{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":59,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":59,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"465036eb6370","filters":{"venue":"Journal of Medical Imaging"}},"results":[{"id":"W3082904399","doi":"10.1117/1.jmi.7.4.044503","title":"Explainable end-to-end deep learning for diabetic retinopathy detection across multiple datasets","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Diabetic retinopathy; Medicine; Artificial intelligence; Deep learning; Fundus (uterus); Convolutional neural network; Retinal; End-to-end principle; Retinopathy; Pattern recognition (psychology); Computer science; Optometry; Machine learning; Ophthalmology; Diabetes mellitus","retraction":null,"screen_n_in":null,"score":{"opus":0.01755500321217589,"gpt":0.3195008864737511,"spread":0.3019458832615752,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001941345,0.0001682852,0.0005342799,0.0001376009,0.0002325831,0.00009691495,0.0002525224,0.00006482458,0.0001598],"category_scores_gemma":[0.01051237,0.0001355629,0.0002659769,0.0003649561,0.00009948867,0.0002301099,0.000105431,0.0008951951,0.00002083734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007827015,"about_ca_system_score_gemma":0.00009248815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002869386,"about_ca_topic_score_gemma":0.000003582513,"domain_scores_codex":[0.9973384,0.0001117287,0.0006736296,0.0002608555,0.001156381,0.0004590784],"domain_scores_gemma":[0.9978676,0.0003989906,0.0003307699,0.0001412251,0.0002654648,0.0009959679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007728822,0.0001689911,0.04970847,0.0004250479,0.0002196896,0.001657149,0.002752101,0.0003705585,0.05268125,0.000002288214,0.004366955,0.8868746],"study_design_scores_gemma":[0.007130363,0.0007722249,0.005651948,0.00120287,0.0007794401,0.002003716,0.008023941,0.8134468,0.02900457,0.00004250905,0.1315193,0.0004224219],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5291383,0.001310556,0.4107636,0.05801205,0.0003996128,0.0002319356,0.00001456258,0.00006456681,0.00006490124],"genre_scores_gemma":[0.992646,0.0000955345,0.00258487,0.003420793,0.001142536,0.000006657647,0.00003063595,0.00003311803,0.00003985213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8864522,"threshold_uncertainty_score":0.9978225,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3159395977","doi":"10.1117/1.jmi.8.s1.014502","title":"Deep CNN models for predicting COVID-19 in CT and x-ray images","year":2021,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Medicine; Coronavirus disease 2019 (COVID-19); Convolutional neural network; Artificial intelligence; Receiver operating characteristic; Area under curve; Deep learning; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Pattern recognition (psychology); Nuclear medicine; Pneumonia; Computed tomography; Radiology; Pathology; Computer science; Disease; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.0363969574671866,"gpt":0.3727608580027925,"spread":0.3363639005356058,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002616395,0.0001429481,0.0005075547,0.0002770262,0.00008005159,0.0000658288,0.000150149,0.00005020505,0.0001268625],"category_scores_gemma":[0.01614432,0.0001220028,0.0001441247,0.0002344019,0.0001375693,0.000284648,0.0001106169,0.0006591693,8.059309e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003179022,"about_ca_system_score_gemma":0.001708766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007748386,"about_ca_topic_score_gemma":0.00002149544,"domain_scores_codex":[0.9975773,0.0001101546,0.0007283594,0.0002431279,0.001016632,0.0003244441],"domain_scores_gemma":[0.996585,0.001914897,0.0002541105,0.0001575379,0.0002571332,0.0008313939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000796369,0.001961184,0.3687952,0.004369867,0.0005491304,0.06320203,0.006545452,0.01302745,0.007140208,0.0004522821,0.1204509,0.4127099],"study_design_scores_gemma":[0.01218661,0.0001087889,0.006016937,0.003080514,0.0003541578,0.009404909,0.002270838,0.9190099,0.0007739341,0.003010361,0.04352294,0.000260109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.100107,0.01233047,0.2972927,0.5891948,0.0006330048,0.0002807252,0.000004654784,0.00004633148,0.00011026],"genre_scores_gemma":[0.9078108,0.001498616,0.01152966,0.07813268,0.0009157784,0.00001062969,0.000004727482,0.00004277362,0.00005435931],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9059824,"threshold_uncertainty_score":0.9921431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3209589623","doi":"10.1117/1.jmi.8.5.052115","title":"Flat-panel conebeam CT in the clinic: history and current state","year":2021,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Radboud Universitair Medisch Centrum; University of Toronto; University of Texas MD Anderson Cancer Center; University of Twente; Georgia Institute of Technology; Johns Hopkins University; Radboud Universiteit; Emory University","keywords":"Medicine; Flat panel detector; Digital radiography; Flat panel; Medical physics; Image quality; High resolution; Nuclear medicine; Scanner; Radiography; Radiology; Computer science; Detector; Artificial intelligence; Computer graphics (images); Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.03705924452277223,"gpt":0.333478614238774,"spread":0.2964193697160017,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002129953,0.0001054155,0.0002562531,0.0001480626,0.00004447592,0.00007925634,0.0003215935,0.00001681647,0.0005910895],"category_scores_gemma":[0.0005578616,0.00007445826,0.00013334,0.0001550756,0.000219753,0.0003015999,0.00008261345,0.001094838,0.00002206949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007651402,"about_ca_system_score_gemma":0.0002322314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000250583,"about_ca_topic_score_gemma":0.00001767844,"domain_scores_codex":[0.9976726,0.0002629368,0.000647268,0.0001397711,0.001053756,0.0002237331],"domain_scores_gemma":[0.9989874,0.0003601923,0.0002555857,0.0001391641,0.00006675852,0.0001908345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003695338,0.0002521704,0.1212841,0.00009368493,0.00006316653,0.02461224,0.001296404,8.453408e-7,0.0003919135,0.00006631381,0.1312092,0.7206931],"study_design_scores_gemma":[0.004192573,0.00002829544,0.2160403,0.001124949,0.0001343294,0.03980738,0.003459459,0.002892114,0.0001896378,0.001465719,0.7303433,0.0003219121],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8707427,0.1131439,0.001268247,0.005719703,0.00640581,0.0000732467,0.000005640573,0.00001454156,0.002626225],"genre_scores_gemma":[0.9938517,0.003210858,0.00009320742,0.002293067,0.0003946026,0.000001039948,0.000002807362,0.00001297091,0.0001397316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7203711,"threshold_uncertainty_score":0.6472016,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2781822205","doi":"10.1117/1.jmi.4.4.045501","title":"Comparing search patterns in digital breast tomosynthesis and full-field digital mammography: an eye tracking study","year":2017,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Digital Radiography and Breast Imaging","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"National Cancer Institute; National Institute of Biomedical Imaging and Bioengineering; National Eye Institute","keywords":"Medicine; Digital Breast Tomosynthesis; Visual search; Computer vision; Saccadic masking; Digital mammography; Eye movement; Mammography; Radiology; Artificial intelligence; Medical physics; Computer science; Breast cancer; Ophthalmology","retraction":null,"screen_n_in":null,"score":{"opus":0.02356831976116204,"gpt":0.332465382199198,"spread":0.3088970624380359,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001152492,0.0002275141,0.0006124782,0.0006059548,0.0001867613,0.00178739,0.00054647,0.00006276411,0.00003464753],"category_scores_gemma":[0.0006147816,0.0001824746,0.0002132777,0.0001557552,0.0002333592,0.003600537,0.0002192241,0.0008953729,0.000001565847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003610825,"about_ca_system_score_gemma":0.0001103083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001077285,"about_ca_topic_score_gemma":0.00003237046,"domain_scores_codex":[0.9970787,0.00003445864,0.0006906022,0.0002871465,0.001454464,0.0004546632],"domain_scores_gemma":[0.9982594,0.0001849307,0.0002855206,0.0003501965,0.0001638387,0.0007560886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001783359,0.0006410152,0.6031023,0.00003434884,0.00007248955,0.002205347,0.0004179547,6.536599e-7,0.0000410023,0.000004103238,0.000009778472,0.3932927],"study_design_scores_gemma":[0.002903075,0.0003038268,0.9777658,0.001587567,0.0000808029,0.007808979,0.005945456,0.003261608,0.00003410042,0.0000749159,0.00003451176,0.0001993619],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934248,0.0001651642,0.0007932623,0.004258654,0.0001642364,0.0001481747,0.000007581159,0.00002250844,0.001015607],"genre_scores_gemma":[0.9993289,0.00003041486,0.00004184384,0.000152763,0.0004078538,0.000001408955,0.000002419021,0.00002781202,0.000006625928],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3930933,"threshold_uncertainty_score":0.9992489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011129081","doi":"10.1117/1.jmi.7.4.042803","title":"Quantitative imaging feature pipeline: a web-based tool for utilizing, sharing, and building image-processing pipelines","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Upload; Computer science; Software; Pipeline (software); Graphical user interface; Segmentation; Feature (linguistics); Interface (matter); Image processing; Application programming interface; Image file formats; Source code; Machine learning; Artificial intelligence; Image (mathematics); World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02133768374042713,"gpt":0.3554667564339915,"spread":0.3341290726935644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002694947,0.0003529791,0.0008723655,0.0003087257,0.0002371048,0.0002862839,0.0004464619,0.0001141574,0.00008337697],"category_scores_gemma":[0.01189256,0.0002789439,0.0003233057,0.0003495396,0.000387773,0.0004801293,0.0001577233,0.00176669,0.000002077019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007522858,"about_ca_system_score_gemma":0.0006741975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001049409,"about_ca_topic_score_gemma":4.083893e-7,"domain_scores_codex":[0.9964514,0.00008011952,0.001005562,0.0004906409,0.001411572,0.0005607288],"domain_scores_gemma":[0.997037,0.0004560091,0.0006841172,0.0001671178,0.0006700354,0.0009857535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001814836,0.0003059831,0.1240811,0.003170288,0.0002049505,0.003214945,0.001921166,0.0001197927,0.07685225,0.0006612067,0.09524999,0.6924035],"study_design_scores_gemma":[0.006656984,0.0001112425,0.0006083429,0.00241895,0.0003325493,0.001331441,0.0008290157,0.9624965,0.0005886952,0.0002230948,0.02412111,0.0002821075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08815388,0.00971834,0.6483252,0.2527357,0.000446235,0.0003125056,0.000005297023,0.0001157421,0.0001871042],"genre_scores_gemma":[0.7910202,0.0003543663,0.1811353,0.02487467,0.002422649,0.000008567374,0.00001106418,0.0001234285,0.00004981567],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9623767,"threshold_uncertainty_score":0.9999663,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1969648931","doi":"10.1117/1.jmi.1.3.035502","title":"Mechanical stability analysis of carrageenan-based polymer gel for magnetic resonance imaging liver phantom with lesion particles","year":2014,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Optical Imaging and Spectroscopy Techniques","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Imaging phantom; Elastic modulus; Relaxation (psychology); Carrageenan; Biomedical engineering; Polymer; Medicine; Calibration curve; Composite material; Calibration; Materials science; Modulus; Nuclear magnetic resonance; Nuclear medicine; Chromatography; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01737294897894677,"gpt":0.3208400490467774,"spread":0.3034671000678307,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002526873,0.0001928796,0.0008483354,0.0003436158,0.00006549239,0.00003468771,0.0002507182,0.0000671391,0.0001954328],"category_scores_gemma":[0.001369314,0.0001290472,0.0003701396,0.0005099805,0.0003800508,0.0001427235,0.00003923231,0.0004588166,5.775408e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008577888,"about_ca_system_score_gemma":0.000309859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007791878,"about_ca_topic_score_gemma":0.00001144572,"domain_scores_codex":[0.9969772,0.0001588887,0.0008285299,0.0002764021,0.001364839,0.0003941612],"domain_scores_gemma":[0.9977188,0.0006594306,0.0003376312,0.0003273824,0.0004965282,0.0004602855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002636105,0.001594324,0.2227018,0.0004709524,0.0004069491,0.0004266716,0.0003554558,0.00001361986,0.1957423,0.001755083,0.001210221,0.5726865],"study_design_scores_gemma":[0.003360833,0.0005966698,0.01596208,0.0009558041,0.002698125,0.0001456551,0.0001693557,0.73444,0.2404949,0.0002918488,0.0006786007,0.0002061405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3800441,0.006567074,0.5968545,0.0160018,0.0000946109,0.0002399358,0.000008150014,0.00006706629,0.0001227286],"genre_scores_gemma":[0.968528,0.00008003392,0.0301143,0.001076067,0.0001543289,0.000006341817,0.000003003609,0.00002610471,0.00001178343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7344264,"threshold_uncertainty_score":0.5262393,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2931985496","doi":"10.1117/1.jmi.6.2.025001","title":"Intraoperative 360-deg three-dimensional transvaginal ultrasound during needle insertions for high-dose-rate transperineal interstitial gynecologic brachytherapy of vaginal tumors","year":2019,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Endometrial and Cervical Cancer Treatments","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Medicine; Brachytherapy; Imaging phantom; Radiology; Ultrasound; Transvaginal ultrasound; Nuclear medicine; Radiation therapy","retraction":null,"screen_n_in":null,"score":{"opus":0.01376684624070131,"gpt":0.2937769305689417,"spread":0.2800100843282404,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007600322,0.000252307,0.000833008,0.0002985981,0.00009352881,0.00002638446,0.0002372592,0.0001049837,0.002239289],"category_scores_gemma":[0.0003269785,0.0001776318,0.0003484301,0.0003198014,0.0002327752,0.0002847486,0.00001861767,0.0006524994,0.000008213469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001955976,"about_ca_system_score_gemma":0.0004963579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009985295,"about_ca_topic_score_gemma":0.00004075591,"domain_scores_codex":[0.9973391,0.0000966975,0.0009452047,0.0002505039,0.0009848921,0.0003835877],"domain_scores_gemma":[0.9981017,0.0006593788,0.0003160381,0.00013647,0.0003676334,0.0004188209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.05780531,0.00746727,0.309128,0.002449,0.004647828,0.003635386,0.003290029,0.00129565,0.4797258,0.002765748,0.0009515108,0.1268385],"study_design_scores_gemma":[0.1688502,0.01333302,0.6897166,0.004976763,0.002002141,0.009063605,0.002328248,0.00901651,0.09529801,0.002764746,0.001381137,0.00126894],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9852145,0.0006713733,0.004883,0.007898094,0.000683191,0.0004447074,0.00003178733,0.00001934785,0.000153992],"genre_scores_gemma":[0.996924,0.0001138105,0.001247776,0.0009089065,0.0006772201,0.000014447,0.0000177562,0.00002964154,0.00006642404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3844278,"threshold_uncertainty_score":0.9986728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2789347607","doi":"10.1117/1.jmi.5.2.021215","title":"Design and validation of an open-source library of dynamic reference frames for research and education in optical tracking","year":2018,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Robotics and Sensor-Based Localization","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Johns Hopkins University","keywords":"Medicine; Open source; Tracking (education); Medical physics; Software","retraction":null,"screen_n_in":null,"score":{"opus":0.05539776239939787,"gpt":0.3753046797025517,"spread":0.3199069173031538,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001337884,0.00004278473,0.0001348026,0.0001880508,0.00002334099,0.00005785015,0.0001407139,0.00005164542,0.00001008494],"category_scores_gemma":[0.0003687325,0.0000378687,0.000006736814,0.0001158969,0.0001239187,0.0004499216,0.00003148416,0.0001806365,6.002671e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000165157,"about_ca_system_score_gemma":0.0001397716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000634133,"about_ca_topic_score_gemma":9.389429e-7,"domain_scores_codex":[0.9991601,0.00007190881,0.0003241812,0.00006451835,0.0002855643,0.0000937178],"domain_scores_gemma":[0.9993175,0.0003077278,0.00006825398,0.00005454141,0.0001593186,0.00009271673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001888659,0.0002644057,0.0041155,0.0003859604,0.0000226479,0.000006206143,0.001447018,0.01279541,0.03137377,0.001844345,0.0003961827,0.9471597],"study_design_scores_gemma":[0.0004289652,0.0001550762,0.002475471,0.0005297477,0.000007034613,0.00002687061,0.0004308032,0.9789124,0.01397465,0.002954288,0.00006131343,0.00004338428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.564124,0.0002038928,0.435118,0.0003722325,0.00004549084,0.0000804891,3.043039e-7,0.000003236423,0.0000523693],"genre_scores_gemma":[0.9622659,0.0001799294,0.03746246,0.00001814255,0.00005305962,9.477573e-7,0.000002574799,0.00001182185,0.000005163517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.966117,"threshold_uncertainty_score":0.1544241,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4308460469","doi":"10.1117/1.jmi.9.6.066001","title":"Predicting recurrence risks in lung cancer patients using multimodal radiomics and random survival forests","year":2022,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"National Cancer Institute","keywords":"Medicine; Concordance; Cohort; Stage (stratigraphy); Radiology; Lung cancer; Nomogram; Cancer; Oncology; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01824316286323242,"gpt":0.3565861531020472,"spread":0.3383429902388148,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003776478,0.0001725778,0.0005939078,0.0003694711,0.0002117086,0.00004289785,0.0002630878,0.00005684463,0.0001582931],"category_scores_gemma":[0.003089335,0.0001484648,0.0001200993,0.0003021174,0.000167334,0.0001989155,0.0002557329,0.002291813,1.174e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003737529,"about_ca_system_score_gemma":0.0004944475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008079383,"about_ca_topic_score_gemma":0.00001671241,"domain_scores_codex":[0.996365,0.0003080482,0.0008729996,0.0002353958,0.001822682,0.0003959105],"domain_scores_gemma":[0.9983393,0.000424818,0.0005023938,0.0001084066,0.0001365774,0.000488517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003199905,0.0001712104,0.9186307,0.0000914161,0.00005506156,0.0005005059,0.0006312724,0.001634531,0.0001064493,0.000006437112,0.000197558,0.07765485],"study_design_scores_gemma":[0.01060918,0.0000480144,0.1916697,0.0007097895,0.0001160547,0.0007175575,0.0003101046,0.7953534,0.000007933494,0.00003174191,0.0003099065,0.0001165405],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9842253,0.003692035,0.005631044,0.00445408,0.001726888,0.0002067915,0.00000534288,0.00001296319,0.00004551529],"genre_scores_gemma":[0.997078,0.0005716803,0.001112455,0.0006256517,0.0005641152,0.000006392534,0.000004487925,0.00003177677,0.00000541857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7937189,"threshold_uncertainty_score":0.9956912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2523271765","doi":"10.1117/1.jmi.3.3.034004","title":"Automatic basal slice detection for cardiac