"score_spread":0.24267443607811182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403147824","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2971358,0.03452403,0.6628842,0.002198157,0.0010082468,0.0017316219,0.00003662866,0.00039457812,0.00008676798],"genre_scores_gemma":[0.9909495,0.003474651,0.00434369,0.0004780881,0.0004457562,0.00014089828,0.00012016888,0.000042152664,0.0000051045868],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99747896,0.0002544305,0.00037995516,0.0006109255,0.00086702657,0.00040870314],"domain_scores_gemma":[0.9987289,0.00039428612,0.000042960706,0.00024601028,0.000154092,0.00043376413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017900526,0.0002646693,0.00056927255,0.00021640204,0.00021779173,0.00016747613,0.000077198325,0.00009278744,0.000015558042],"category_scores_gemma":[0.00024492096,0.00022363545,0.00049023575,0.0003261095,0.00020272408,0.00007500739,0.000050313447,0.00049561687,6.3231363e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052472085,0.00020539653,0.92950034,0.0013625306,0.0013361129,0.00007589203,0.00018637265,0.0005255774,0.00017676059,0.00022271366,0.00052930316,0.06582654],"study_design_scores_gemma":[0.0067356396,0.00017251787,0.5012041,0.0026108047,0.0015582892,0.00012396544,0.00016465169,0.4779525,0.000018929177,0.00018846059,0.008856083,0.00041408004],"about_ca_topic_score_codex":0.000104229985,"about_ca_topic_score_gemma":0.000029256138,"teacher_disagreement_score":0.6938137,"about_ca_system_score_codex":0.000053904078,"about_ca_system_score_gemma":0.00018767893,"threshold_uncertainty_score":0.91195893},"labels":[],"label_agreement":null},{"id":"W4407216978","doi":"10.1016/j.compmedimag.2025.102503","title":"TQGDNet: Coronary artery calcium deposit detection on computed tomography","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto General Hospital","funders":"","keywords":"Coronary artery calcium; Computed tomography; Calcium; Computer science; Radiology; Medicine; Internal medicine","score_opus":0.006081829423531283,"score_gpt":0.23027624904814994,"score_spread":0.22419441962461867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407216978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.124583416,0.0019943912,0.86959535,0.0005125428,0.0017645766,0.00014597438,0.0000038348144,0.00085789594,0.0005420366],"genre_scores_gemma":[0.99536437,0.00026801624,0.0017719612,0.002374728,0.00015008084,0.000015267335,0.000016510496,0.000027759324,0.00001133724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986906,0.000050434588,0.00030222264,0.00032532035,0.0002674781,0.00036394093],"domain_scores_gemma":[0.99928284,0.00018139691,0.000027629,0.0002363256,0.000041437354,0.00023035002],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015639282,0.00026352098,0.00028968396,0.00038337303,0.00020801624,0.00007549176,0.00018923017,0.00011156736,0.000005923313],"category_scores_gemma":[0.000021769114,0.00026364447,0.00010173984,0.00056395645,0.00021442054,0.00012718394,0.00008193267,0.0005710487,0.0000033178908],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010319917,0.00014450506,0.008402871,0.00039635075,0.00027165684,0.00036455484,0.00021536702,0.0011225253,0.006600645,0.001821361,0.0018331077,0.9787239],"study_design_scores_gemma":[0.0020209602,0.00005250442,0.038273554,0.00073622423,0.000059927377,0.00022583794,0.000045213674,0.94377023,0.003512655,0.0025755353,0.008247878,0.0004794915],"about_ca_topic_score_codex":0.0000064942315,"about_ca_topic_score_gemma":0.0000037645173,"teacher_disagreement_score":0.97824436,"about_ca_system_score_codex":0.000023415321,"about_ca_system_score_gemma":0.00001740527,"threshold_uncertainty_score":0.9999816},"labels":[],"label_agreement":null},{"id":"W4408741341","doi":"10.1016/j.compmedimag.2025.102529","title":"Class balancing diversity multimodal ensemble for Alzheimer’s disease diagnosis and early detection","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research; National Institutes of Health; Università Campus Bio-Medico di Roma; European Commission; Alzheimer's Disease Neuroimaging Initiative; Alzheimer's Association; National Institute of Biomedical Imaging and Bioengineering; Northern California Institute for Research and Education; Foundation for the National Institutes of Health; U.S. Department of Defense","keywords":"Computer science; Class (philosophy); Diversity (politics); Artificial intelligence; Disease; Alzheimer's disease; Natural language processing; Machine learning; Medicine","score_opus":0.01740771888081893,"score_gpt":0.2780347348552619,"score_spread":0.260627015974443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408741341","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09476243,0.00091038964,0.9002965,0.0029738962,0.00040850832,0.00023270748,0.000010270693,0.00038854094,0.000016720476],"genre_scores_gemma":[0.9406942,0.00035266575,0.057559643,0.0012739741,0.000052142575,0.00005115353,0.0000060133284,0.000006864542,0.0000033580486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987391,0.00006562391,0.00018939623,0.0004999856,0.00024345177,0.00026244728],"domain_scores_gemma":[0.998766,0.00047169012,0.000058780704,0.0003263044,0.00007470992,0.00030248985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043186746,0.000158646,0.00021557465,0.00020739908,0.0004627379,0.0002132697,0.0004838063,0.00007043515,4.8581074e-7],"category_scores_gemma":[0.00023840285,0.0001560967,0.00006105279,0.00026010012,0.00021212889,0.0003356428,0.001529717,0.00018700631,2.3160169e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003818911,0.0000758526,0.09245988,0.00008397377,0.000059787664,0.000039923252,0.00024426312,3.8242194e-7,0.00010225876,0.008780083,0.0021198625,0.89599556],"study_design_scores_gemma":[0.0019640962,0.000088422,0.1635991,0.00047608206,0.00014342702,0.00001717049,0.000014281434,0.8023759,0.0008493451,0.023558438,0.0065066256,0.0004070776],"about_ca_topic_score_codex":0.0001279259,"about_ca_topic_score_gemma":0.000008030015,"teacher_disagreement_score":0.89558846,"about_ca_system_score_codex":0.000012846814,"about_ca_system_score_gemma":0.000054805303,"threshold_uncertainty_score":0.63654387},"labels":[],"label_agreement":null},{"id":"W4408801012","doi":"10.1016/j.compmedimag.2025.102533","title":"A technology framework for distributed preoperative planning and medical training in deep brain stimulation","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Neurological disorders and treatments","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Deep brain stimulation; Computer science; Stimulation; Brain stimulation; Physical medicine and rehabilitation; Training (meteorology); Medicine; Neuroscience; Artificial intelligence; Medical physics; Psychology; Pathology","score_opus":0.018857081521910717,"score_gpt":0.3350716657230132,"score_spread":0.3162145842011025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408801012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37273374,0.0017971933,0.5817239,0.043165542,0.000105554565,0.00036122993,0.0000050482213,0.0000842431,0.000023532246],"genre_scores_gemma":[0.9834802,0.00014287219,0.0074781543,0.008747314,0.00003366635,0.00005305135,0.00005277182,0.000008078694,0.0000038972776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989052,0.000050100767,0.00025670542,0.0003389384,0.00020293066,0.00024614844],"domain_scores_gemma":[0.9987605,0.0008816727,0.000034973044,0.00009434499,0.00003621735,0.00019228227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026977865,0.00014259387,0.00036617738,0.00023454761,0.000108327775,0.000023806244,0.000065891014,0.00024867585,0.00000772968],"category_scores_gemma":[0.0020774086,0.00011192135,0.000036843023,0.00040019117,0.00033973632,0.000033139,0.00009056199,0.0004637808,1.0299329e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006507025,0.00040590324,0.4232269,0.00027123906,0.00017219747,0.000733778,0.0013385003,0.000011783157,0.00005228102,0.05759131,0.00033753348,0.5152079],"study_design_scores_gemma":[0.01204155,0.00040143981,0.13638002,0.0019847804,0.00009358054,0.00009272199,0.00046352576,0.5859711,0.000015218771,0.26148373,0.0008565917,0.00021576871],"about_ca_topic_score_codex":0.000003865616,"about_ca_topic_score_gemma":0.0000037461464,"teacher_disagreement_score":0.61074644,"about_ca_system_score_codex":0.00000975091,"about_ca_system_score_gemma":0.000100590114,"threshold_uncertainty_score":0.45640203},"labels":[],"label_agreement":null},{"id":"W4409351696","doi":"10.1016/j.compmedimag.2025.102550","title":"CASCADE-FSL: Few-shot learning for collateral evaluation in ischemic stroke","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cascade; Collateral; Collateral damage; Shot (pellet); Stroke (engine); Ischemic stroke; Collateral circulation; Medicine; Computer science; Artificial intelligence; Cardiology; Ischemia; Psychology; Physics; Business; Engineering; Chemistry","score_opus":0.01926121004152707,"score_gpt":0.3237557017531286,"score_spread":0.30449449171160153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409351696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8758311,0.0024471143,0.09105158,0.017664568,0.00090577576,0.001593619,0.000005891895,0.00019441576,0.010305918],"genre_scores_gemma":[0.9909829,0.00032109485,0.0037620752,0.003976103,0.00016994683,0.000109877175,0.00009757592,0.000019829793,0.00056063203],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983356,0.0000731299,0.00037800905,0.00039735917,0.0004898349,0.00032609617],"domain_scores_gemma":[0.9992249,0.0002444671,0.000068432986,0.00017944083,0.000118772194,0.00016397728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010895771,0.00017949467,0.00037733917,0.00036368475,0.00009158163,0.0000414568,0.00011851698,0.00012153639,0.000023750978],"category_scores_gemma":[0.00036115607,0.00016755975,0.00009197171,0.0003390772,0.00016304,0.000058747573,0.00016353566,0.0004683191,0.0000010110748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087595906,0.00035061725,0.14278862,0.0013845044,0.00051957805,0.00019233949,0.000775746,0.000051567793,0.020050043,0.0006666386,0.13614094,0.6962035],"study_design_scores_gemma":[0.012662403,0.00008123352,0.012558979,0.001060639,0.00030689203,0.00007308472,0.00020332092,0.77279025,0.0009884173,0.00016180176,0.19887498,0.00023796632],"about_ca_topic_score_codex":0.000025838912,"about_ca_topic_score_gemma":0.0000035107557,"teacher_disagreement_score":0.7727387,"about_ca_system_score_codex":0.00007211169,"about_ca_system_score_gemma":0.00017971493,"threshold_uncertainty_score":0.6832888},"labels":[],"label_agreement":null},{"id":"W4410856007","doi":"10.1016/j.compmedimag.2025.102575","title":"Unpaired multi-modal training and single-modal testing for detecting signs of endometriosis","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Endometriosis Research and Treatment","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University Medical Centre","funders":"Endometriosis Australia; Department of Health and Aged Care, Australian Government","keywords":"Modal; Computer science; Modal testing; Artificial intelligence; Computer vision; Radiology; Medicine; Modal analysis; Engineering; Structural engineering; Materials science; Finite element method","score_opus":0.07378367443361472,"score_gpt":0.3478602620941214,"score_spread":0.2740765876605067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410856007","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7086276,0.005234376,0.28173885,0.0028136056,0.00024854802,0.0009861803,0.000019131747,0.00016535599,0.00016634882],"genre_scores_gemma":[0.93171287,0.0002631455,0.0674278,0.00043548952,0.000072183335,0.000043786185,0.000010907713,0.000017891642,0.000015953741],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824435,0.00008514173,0.00044272686,0.00039610037,0.00040094394,0.00043072028],"domain_scores_gemma":[0.9907589,0.008324218,0.00010216857,0.00016681004,0.00023732515,0.0004106044],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009112387,0.00020356932,0.00062436936,0.0008448504,0.00020646985,0.000049056023,0.00009522999,0.000097094504,0.0000027793253],"category_scores_gemma":[0.018883001,0.000170032,0.00012846262,0.0011155301,0.0004002179,0.000061101084,0.000146496,0.00030061472,1.0173556e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022735052,0.00045082084,0.03419279,0.0008051686,0.00033890348,0.00007906281,0.00037433126,8.2045636e-7,0.036221523,0.00025165433,0.00003813069,0.9270194],"study_design_scores_gemma":[0.10163016,0.0057013365,0.052138586,0.009656589,0.0013295759,0.0009838333,0.0019282704,0.78434926,0.033021852,0.0027345961,0.0053293896,0.0011965283],"about_ca_topic_score_codex":0.000048784757,"about_ca_topic_score_gemma":0.000005046767,"teacher_disagreement_score":0.9258229,"about_ca_system_score_codex":0.000031733387,"about_ca_system_score_gemma":0.00019960228,"threshold_uncertainty_score":0.9893814},"labels":[],"label_agreement":null},{"id":"W4411331319","doi":"10.1016/j.compmedimag.2025.102578","title":"Classification of glioma grade and Ki-67 level prediction in