analysis","year":2016,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"National Medical Research Council; National University Health System","keywords":"Basal (medicine); Medicine; Ventricle; Segmentation; Artificial intelligence; Magnetic resonance imaging; Cardiac magnetic resonance imaging; Biomedical engineering; Cardiology; Computer science; Internal medicine; Radiology","retraction":null,"screen_n_in":null,"score":{"opus":0.009005072385496663,"gpt":0.3604322117590711,"spread":0.3514271393735744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006447904,0.00008531779,0.0004271897,0.0002338107,0.00004017132,0.0000158018,0.00006291563,0.00004045592,0.000259506],"category_scores_gemma":[0.0008288798,0.00004717253,0.001883138,0.000210237,0.00003871709,0.0001054712,0.00001660287,0.00008830168,0.000007726435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001184143,"about_ca_system_score_gemma":0.000139496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001259374,"about_ca_topic_score_gemma":6.267944e-7,"domain_scores_codex":[0.9985297,0.00004318242,0.0003545279,0.00009901201,0.0008075622,0.0001660028],"domain_scores_gemma":[0.9988372,0.0002522469,0.0001818247,0.000118875,0.0002063413,0.0004035642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001195147,0.0001275465,0.2341195,0.00004610179,0.005296397,0.00008129686,0.00003242614,5.746995e-7,0.000977551,0.000008173016,0.001701131,0.7574897],"study_design_scores_gemma":[0.009019311,0.0002169114,0.9347346,0.0007409608,0.03025614,0.0001811443,0.000281019,0.01715254,0.001641298,0.0002924986,0.005281486,0.0002021161],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8944944,0.001601849,0.09255667,0.01007671,0.0008778358,0.0001852203,0.00001629117,0.00002675321,0.0001643095],"genre_scores_gemma":[0.9984298,0.0001429167,0.0003182445,0.0003934046,0.0006468846,0.00000597703,0.000001912872,0.00001167484,0.00004916443],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7572876,"threshold_uncertainty_score":0.2841408,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140603372","doi":"10.1117/1.jmi.2.1.013502","title":"Single-coil magnetic induction tomographic three-dimensional imaging","year":2015,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Electrical and Bioimpedance Tomography","field":"Engineering","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kimberly-Clark (Canada)","funders":"Kimberly-Clark","keywords":"Electromagnetic coil; Eddy current; Electromagnetic induction; Medicine; Nuclear magnetic resonance; Transverse plane; Conductivity; Tomography; Acoustics; Biomedical engineering; Physics; Radiology","retraction":null,"screen_n_in":null,"score":{"opus":0.01459418552375493,"gpt":0.2266792447152741,"spread":0.2120850591915192,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009759883,0.0001765148,0.0002705169,0.0004470703,0.0000446536,0.00006315918,0.0003028028,0.00007586049,0.0001103193],"category_scores_gemma":[0.0002298316,0.0001376986,0.0001772614,0.0006861012,0.0001387202,0.0003589311,0.00004202841,0.0007965189,0.00001252806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007486797,"about_ca_system_score_gemma":0.00009159382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001627922,"about_ca_topic_score_gemma":0.000006611291,"domain_scores_codex":[0.9974278,0.00004282433,0.0005544355,0.0001270975,0.001473619,0.0003742064],"domain_scores_gemma":[0.9988844,0.00007615401,0.0001148847,0.0001118239,0.0002230616,0.0005896275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004072929,0.0001823132,0.03219173,0.00004497009,0.00006666366,0.0007099361,0.0001074527,0.000472453,0.01000834,0.00005546071,0.03485696,0.921263],"study_design_scores_gemma":[0.006946809,0.000501466,0.02018793,0.001518126,0.0003525383,0.01389449,0.0003988621,0.884117,0.006347135,0.01508162,0.04918419,0.001469811],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9253467,0.0394106,0.01897796,0.01114524,0.003215937,0.0001100858,0.000001787252,0.0002862525,0.001505424],"genre_scores_gemma":[0.9973556,0.0001027096,0.001059299,0.0004249606,0.001016237,0.000001374056,0.000001219187,0.00002855456,0.000009988071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9197932,"threshold_uncertainty_score":0.5615188,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142717410","doi":"10.1117/1.jmi.1.3.031005","title":"Magnetization-prepared rapid acquisition with gradient echo magnetic resonance imaging signal and texture features for the prediction of mild cognitive impairment to Alzheimer’s disease progression","year":2014,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute on Aging; University of California, San Diego; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; National Institutes of Health; Genentech; IXICO; Servier; Instituto Tecnológico y de Estudios Superiores de Monterrey; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; F. Hoffmann-La Roche; Medpace; AstraZeneca; Eli Lilly and Company; Bristol-Myers Squibb; Novartis Pharmaceuticals Corporation; Consejo Nacional de Ciencia y Tecnología; Synarc; Bayer HealthCare; Meso Scale Diagnostics; Foundation for the National Institutes of Health","keywords":"Medicine; Magnetic resonance imaging; Neuroimaging; Positron emission tomography; Logistic regression; Artificial intelligence; Cognition; Pattern recognition (psychology); Radiology; Internal medicine; Computer science; Psychiatry","retraction":null,"screen_n_in":null,"score":{"opus":0.01009305487226867,"gpt":0.3086486459863266,"spread":0.2985555911140579,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00130086,0.0001617842,0.0002673184,0.0001969466,0.0001599106,0.00005740476,0.0001325113,0.00003531464,0.000182894],"category_scores_gemma":[0.0003773889,0.00009280507,0.00009677497,0.0001964796,0.0002466459,0.000159909,0.00006826173,0.0002866108,6.64311e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000380514,"about_ca_system_score_gemma":0.0002003766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005847995,"about_ca_topic_score_gemma":0.000001046372,"domain_scores_codex":[0.9973628,0.0001447831,0.000428301,0.0002284469,0.001545994,0.0002896557],"domain_scores_gemma":[0.9980272,0.0003586813,0.0002280869,0.0001132592,0.0007408223,0.0005319276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.005348787,0.0004486948,0.1792533,0.0001659948,0.00009531632,0.00008788129,0.000637788,0.000006154452,0.0006251727,0.00002111025,0.005637026,0.8076728],"study_design_scores_gemma":[0.008234495,0.002601725,0.9407198,0.004581537,0.001179654,0.0004076551,0.001107897,0.03746621,0.00158988,0.0001714803,0.001803622,0.0001360689],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.522195,0.1123838,0.2590942,0.09748361,0.0006599591,0.007370648,0.0001460384,0.00008280668,0.0005839323],"genre_scores_gemma":[0.9970467,0.0004352763,0.0006584156,0.00131878,0.0003908593,0.00007421103,0.00002207197,0.00002018799,0.00003350373],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8075367,"threshold_uncertainty_score":0.3784481,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034780937","doi":"10.1117/1.jmi.7.3.033502","title":"Photon-counting computed tomography of lanthanide contrast agents with a high-flux 330-μm-pitch cadmium zinc telluride detector in a table-top system","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Redlen Technologies (Canada); University of Victoria","funders":"","keywords":"Cadmium zinc telluride; Imaging phantom; Gadolinium; Nuclear medicine; Detector; Medicine; Contrast (vision); Tomography; Lutetium; Photon counting; Optics; Physics; Materials science; Radiology","retraction":null,"screen_n_in":null,"score":{"opus":0.005869698926480241,"gpt":0.2130379416736901,"spread":0.2071682427472099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068195,0.0002635245,0.0007286565,0.0002903274,0.00005072436,0.00005319355,0.0004323533,0.00007666552,0.00007185556],"category_scores_gemma":[0.0002018613,0.0002213799,0.000117795,0.0007375197,0.00009438511,0.0004002863,0.00006406478,0.0009230284,0.000003269721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001097523,"about_ca_system_score_gemma":0.0001269301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000094399,"about_ca_topic_score_gemma":0.00001413075,"domain_scores_codex":[0.9971799,0.00006538541,0.0009947877,0.0001970219,0.001074915,0.000488043],"domain_scores_gemma":[0.9986884,0.0002097336,0.0003691407,0.0001317736,0.0001640567,0.0004369201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001785819,0.0007699808,0.3594645,0.01186761,0.002471539,0.03102184,0.01074756,0.1345726,0.3520186,0.0004206581,0.006467667,0.08839167],"study_design_scores_gemma":[0.005537085,0.0000928751,0.005762959,0.005622009,0.0001542231,0.001249591,0.002793811,0.9188493,0.05807898,0.00002590748,0.001310603,0.0005226899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7833562,0.001773555,0.2129342,0.0007554609,0.0005490098,0.0001932022,0.00001179497,0.0001404199,0.0002861776],"genre_scores_gemma":[0.9961267,0.00003914517,0.003062597,0.000323725,0.0003864147,0.000003654652,0.00000265311,0.00005328774,0.000001812591],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7842767,"threshold_uncertainty_score":0.902761,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2563437364","doi":"10.1117/1.jmi.3.4.044505","title":"Computer-aided diagnosis of retinopathy in retinal fundus images of preterm infants via quantification of vascular tortuosity","year":2016,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Retinopathy of Prematurity Studies","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Universidade Federal de Alagoas","keywords":"Medicine; Retinopathy of prematurity; Tortuosity; Retinal; Fundus (uterus); Ophthalmology; Receiver operating characteristic; Quadrant (abdomen); Retinopathy; Radiology; Surgery; Gestational age; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01869066111123832,"gpt":0.2994506669126495,"spread":0.2807600058014111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003466426,0.0001684834,0.00103673,0.0003572196,0.00002297226,0.000005957581,0.0003447592,0.0001165466,0.00007491996],"category_scores_gemma":[0.003527709,0.0001131242,0.0002861534,0.0002180359,0.0005285635,0.0002035859,0.000150296,0.0003955664,0.000001090773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000758738,"about_ca_system_score_gemma":0.0001613558,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007316065,"about_ca_topic_score_gemma":0.000004264724,"domain_scores_codex":[0.9958116,0.0002682847,0.00171627,0.000204216,0.001765258,0.0002343755],"domain_scores_gemma":[0.9965602,0.000700608,0.001499915,0.0003334299,0.0007028249,0.0002029945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003776092,0.0004850813,0.8418309,0.000747063,0.0001384123,0.0002058385,0.0007874301,9.006957e-7,0.0719571,0.00001810395,0.0006246592,0.08282689],"study_design_scores_gemma":[0.003445917,0.0003740405,0.8513229,0.009684534,0.0002292759,0.0003465909,0.0001845141,0.0006828634,0.1333161,0.0002120205,0.00007317275,0.0001279536],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.980356,0.002500184,0.01071607,0.005788218,0.0003472526,0.0002039834,0.000006991259,0.000008113659,0.00007314835],"genre_scores_gemma":[0.9941927,0.001919581,0.003599669,0.00006268558,0.0002022942,0.000002886591,0.000001044459,0.00001475178,0.000004436118],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08269893,"threshold_uncertainty_score":0.4613072,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318695000","doi":"10.1117/1.jmi.10.1.017501","title":"Single patch super-resolution of histopathology whole slide images: a comparative study","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Magnification; Histopathology; Artificial intelligence; Digital pathology; Image resolution; Image quality; Computer science; Medicine; Pixel; Digital imaging; Computer vision; Digital image; Deep learning; Image processing; Pattern recognition (psychology); Medical physics; Image (mathematics); Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.04251881914739823,"gpt":0.3364908861053369,"spread":0.2939720669579386,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002258407,0.0001032363,0.0003457284,0.0003306578,0.00007824339,0.00004367817,0.0008006891,0.00004556687,0.00002191675],"category_scores_gemma":[0.0003727641,0.00008817866,0.00009518886,0.0006469747,0.0001488458,0.0005475173,0.000265158,0.0004407189,0.00002110309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000193656,"about_ca_system_score_gemma":0.0002000194,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000722398,"about_ca_topic_score_gemma":0.00001744174,"domain_scores_codex":[0.9973678,0.0003062762,0.0006443337,0.0001917563,0.001252198,0.0002376308],"domain_scores_gemma":[0.9986677,0.0002500383,0.0004066322,0.0002335156,0.0002914736,0.000150603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001992316,0.002812708,0.06303422,0.0001389403,0.0001822641,0.005666122,0.05692453,0.001416202,0.1374965,0.0004292326,0.1253593,0.6063407],"study_design_scores_gemma":[0.007251776,0.002493767,0.08740272,0.0008823142,0.0001489456,0.00372563,0.01969551,0.8302059,0.01988163,0.004454527,0.02315994,0.000697409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4196495,0.0004534488,0.5670151,0.01058109,0.001869385,0.0001230258,0.000001227012,0.00007234822,0.0002349425],"genre_scores_gemma":[0.9966725,0.00002108898,0.002862191,0.0001528484,0.0002369273,0.000003191896,3.635372e-7,0.00000710394,0.00004376203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8287897,"threshold_uncertainty_score":0.3595822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2175730465","doi":"10.1117/1.jmi.2.4.044002","title":"Quantitative performance characterization of image quality and radiation dose for a CS 9300 dental cone beam computed tomography machine","year":2015,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Centre National de la Recherche Scientifique","keywords":"Imaging phantom; Cone beam computed tomography; Image quality; Medicine; Nuclear medicine; Pixel; Scanner; Image resolution; Dot pitch; Ionization chamber; Optics; Medical physics; Computed tomography; Physics; Artificial intelligence; Radiology; Ionization; Image (mathematics); Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02646565339722995,"gpt":0.3378828525717866,"spread":0.3114171991745566,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001896089,0.0001279073,0.0003663605,0.0003368133,0.00006770033,0.00007619824,0.000192857,0.00005035994,0.00002180878],"category_scores_gemma":[0.0004430176,0.0001125343,0.0001575925,0.0003093166,0.000238571,0.0009391449,0.00004979298,0.0002625094,0.000001476502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003410774,"about_ca_system_score_gemma":0.00007257561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002793876,"about_ca_topic_score_gemma":0.000002474379,"domain_scores_codex":[0.9979128,0.0001187127,0.0007932481,0.0001346447,0.0008659302,0.0001746262],"domain_scores_gemma":[0.9983341,0.0001760842,0.0007850428,0.00008574173,0.000344482,0.0002745321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001529919,0.0006194591,0.7299522,0.0006430516,0.0003519622,0.0001470724,0.001817542,0.000007706319,0.1208706,0.0003373608,0.00124319,0.1424799],"study_design_scores_gemma":[0.008726957,0.0003006264,0.8478953,0.0005736843,0.0001605084,0.001209291,0.001364673,0.1266845,0.01191363,0.000218337,0.0006742981,0.0002782505],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9252324,0.001461957,0.07173455,0.0005497194,0.000778252,0.0001374044,0.00004675607,0.00001362152,0.00004530784],"genre_scores_gemma":[0.9968824,0.0001809752,0.00244041,0.0002394118,0.0001823885,0.000002219807,0.00005270856,0.0000139008,0.00000556736],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1422016,"threshold_uncertainty_score":0.4589016,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2929768480","doi":"10.1117/1.jmi.6.2.021603","title":"Initial evaluation of three-dimensionally printed patient-specific coronary phantoms for CT-FFR software validation","year":2019,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Coronary Interventions and Diagnostics","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"University of California, Irvine; Canon Medical Systems USA","keywords":"Medicine; Fractional flow reserve; Imaging phantom; Pulsatile flow; Coronary artery disease; Scanner; Coronary arteries; Nuclear medicine; Biomedical engineering; Radiology; Coronary angiography; Artery; Artificial intelligence; Cardiology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.044256349212677,"gpt":0.3599811020074867,"spread":0.3157247527948097,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001633194,0.0001027855,0.0003073505,0.0001866285,0.0000328315,0.00001284413,0.0001176579,0.00004349334,0.00222544],"category_scores_gemma":[0.002013364,0.00008190252,0.000245691,0.0001029358,0.00006321108,0.0001884387,0.00005116979,0.0002485796,0.00001295319],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000119093,"about_ca_system_score_gemma":0.0004613495,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005458123,"about_ca_topic_score_gemma":0.000001906343,"domain_scores_codex":[0.9968597,0.00007575997,0.0008248118,0.0001252025,0.001968966,0.0001455914],"domain_scores_gemma":[0.9971076,0.0005096915,0.000511917,0.0001437082,0.001559878,0.0001672284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007006715,0.000798156,0.08333212,0.0001749725,0.0001659198,0.0001663236,0.0001282649,0.0001346651,0.002294506,0.0001725132,0.005397348,0.9065346],"study_design_scores_gemma":[0.06043359,0.005485598,0.5232635,0.0184912,0.002923117,0.01301496,0.002077417,0.3171365,0.02359623,0.007595995,0.02513973,0.0008422067],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9598096,0.001354144,0.03492966,0.002116454,0.001180894,0.0004836586,0.00001194103,0.00001046935,0.0001031563],"genre_scores_gemma":[0.9965666,0.00005992415,0.002778852,0.0002554152,0.000250814,0.000006895775,0.00004755155,0.00001624019,0.00001768687],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9056923,"threshold_uncertainty_score":0.9986867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2762353096","doi":"10.1117/1.jmi.4.4.041306","title":"Dimension reduction technique using a multilayered descriptor for high-precision classification of ovarian cancer tissue using optical coherence tomography: a feasibility study","year":2017,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Optical Coherence Tomography Applications","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Medicine; Optical coherence tomography; Reduction (mathematics); Dimension (graph theory); Ovarian cancer; Tomography; Radiology; Artificial intelligence; Medical physics; Cancer; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.07148382159995947,"gpt":0.3812655442851755,"spread":0.309781722685216,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001766065,0.0002006484,0.0004588741,0.0002835725,0.0002779468,0.0001104159,0.000612737,0.0001605116,0.00004063504],"category_scores_gemma":[0.0007064817,0.0001799073,0.0001434721,0.0002620863,0.0002895671,0.000563421,0.00008460046,0.0005014903,3.164489e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002170746,"about_ca_system_score_gemma":0.0001626901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002050888,"about_ca_topic_score_gemma":0.00001450867,"domain_scores_codex":[0.9975161,0.00008361309,0.0009573307,0.0002673031,0.0008981309,0.0002775206],"domain_scores_gemma":[0.9978473,0.0001410841,0.000577526,0.0005459796,0.0006105667,0.0002775623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001582062,0.0005024237,0.009528694,0.0001074122,0.00009169718,0.00001226452,0.000211041,0.001216509,0.9364625,0.0001227169,0.00004626442,0.05154024],"study_design_scores_gemma":[0.003339162,0.0003177773,0.08295967,0.001723353,0.00057941,0.0002419972,0.001180579,0.7685372,0.1388434,0.001724864,0.00003687277,0.0005157051],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.646934,0.000151132,0.3513195,0.0002298514,0.0004503987,0.0008619881,0.000008023343,0.00003316887,0.00001197286],"genre_scores_gemma":[0.9179881,0.00001830783,0.08167374,0.000004013372,0.0002247449,0.00005901414,0.000001007301,0.00003025208,7.954047e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7976191,"threshold_uncertainty_score":0.7336406,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2553903516","doi":"10.1117/1.jmi.3.4.046003","title":"Preterm neonatal lateral ventricle volume from three-dimensional ultrasound is not strongly correlated to two-dimensional ultrasound measurements","year":2016,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Neonatal and fetal brain pathology","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"London Health Sciences Centre; Western University","funders":"Canadian Institutes of Health Research; Academic Medical Organization of Southwestern Ontario","keywords":"Medicine; Ventricle; Lateral ventricles; Ultrasound; Nuclear medicine; Cerebral ventricle; Cardiology; Anatomy; Radiology","retraction":null,"screen_n_in":null,"score":{"opus":0.01890291553348997,"gpt":0.2777786952486552,"spread":0.2588757797151653,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001091241,0.0003165765,0.0006502708,0.0002323669,0.0001219776,0.00004030746,0.0003968832,0.000147889,0.004286318],"category_scores_gemma":[0.001650413,0.0002035759,0.0003009365,0.0002013226,0.0002854362,0.0003582922,0.00016501,0.0007582023,0.0003223202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002243951,"about_ca_system_score_gemma":0.000371072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008235531,"about_ca_topic_score_gemma":0.00001245469,"domain_scores_codex":[0.9949322,0.0001199758,0.000999646,0.0004361543,0.002911739,0.000600271],"domain_scores_gemma":[0.9970609,0.0007126303,0.0003728147,0.0002783263,0.0004509802,0.001124329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004051798,0.0005768223,0.4264259,0.00003560133,0.0007595084,0.009531377,0.0005341926,0.00004573157,0.4072952,0.00001765785,0.02903744,0.1216888],"study_design_scores_gemma":[0.05395924,0.001762724,0.7875555,0.006160708,0.001217807,0.07487491,0.0001329468,0.008463421,0.04518418,0.002107211,0.01688346,0.001697955],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.976824,0.0007972425,0.002820404,0.01744551,0.001681185,0.0002168207,0.0000945178,0.00003592512,0.00008443959],"genre_scores_gemma":[0.9901906,0.0000090207,0.001740503,0.006624813,0.0009454444,0.000003158112,0.00002269392,0.00004272765,0.0004210708],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.362111,"threshold_uncertainty_score":0.9966239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390607650","doi":"10.1117/1.jmi.11.1.014005","title":"Robust fiber orientation distribution function estimation using deep constrained spherical deconvolution for diffusion-weighted magnetic resonance imaging","year":2024,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Biomedical Imaging and Bioengineering; National Center for Research Resources; National Institute of General Medical Sciences; National Institutes of Health; National Science Foundation","keywords":"Human Connectome Project; Deconvolution; Diffusion MRI; Magnetic resonance imaging; Artificial intelligence; Regularization (linguistics); Tractography; Orientation (vector space); Deep learning; Computer science; Real-time MRI; Pattern recognition (psychology); Algorithm; Medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03570822091407746,"gpt":0.3462099798567345,"spread":0.3105017589426571,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006000384,0.0001618818,0.0002590986,0.0001353999,0.0001636779,0.00008407827,0.0001004971,0.00007014494,0.0002204981],"category_scores_gemma":[0.0005478573,0.000138673,0.0001637977,0.0003922517,0.0001676975,0.0004253134,0.00003298842,0.0004335677,0.000005020958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003127453,"about_ca_system_score_gemma":0.0002476627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007480447,"about_ca_topic_score_gemma":4.184454e-7,"domain_scores_codex":[0.9980551,0.00004357092,0.0006884073,0.0002704653,0.000690623,0.0002518107],"domain_scores_gemma":[0.9988333,0.0002399243,0.0002228652,0.0001390945,0.0003397429,0.0002250988],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002298797,0.0001405735,0.001397882,0.000148892,0.00001394828,0.0001220951,0.00005797914,0.0003035345,0.005819253,0.001190923,0.003490676,0.9870844],"study_design_scores_gemma":[0.001257403,0.00007500433,0.002095782,0.0009221905,0.0002582303,0.00184159,0.00008406225,0.969075,0.0003471271,0.002810496,0.02110536,0.0001277051],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01665855,0.004406929,0.9701797,0.007765028,0.0004421559,0.0003577133,0.00001329588,0.0001366391,0.00004003184],"genre_scores_gemma":[0.7636485,0.0002993392,0.2337512,0.0008806296,0.001037327,0.00004063452,0.0001930604,0.00006585166,0.00008342785],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9869567,"threshold_uncertainty_score":0.5654921,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901694925","doi":"10.1117/1.jmi.5.2.026002","title":"Development of a pulmonary imaging biomarker pipeline for phenotyping of chronic lung disease","year":2018,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Atomic and Subatomic Physics Research","field":"Physics and Astronomy","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Paul's Hospital; University of Toronto; Sunnybrook Health Science Centre; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Medicine; Magnetic resonance imaging; Radiology; Biomarker; Ventilation (architecture); Nuclear medicine; Biomedical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01846309291189233,"gpt":0.3415296468261708,"spread":0.3230665539142784,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001204075,0.0001223932,0.0003318249,0.0001393905,0.00009129859,0.00001550287,0.0003949891,0.00001694223,0.0003274417],"category_scores_gemma":[0.00007928497,0.00009984986,0.0001867341,0.0001443229,0.0002558863,0.0001957261,0.0001479602,0.0002111824,0.000002253807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000104406,"about_ca_system_score_gemma":0.001730535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001103688,"about_ca_topic_score_gemma":2.651468e-7,"domain_scores_codex":[0.997978,0.00004161999,0.000793433,0.0001338415,0.0007515997,0.0003015344],"domain_scores_gemma":[0.998544,0.0001480775,0.0004642643,0.0001335707,0.0004096318,0.0003004681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000121554,0.0001939424,0.009684581,0.0001204063,0.00009595017,0.000009451963,0.0003296389,0.000002185742,0.006889966,0.0005837823,0.001328883,0.9806396],"study_design_scores_gemma":[0.0009071906,7.959124e-7,0.0002569555,0.0005697805,0.00004424949,0.0000055064,0.0004382746,0.9913011,0.002545121,0.001637349,0.002196534,0.00009720513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0214185,0.0008480102,0.9759102,0.0009157998,0.0001984844,0.000111439,0.00000935094,0.000003839091,0.0005843471],"genre_scores_gemma":[0.9983425,0.000008527907,0.0006158193,0.00004089135,0.0009318473,0.000003954628,0.000006690052,0.00001919808,0.00003063575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9912989,"threshold_uncertainty_score":0.4071759,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4379388013","doi":"10.1117/1.jmi.10.3.034505","title":"Automated fatty liver disease detection in point-of-care ultrasound B-mode images","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Liver Disease Diagnosis and Treatment","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph; Toronto General Hospital","funders":"Mitacs","keywords":"Medicine; Fatty liver; Steatosis; Artificial intelligence; Radiology; Receiver operating characteristic; Ultrasound; Liver disease; Internal medicine; Disease; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01071872462260449,"gpt":0.3182379100767617,"spread":0.3075191854541572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003630754,0.0001129207,0.000311117,0.0003202268,0.00003278756,0.0000186919,0.0001034574,0.00004225899,0.0001736766],"category_scores_gemma":[0.0009282805,0.0000829424,0.0002006562,0.0003124661,0.00008424037,0.0001778802,0.00003670147,0.0002536598,0.00002170979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001465781,"about_ca_system_score_gemma":0.0002498401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009193098,"about_ca_topic_score_gemma":0.00001015002,"domain_scores_codex":[0.9981888,0.00007418318,0.0004546798,0.0001281235,0.000953568,0.0002006594],"domain_scores_gemma":[0.9987543,0.0002572767,0.0001792439,0.0001214189,0.000186629,0.0005011898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005621373,0.0009941817,0.839555,0.0007006184,0.000250317,0.01491539,0.001327685,0.00005277281,0.002862975,0.00001294393,0.005499487,0.1332665],"study_design_scores_gemma":[0.003178664,0.00008259495,0.973136,0.001632746,0.0003500476,0.0002309779,0.0009100716,0.01605891,0.004118347,0.00006518963,0.0001483175,0.00008813758],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912295,0.00392832,0.0002615842,0.00390525,0.0003120553,0.000166551,0.00001566783,0.00008652207,0.00009455361],"genre_scores_gemma":[0.9977545,0.001650702,0.0001007833,0.0002690137,0.0001813586,0.00000584072,0.0000141147,0.00001578513,0.000007922002],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.133581,"threshold_uncertainty_score":0.3382293,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2759305182","doi":"10.1117/1.jmi.4.3.031212","title":"Comparison of the CTDI and AAPM report No. 111 methodology in adult, adolescent, and child head phantoms for MSCT and dental CBCT scanners","year":2017,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Dental Radiography and Imaging","field":"Dentistry","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vancouver Coastal Health; University of British Columbia","funders":"University of British Columbia; American Association of Physicists in Medicine","keywords":"Imaging phantom; Medicine; Cone beam computed tomography; Nuclear