MRI data: A SHAP-driven interpretation","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Glioma; Interpretation (philosophy); Computer science; Artificial intelligence; Nuclear medicine; Pattern recognition (psychology); Medicine; Cancer research","score_opus":0.06090363175672895,"score_gpt":0.322569541592251,"score_spread":0.261665909835522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411331319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6027483,0.00023754947,0.38620138,0.009388488,0.0007409378,0.00030376358,0.000051413663,0.00013080734,0.00019741559],"genre_scores_gemma":[0.99825937,0.00030675167,0.00063816976,0.000693312,0.00003163135,0.000014090907,0.000033502893,0.0000066687085,0.000016516276],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855113,0.00019322861,0.0003781763,0.00047778885,0.00026820198,0.00013147108],"domain_scores_gemma":[0.99915636,0.00030788092,0.00011946293,0.00028759273,0.00003949796,0.000089214365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043633147,0.0001079102,0.00017109621,0.00039260252,0.000099597884,0.00005844073,0.0002392197,0.00007952107,0.0000043936334],"category_scores_gemma":[0.0006042126,0.00010494407,0.0000222311,0.0006278666,0.00045064633,0.00026286417,0.00016367182,0.00025414405,6.1249705e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027533088,0.00049210846,0.034069195,0.00050220836,0.000028467888,0.000035477624,0.0014719904,0.00001254863,0.505501,0.04415229,0.002333385,0.41112605],"study_design_scores_gemma":[0.00099655,0.000018787481,0.15958706,0.00023706692,0.0000135202,0.000043022956,0.00008703419,0.8343628,0.0018474632,0.0019463475,0.00078349095,0.00007684158],"about_ca_topic_score_codex":0.000019231557,"about_ca_topic_score_gemma":0.000013953766,"teacher_disagreement_score":0.8343503,"about_ca_system_score_codex":0.000016494992,"about_ca_system_score_gemma":0.000060521,"threshold_uncertainty_score":0.4279495},"labels":[],"label_agreement":null},{"id":"W4412805201","doi":"10.1016/j.compmedimag.2025.102615","title":"IgCONDA-PET: Weakly-supervised PET anomaly detection using implicitly-guided attention-conditional counterfactual diffusion modeling — a multi-center, multi-cancer, and multi-tracer study","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Anomaly detection; Thresholding; Deep learning; Pattern recognition (psychology); Ground truth; Autoencoder; Machine learning; Image (mathematics)","score_opus":0.028991514474840444,"score_gpt":0.3455330713684343,"score_spread":0.31654155689359387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412805201","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5868048,0.0007405312,0.41016212,0.0011768542,0.0005175155,0.00044846116,0.000014401472,0.0001315641,0.0000037307404],"genre_scores_gemma":[0.97450036,0.0008711728,0.021777436,0.0023551327,0.00022950544,0.000046616093,0.0000758862,0.000053580177,0.00009031635],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969425,0.00018828706,0.0008033136,0.00088695844,0.00064179784,0.0005371011],"domain_scores_gemma":[0.9985549,0.00017045304,0.00016181378,0.00030443064,0.00025998458,0.00054844853],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00080110464,0.0004545711,0.0007501034,0.00052722904,0.0006214163,0.00018995829,0.00019304482,0.00011559101,0.000027753136],"category_scores_gemma":[0.00032862826,0.0004072604,0.00017144381,0.0003749715,0.00043953638,0.00021519214,0.0003169814,0.0011136981,0.0000012689427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010096167,0.012499956,0.6422616,0.0018444516,0.0018063878,0.001824708,0.002668663,0.00086279114,0.12364737,0.00014229884,0.00038403153,0.21104811],"study_design_scores_gemma":[0.024248846,0.00007800079,0.033979006,0.0009346826,0.00029627184,0.000888021,0.0004126537,0.93849516,0.000029426274,0.000031050553,0.00027616892,0.00033074114],"about_ca_topic_score_codex":0.00080722675,"about_ca_topic_score_gemma":0.00005658588,"teacher_disagreement_score":0.9376323,"about_ca_system_score_codex":0.000089978406,"about_ca_system_score_gemma":0.00019225222,"threshold_uncertainty_score":0.99983793},"labels":[],"label_agreement":null},{"id":"W4413113592","doi":"10.1016/j.compmedimag.2025.102612","title":"FGDN: A Federated Graph Convolutional Network framework for multi-site major depression disorder diagnosis","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Qinglan