medicine; Dosimetry; Task group; Dose profile; Medical physics; Multislice; Computed tomography; Radiology","retraction":null,"screen_n_in":null,"score":{"opus":0.05669146769317305,"gpt":0.419512734047842,"spread":0.3628212663546689,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001950745,0.0001355724,0.0005003526,0.0001565076,0.0002306922,0.0001188047,0.0003508966,0.00006967254,0.000009921369],"category_scores_gemma":[0.002223699,0.0000970093,0.0001387207,0.00006112267,0.0007445567,0.0003586082,0.0002069049,0.0005671376,2.876935e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002164414,"about_ca_system_score_gemma":0.00003934577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001945352,"about_ca_topic_score_gemma":0.0002166315,"domain_scores_codex":[0.9981555,0.0001546245,0.0007224744,0.000197786,0.0005331029,0.0002364577],"domain_scores_gemma":[0.9984115,0.0002211671,0.0008584282,0.0001958056,0.0001043114,0.000208764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001381462,0.00008582776,0.9632946,0.0001378668,0.00005225575,0.0003889835,0.0002094702,3.021292e-7,0.0008974505,0.00002694192,0.00115135,0.03361686],"study_design_scores_gemma":[0.003441084,0.00004953297,0.9683986,0.001788153,0.0001092004,0.01734086,0.001272958,0.004981697,0.001431252,0.000148121,0.00090516,0.0001334153],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898725,0.003963397,0.00176261,0.002609869,0.001339116,0.000139725,0.000006189972,0.000004260828,0.0003023798],"genre_scores_gemma":[0.998066,0.0002954677,0.001094337,0.000262945,0.0002460205,0.000001349737,8.629839e-7,0.000012839,0.00002015219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03348345,"threshold_uncertainty_score":0.3955924,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2594785967","doi":"10.1117/1.jmi.4.2.021104","title":"Differentiation of arterioles from venules in mouse histology images using machine learning","year":2017,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Digital Imaging for Blood Diseases","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research; Cancer Care Ontario; London Health Sciences Centre; Natural Sciences and Engineering Research Council of Canada; Heart and Stroke Foundation of Canada","keywords":"Medicine; Generalizability theory; Artificial intelligence; Digital pathology; Feature selection; Pattern recognition (psychology); Receiver operating characteristic; Segmentation; Feature (linguistics); Computer science; Pathology; Biomedical engineering; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01691633445342543,"gpt":0.2899682432812705,"spread":0.273051908827845,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004349012,0.00009880359,0.0003002842,0.000196348,0.00007761042,0.0002431527,0.001180231,0.00003274747,0.00001505477],"category_scores_gemma":[0.001382058,0.00008642177,0.000095797,0.00004415858,0.0001935123,0.001039538,0.0003303001,0.000304441,0.000001483724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000453874,"about_ca_system_score_gemma":0.0001154125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003153937,"about_ca_topic_score_gemma":0.00001425215,"domain_scores_codex":[0.9984977,0.00009025515,0.0004801857,0.0001390788,0.00061844,0.0001743049],"domain_scores_gemma":[0.9985592,0.0001178224,0.0008252292,0.0002641379,0.00009160643,0.0001419501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003178828,0.0003922689,0.7162657,0.00004886564,0.00006228046,0.0008370984,0.0005625467,0.0001123338,0.03900541,0.0006078735,0.0001178139,0.241956],"study_design_scores_gemma":[0.003002151,0.00005363472,0.2531886,0.001264637,0.00006864031,0.0003574083,0.0001119507,0.7119299,0.02146232,0.007747886,0.0004840796,0.0003288219],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9061844,0.002241166,0.08885088,0.002186963,0.0004219092,0.00002405466,0.000004775013,0.00001227428,0.00007355813],"genre_scores_gemma":[0.9930831,0.00006295399,0.0066672,0.00007265014,0.0000962078,2.77399e-7,0.000001311241,0.000008192597,0.000008169203],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7118175,"threshold_uncertainty_score":0.3524177,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138181477","doi":"10.1117/1.jmi.2.4.046501","title":"Implementation methods of medical image sharing for collaborative health care based on IHE XDS-I profile","year":2015,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Digital Radiography and Breast Imaging","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Chinese Academy of Sciences; Radiological Society of North America","keywords":"Medicine; Image sharing; Metadata; DICOM; Health care; Implementation; Data sharing; Medical record; Image (mathematics); World Wide Web; Computer science; Artificial intelligence; Radiology; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.04435797911218377,"gpt":0.476245355256247,"spread":0.4318873761440633,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005978391,0.0001694828,0.0006240576,0.0004407182,0.00006145739,0.00005759677,0.0003275874,0.00007360709,0.0001881784],"category_scores_gemma":[0.002128854,0.0001264604,0.0002478393,0.0004943658,0.0001846384,0.0003324207,0.00005968557,0.0004984701,0.000001120797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002130202,"about_ca_system_score_gemma":0.003015233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004910837,"about_ca_topic_score_gemma":0.00000537711,"domain_scores_codex":[0.9955645,0.0001840072,0.0009908414,0.0002074198,0.00270724,0.0003460248],"domain_scores_gemma":[0.9967127,0.0003751598,0.0006508399,0.0001659631,0.001037736,0.001057606],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007525926,0.000375094,0.009148143,0.0006298105,0.0001518692,0.0002919888,0.002734312,0.000005572169,0.0002229082,0.0004455017,0.02573978,0.9595025],"study_design_scores_gemma":[0.1254731,0.01247639,0.01658895,0.02697891,0.001686977,0.007950095,0.2743408,0.3800386,0.05359482,0.003506712,0.09544114,0.00192352],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03080659,0.005736304,0.7416479,0.2116778,0.001894649,0.001715926,0.0001182083,0.00008426831,0.00631828],"genre_scores_gemma":[0.8375056,0.00006864736,0.1535663,0.007608281,0.001067683,0.00002832156,0.00007863964,0.00005942326,0.00001705856],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9575789,"threshold_uncertainty_score":0.5348894,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2277068097","doi":"10.1117/1.jmi.3.1.016001","title":"Fabrication and control of CT number through polymeric composites based on coronary plaque CT phantom applications","year":2016,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Advanced X-ray and CT Imaging","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University Health Network; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University Health Network","keywords":"Imaging phantom; Fabrication; Hounsfield scale; Biomedical engineering; Medicine; Thermoplastic polyurethane; Polyvinylidene fluoride; Materials science; Composite material; Polymer; Computed tomography; Nuclear medicine; Radiology; Elastomer","retraction":null,"screen_n_in":null,"score":{"opus":0.005083402073368344,"gpt":0.2559191669791666,"spread":0.2508357649057983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002281977,0.0001126003,0.0002353303,0.00006442236,0.00004403537,0.00001202146,0.0001635176,0.00001542044,0.0001120554],"category_scores_gemma":[0.00007644622,0.0000791741,0.00005938339,0.0001077555,0.0001266934,0.0002924183,0.00001286009,0.000202097,0.00000618304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004415323,"about_ca_system_score_gemma":0.00003838264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004142008,"about_ca_topic_score_gemma":1.923699e-7,"domain_scores_codex":[0.9988864,0.00003529112,0.0003913128,0.00008976476,0.0004390253,0.0001582065],"domain_scores_gemma":[0.9990735,0.0004519895,0.0001665782,0.0001116849,0.00006731466,0.0001289521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008853169,0.000196717,0.04992527,0.0001268434,0.0001197332,0.0001620657,0.0001274987,0.001760346,0.08012197,0.0005716048,0.000968739,0.8658307],"study_design_scores_gemma":[0.01740867,0.000148207,0.02928218,0.003846164,0.0004091635,0.004611628,0.0005465192,0.7629915,0.1194386,0.00411065,0.05615926,0.001047379],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02031952,0.001474975,0.973899,0.003455353,0.0001294651,0.00008348862,0.000007640738,0.00003625458,0.0005943112],"genre_scores_gemma":[0.9960225,0.0003699263,0.002915095,0.0004869788,0.0001728131,0.000006528967,0.000001243973,0.00001887054,0.000006072545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9757029,"threshold_uncertainty_score":0.3228626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2756068656","doi":"10.1117/1.jmi.4.3.036001","title":"Ex vivo tissue imaging for radiology–pathology correlation: a pilot study with a small bore 7-T MRI in a rare pigmented ganglioglioma exhibiting complex MR signal characteristics associated with melanin and hemosiderin","year":2017,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Winnipeg; University of Manitoba; Health Sciences Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Manitoba Medical Service Foundation","keywords":"Hemosiderin; Medicine; Ex vivo; Magnetic resonance imaging; Pathology; Diffusion MRI; In