Project of Jiangsu Province of China; Jiangsu Provincial Key Research and Development Program; National Natural Science Foundation of China","keywords":"Computer science; Graph; Convolutional neural network; Homomorphic encryption; Artificial intelligence; Data mining; Theoretical computer science; Machine learning; Encryption; Computer network","score_opus":0.02767950749675071,"score_gpt":0.3109068497365214,"score_spread":0.2832273422397707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413113592","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03727308,0.002800028,0.9348171,0.022368094,0.0019869967,0.00044602092,0.000035246383,0.00024416068,0.000029313127],"genre_scores_gemma":[0.88456064,0.0019313758,0.045995817,0.06594757,0.00065916945,0.0006972653,0.0000433615,0.00004954801,0.000115236704],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979581,0.00018778627,0.00029983834,0.00073577673,0.00038333592,0.00043513055],"domain_scores_gemma":[0.98925704,0.01017747,0.00008407582,0.00018139549,0.000116676274,0.00018332328],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004125892,0.00024328085,0.00034022276,0.00016714516,0.0011268427,0.00014091285,0.00019905085,0.00014943027,0.000015692352],"category_scores_gemma":[0.008530517,0.0002155776,0.00013985815,0.00071512535,0.0006086007,0.00011836349,0.00033584007,0.00044162615,0.0000022167044],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007587384,0.0010253247,0.60912573,0.0005106669,0.00027861935,0.00009138465,0.00030863492,0.0001637387,0.0013220222,0.17651172,0.11133818,0.098565236],"study_design_scores_gemma":[0.007832877,0.00009463794,0.096749656,0.0017126863,0.00013092374,0.000055433204,0.000049239265,0.6985084,0.0006242365,0.1229907,0.070451915,0.000799327],"about_ca_topic_score_codex":0.000025636897,"about_ca_topic_score_gemma":0.00002129065,"teacher_disagreement_score":0.88882124,"about_ca_system_score_codex":0.000016988566,"about_ca_system_score_gemma":0.000087167995,"threshold_uncertainty_score":0.99982107},"labels":[],"label_agreement":null},{"id":"W4413149186","doi":"10.1016/j.compmedimag.2025.102630","title":"Inference time correction based on confidence and uncertainty for improved deep-learning model performance and explainability in medical image classification","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"ASTER","funders":"Qatar National Research Fund; Qatar Foundation","keywords":"Inference; Artificial intelligence; Computer science; Deep learning; Machine learning; Image (mathematics); Confidence interval; Medical imaging; Pattern recognition (psychology); Computer vision; Statistics; Mathematics","score_opus":0.008764051783965858,"score_gpt":0.3013993181054609,"score_spread":0.29263526632149506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413149186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33958393,0.00021256875,0.64131397,0.017863061,0.00023198283,0.0004586252,0.0000014183468,0.00010681138,0.00022760531],"genre_scores_gemma":[0.9884627,0.0008031987,0.0059598824,0.0045519583,0.000055286677,0.000053428837,0.00003521496,0.000015283478,0.00006306724],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982719,0.00013383885,0.00040619913,0.00053848716,0.00034797282,0.0003016448],"domain_scores_gemma":[0.9979594,0.0012521092,0.000089804904,0.0001824896,0.00013937945,0.00037685456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018194905,0.0002058793,0.00042597135,0.00027877605,0.00021927482,0.00007296334,0.00010673096,0.00017050856,0.000009398172],"category_scores_gemma":[0.0044485764,0.00017927679,0.000044375513,0.00025165547,0.0007445078,0.00010373809,0.0000903635,0.0010121035,2.5283177e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068759173,0.00020481135,0.038885046,0.00082678266,0.000025861767,0.000020898384,0.00029097547,0.0004045309,0.0015507366,0.0014728853,0.00028529376,0.9553446],"study_design_scores_gemma":[0.0035462189,0.00012999334,0.028023181,0.0011104797,0.000035204877,0.000034782774,0.000043459124,0.9656033,0.0000167339,0.0008293161,0.0004781883,0.00014916541],"about_ca_topic_score_codex":0.00004659212,"about_ca_topic_score_gemma":0.0000041221692,"teacher_disagreement_score":0.96519876,"about_ca_system_score_codex":0.000046361507,"about_ca_system_score_gemma":0.00029371513,"threshold_uncertainty_score":0.7310695},"labels":[],"label_agreement":null}]}