vivo; Melanin; Radiology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.07248924691438242,"gpt":0.3546072313228859,"spread":0.2821179844085034,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00100944,0.0002263353,0.0006576057,0.0002467526,0.0002789416,0.00008215413,0.0002560746,0.00004501097,0.00002919693],"category_scores_gemma":[0.000788247,0.0001718281,0.00003519416,0.0001431857,0.0003554629,0.0001846126,0.0001088215,0.0006735388,2.558518e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009138705,"about_ca_system_score_gemma":0.0001483886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002703012,"about_ca_topic_score_gemma":0.00004012988,"domain_scores_codex":[0.9981353,0.0001034641,0.0006572218,0.0003182389,0.0004372205,0.0003485152],"domain_scores_gemma":[0.9978711,0.0003367781,0.0009654569,0.0002604992,0.0003206221,0.0002455378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001700706,0.001371215,0.9384902,0.0001023855,0.0001160589,0.01457855,0.0007577222,0.00001161493,0.01779778,0.0000875643,0.001234111,0.02375211],"study_design_scores_gemma":[0.03207563,0.006596495,0.8144746,0.004788369,0.0007204427,0.04015515,0.00290877,0.09431662,0.001317316,0.0005139825,0.001383671,0.0007489811],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7446953,0.0001243045,0.2376088,0.01652156,0.00004846361,0.0008650825,0.00001586239,0.00005669165,0.00006389376],"genre_scores_gemma":[0.9824569,0.00003574463,0.01646212,0.0007531245,0.0001716361,0.00003984481,0.0000173098,0.0000452266,0.00001809028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2377616,"threshold_uncertainty_score":0.7006945,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3154339073","doi":"10.1117/1.jmi.8.2.024502","title":"Early diagnosis of Alzheimer’s disease on ADNI data using novel longitudinal score based on functional principal component analysis","year":2021,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Institute on Aging; National Institutes of Health","keywords":"Medicine; Longitudinal study; Magnetic resonance imaging; Receiver operating characteristic; Disease; Principal component analysis; Lasso (programming language); Population; Internal medicine; Artificial intelligence; Pathology; Radiology","retraction":null,"screen_n_in":null,"score":{"opus":0.1516749171060258,"gpt":0.4007444366858758,"spread":0.24906951957985,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001544259,0.0001575804,0.0005053476,0.0005640498,0.00008292512,0.00004698261,0.0002742146,0.00003664804,0.002492365],"category_scores_gemma":[0.0014353,0.0001219298,0.0003510847,0.0006212552,0.0001727482,0.0001744724,0.0002128056,0.0006094089,0.000005097369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008791406,"about_ca_system_score_gemma":0.001127586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003318477,"about_ca_topic_score_gemma":0.000003268696,"domain_scores_codex":[0.9946972,0.0001396811,0.0006658491,0.0003181229,0.003889007,0.0002901538],"domain_scores_gemma":[0.9974601,0.0003569354,0.000314035,0.0004139011,0.0006515821,0.0008033935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008987508,0.002710497,0.9812082,0.00006393342,0.001513512,0.003001858,0.00001401883,0.0003845379,0.0004680667,0.00002681019,0.0004925718,0.009217233],"study_design_scores_gemma":[0.003060024,0.0001519174,0.8350813,0.00107297,0.003621961,0.0001073006,0.00006295398,0.1557955,0.0007110395,0.000005926761,0.0002400827,0.00008905045],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9541876,0.0006300299,0.03499407,0.009626525,0.0002381244,0.0001218446,0.00005586717,0.000006739401,0.0001391792],"genre_scores_gemma":[0.9973146,0.00006591761,0.0009583342,0.001118472,0.0003989727,0.00000293049,0.000112369,0.00001503783,0.00001338191],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1554109,"threshold_uncertainty_score":0.9984195,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W784778127","doi":"10.1117/1.jmi.2.2.025002","title":"Three-dimensional nonrigid landmark-based magnetic resonance to transrectal ultrasound registration for image-guided prostate biopsy","year":2015,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Magnetic resonance imaging; Landmark; Ultrasound; Radiology; Image registration; Prostate; Biopsy; Prostate biopsy; Artificial intelligence; Image (mathematics); Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02830324013679844,"gpt":0.3241517898381175,"spread":0.295848549701319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00133839,0.0001721325,0.0003889143,0.0001337052,0.00005509676,0.00005487705,0.0001291699,0.00006030294,0.00009535733],"category_scores_gemma":[0.001101616,0.0001264544,0.0001666128,0.0001694013,0.00011123,0.0001492004,0.00001200908,0.000249184,0.000007899333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002364441,"about_ca_system_score_gemma":0.001148817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006286361,"about_ca_topic_score_gemma":0.00002683603,"domain_scores_codex":[0.9975167,0.00003552309,0.0006390566,0.0002218148,0.001275691,0.0003112499],"domain_scores_gemma":[0.9979327,0.0002583918,0.0002055329,0.000155176,0.0006345917,0.000813633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.008893517,0.002499269,0.1235459,0.0005165172,0.0002370574,0.007369612,0.00107365,0.0001624756,0.01934663,0.0001587811,0.442545,0.3936517],"study_design_scores_gemma":[0.1740074,0.01731739,0.1772813,0.01694134,0.002848214,0.04521956,0.0009480979,0.1259423,0.0657674,0.006375907,0.3647837,0.002567382],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7605585,0.01448837,0.06399769,0.1567938,0.001540497,0.001940775,0.0001084693,0.00006632641,0.0005056552],"genre_scores_gemma":[0.9370611,0.0001828295,0.05552299,0.005602929,0.001250066,0.0001103418,0.00006786999,0.00006739491,0.0001344869],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3910843,"threshold_uncertainty_score":0.5156661,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1492342382","doi":"10.1117/1.jmi.2.3.034002","title":"Hole filling with oriented sticks in ultrasound volume reconstruction","year":2015,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"National Center for Research Resources; National Institute of Mental Health","keywords":"Interpolation (computer graphics); Medicine; Voxel; Artificial intelligence; Computer vision; Ultrasound; Volume (thermodynamics); Iterative reconstruction; Fidelity; Image (mathematics); Radiology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01076078763955575,"gpt":0.289932921175335,"spread":0.2791721335357792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002583564,0.0001290815,0.0004114838,0.0003042184,0.00003669907,0.00003896852,0.0001497999,0.00007329939,0.0002063138],"category_scores_gemma":[0.005146834,0.00008989823,0.00007040306,0.000313734,0.000233182,0.0002343032,0.00002075432,0.001423141,0.000007408152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001741032,"about_ca_system_score_gemma":0.0006160607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000705835,"about_ca_topic_score_gemma":0.000004235135,"domain_scores_codex":[0.9974201,0.00009285942,0.000614808,0.0001539839,0.001433298,0.0002848896],"domain_scores_gemma":[0.9983566,0.0001686276,0.000292192,0.0001225309,0.0002998799,0.000760164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004209207,0.0002406613,0.6064172,0.00007176164,0.00009265012,0.004136839,0.001132426,0.0006331141,0.0008716676,0.00007246093,0.007781897,0.3781283],"study_design_scores_gemma":[0.02724847,0.0007447288,0.05549344,0.008582376,0.0004421273,0.09657174,0.009696888,0.7304361,0.0004084575,0.0007205167,0.06902247,0.0006326602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8771998,0.0009736273,0.09832117,0.02037549,0.001092036,0.0001048655,5.569316e-7,0.00002899664,0.001903403],"genre_scores_gemma":[0.9878396,0.0001312347,0.009810802,0.001230271,0.000830941,0.000001164404,0.000003493686,0.00002623798,0.0001261929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.729803,"threshold_uncertainty_score":0.6182916,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392388989","doi":"10.1117/1.jmi.11.2.026001","title":"Machine learning based prediction of image quality in prostate MRI using rapid localizer images","year":2024,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Vale (Canada); University of Calgary; University of Guelph","funders":"Mitacs; Compute Canada; University of Toronto; Johns Hopkins University","keywords":"Medicine; Artificial intelligence; Image quality; Receiver operating characteristic; Magnetic resonance imaging; Effective diffusion coefficient; Sagittal plane; Prostate; Diffusion MRI; Segmentation; Pattern recognition (psychology); Nuclear medicine; Radiology; Computer science; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02423448289816226,"gpt":0.3527592443479683,"spread":0.3285247614498061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002556247,0.0001489616,0.0004910121,0.0003483487,0.00003215081,0.00004365271,0.00008515722,0.00004944867,0.0003674957],"category_scores_gemma":[0.0005702368,0.0001062901,0.0001942605,0.0003078571,0.0001595055,0.0002754707,0.00003708345,0.0007596212,0.000002068923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002962282,"about_ca_system_score_gemma":0.0005889055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001956698,"about_ca_topic_score_gemma":0.000002512371,"domain_scores_codex":[0.9973401,0.0001899898,0.0009638015,0.0001851571,0.001085939,0.0002349419],"domain_scores_gemma":[0.9989318,0.0002458439,0.0002755218,0.0001087108,0.0001913585,0.0002467446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001005283,0.001347332,0.5592011,0.002755489,0.0004790641,0.01090793,0.001265726,0.001204983,0.02676665,0.0000539028,0.003137603,0.391875],"study_design_scores_gemma":[0.01055571,0.0006028065,0.04834351,0.01523938,0.0005632883,0.001438795,0.0006479943,0.8820911,0.0286713,0.0002127138,0.01138574,0.0002476361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7235795,0.1003883,0.1102827,0.06173181,0.002060511,0.0009082041,0.000130614,0.0001371221,0.0007812706],"genre_scores_gemma":[0.9940051,0.0031614,0.002193418,0.0003369609,0.0002347878,0.000004552727,0.00001448402,0.00002818898,0.00002112722],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8808861,"threshold_uncertainty_score":0.4334386,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385235400","doi":"10.1117/1.jmi.10.4.044004","title":"Automatic classification of symmetry of hemithoraces in canine and feline radiographs","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; University of Guelph","funders":"","keywords":"Medicine; Radiography; Thorax (insect anatomy); Artificial intelligence; Segmentation; Convolutional neural network; Pattern recognition (psychology); Radiology; Classifier (UML); Nuclear medicine; Anatomy; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02846764124882535,"gpt":0.3727024270726368,"spread":0.3442347858238115,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002356819,0.00007876149,0.0004585604,0.0009206298,0.00001311934,0.000006692441,0.0001192474,0.00005941169,0.0000541804],"category_scores_gemma":[0.003497391,0.00006218625,0.00008199948,0.00098711,0.0001752366,0.00008443832,0.00004114771,0.0003295674,7.454879e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005394925,"about_ca_system_score_gemma":0.000277548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001050364,"about_ca_topic_score_gemma":0.000009415818,"domain_scores_codex":[0.9979146,0.00007152044,0.0008323422,0.00009742039,0.0009479456,0.0001362114],"domain_scores_gemma":[0.9983533,0.0007074573,0.0004673279,0.0001193512,0.0001709101,0.0001816733],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000707143,0.0003646637,0.6256307,0.001459009,0.0001046687,0.0005062895,0.0008300017,0.00001596959,0.03037417,0.00005780554,0.016627,0.3239591],"study_design_scores_gemma":[0.00339639,0.0001214654,0.7301097,0.006592083,0.0002241085,0.0005665079,0.001350492,0.2521516,0.004010738,0.0002203632,0.001154291,0.0001023049],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9131095,0.001858788,0.0002738859,0.08451706,0.0001386481,0.00006916014,0.000001278895,0.00001539343,0.00001627686],"genre_scores_gemma":[0.9968511,0.001145341,0.0008579351,0.001002014,0.0001220449,0.000001202578,0.000002054596,0.00001201746,0.000006253716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3238567,"threshold_uncertainty_score":0.4186956,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2175570168","doi":"10.1117/1.jmi.2.4.043502","title":"Model predictions for the wide-angle x-ray scatter signals of healthy and malignant breast duct biopsies","year":2015,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Laurentian University","funders":"Compute Canada","keywords":"Medicine; Biopsy; Ductal carcinoma; Radiology; Breast tissue; Mammography; X-ray; Nuclear medicine; Pathology; Breast cancer; Optics; Cancer; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03038494459664787,"gpt":0.3616494652150114,"spread":0.3312645206183635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001482632,0.00008360948,0.0001704374,0.00004959465,0.00005251042,0.00001769018,0.0003351701,0.00009331173,0.00002055182],"category_scores_gemma":[0.0009749332,0.00004786597,0.00009204684,0.0000716231,0.0004995395,0.000007928763,0.0001441168,0.0002226235,2.309833e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001907979,"about_ca_system_score_gemma":0.0003177181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008300518,"about_ca_topic_score_gemma":7.421651e-7,"domain_scores_codex":[0.99857,0.00003732167,0.0003693486,0.0001246791,0.0006852872,0.0002133964],"domain_scores_gemma":[0.9989474,0.0001308668,0.0001457771,0.0001363201,0.0002899767,0.0003496875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009793269,0.0004520222,0.004225912,0.0001767542,0.000250705,0.00002336408,0.0001951853,0.0001126756,0.5875806,0.0002355051,0.3750979,0.03067009],"study_design_scores_gemma":[0.007534544,0.00233339,0.001305004,0.00113251,0.0003531885,0.003416151,0.001810163,0.3714657,0.4784126,0.0159682,0.1155725,0.0006959645],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1487107,0.009613382,0.7380251,0.1027219,0.0003008668,0.0002773155,0.00005506157,0.00001177251,0.0002839361],"genre_scores_gemma":[0.9923412,0.001249722,0.004032218,0.001697442,0.0005043443,0.00001253689,0.000005694577,0.00001335682,0.0001434544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8436306,"threshold_uncertainty_score":0.1951918,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3015288507","doi":"10.1117/1.jmi.7.2.026002","title":"Detectability of fluorescent gold nanoparticles under micro-CT and optical projection tomography imaging","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Photoacoustic and Ultrasonic Imaging","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autofluorescence; Medicine; Colloidal gold; Preclinical imaging; Tomography; Histology; Biomedical engineering; In vivo; Pathology; Melanoma; Nuclear medicine; Microscopy; Gold standard (test); Fluorescence; Radiology; Nanoparticle; Materials science; Optics; Cancer research; Nanotechnology","retraction":null,"screen_n_in":null,"score":{"opus":0.008090612711843883,"gpt":0.2295080581712676,"spread":0.2214174454594237,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006964204,0.0001485144,0.0003146054,0.0001089475,0.00003392857,0.00004522099,0.0001884923,0.00002292461,0.00003496571],"category_scores_gemma":[0.0003978142,0.0001258445,0.0001180157,0.0002337775,0.0002236984,0.0002506673,0.00005517104,0.0005263529,9.274527e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005080326,"about_ca_system_score_gemma":0.00007619616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001106217,"about_ca_topic_score_gemma":7.685263e-7,"domain_scores_codex":[0.9982919,0.00004440292,0.0006033592,0.0001414828,0.0006346548,0.0002842483],"domain_scores_gemma":[0.9991742,0.0001641424,0.0001111372,0.00008608402,0.000089213,0.000375232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005339215,0.00009726629,0.03118153,0.00044786,0.0001123446,0.0002821973,0.0007458461,0.0005580542,0.8274573,0.00004697578,0.001266092,0.1377511],"study_design_scores_gemma":[0.001794418,0.00004280234,0.00925827,0.0005475282,0.0001841371,0.002042683,0.002166443,0.645293,0.3375857,0.0002760844,0.0005016635,0.0003072377],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9369029,0.003235846,0.05567239,0.003596201,0.0003260039,0.00008999566,0.000002324957,0.0000635361,0.0001108475],"genre_scores_gemma":[0.9970248,0.0001983351,0.002210057,0.0003598239,0.0001837486,0.00000117221,3.263086e-7,0.00002138726,3.986615e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.644735,"threshold_uncertainty_score":0.5131792,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410960143","doi":"10.1117/1.jmi.12.3.034504","title":"Highly efficient homomorphic encryption-based federated learning for diabetic retinopathy classification","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Homomorphic encryption; Diabetic retinopathy; Encryption; Artificial intelligence; Diabetes mellitus; Computer network; Endocrinology","retraction":null,"screen_n_in":null,"score":{"opus":0.01373181572753159,"gpt":0.3099355534349046,"spread":0.2962037377073731,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002172317,0.0001372272,0.0004395175,0.0004734123,0.0002014532,0.00009268898,0.0001540367,0.00007728626,0.00006455906],"category_scores_gemma":[0.00378808,0.0001061383,0.0002826482,0.0004876207,0.0001395215,0.00004852863,0.00001864977,0.0006959634,0.000007700057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001392874,"about_ca_system_score_gemma":0.0006042208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008136214,"about_ca_topic_score_gemma":2.867922e-7,"domain_scores_codex":[0.9977437,0.000146104,0.0007344264,0.0001894518,0.0009320346,0.0002543059],"domain_scores_gemma":[0.9980329,0.0004819418,0.0003949932,0.0001201058,0.0007132527,0.0002568507],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001320296,0.001805483,0.2411474,0.001502658,0.0007322278,0.0009530905,0.0004816708,0.004537794,0.1287669,0.000809522,0.01862065,0.5993223],"study_design_scores_gemma":[0.002988191,0.00008951507,0.009866917,0.002025526,0.0005576214,0.0001131705,0.0004945716,0.9761614,0.00278395,0.00008614047,0.004722506,0.0001105287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4690866,0.001341533,0.4293432,0.09896127,0.0005297289,0.0001805727,6.38115e-7,0.00007625561,0.0004801564],"genre_scores_gemma":[0.9965302,0.00006047948,0.001292527,0.001569286,0.0002679066,0.000007382945,0.000009015112,0.0000199267,0.0002433075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9716235,"threshold_uncertainty_score":0.4534959,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407992683","doi":"10.1117/1.jmi.12.2.026001","title":"Identifying texture features from structural magnetic resonance imaging scans associated with Tourette’s syndrome using machine learning","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Obsessive-Compulsive Spectrum Disorders","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Medicine; Magnetic resonance imaging; Texture (cosmology); Tourette syndrome; Neuroimaging; Nuclear magnetic resonance; Radiology; Artificial intelligence; Nuclear medicine; Image (mathematics); Psychiatry","retraction":null,"screen_n_in":null,"score":{"opus":0.007563108544009804,"gpt":0.3045204565898584,"spread":0.2969573480458486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008212499,0.0003695416,0.0006985297,0.0005040796,0.0003527358,0.0002427201,0.0008212231,0.0001616522,0.001871597],"category_scores_gemma":[0.001091539,0.0002980682,0.0002061426,0.0007055444,0.0003475347,0.0003889955,0.0001702575,0.002738068,0.000005830734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002980752,"about_ca_system_score_gemma":0.000275157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001130936,"about_ca_topic_score_gemma":0.0002184815,"domain_scores_codex":[0.9961281,0.0005372863,0.0007872055,0.0004454473,0.00141343,0.0006885444],"domain_scores_gemma":[0.9979671,0.0005274727,0.0007475822,0.0002601476,0.0002296395,0.0002680105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002388852,0.0001086149,0.8605005,0.00003187291,0.0004004827,0.009509854,0.002195089,0.0002173695,0.00100563,0.0003088693,0.002883886,0.1225989],"study_design_scores_gemma":[0.00582292,0.00006965362,0.9326066,0.003748298,0.000472267,0.003576358,0.003879081,0.04631666,0.00005320311,0.002105317,0.0008236524,0.0005259292],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8849753,0.08886418,0.009864336,0.01221485,0.002676415,0.0001895133,0.00001965899,0.00009516823,0.001100608],"genre_scores_gemma":[0.9968055,0.00005010411,0.0008769646,0.00151927,0.0002688537,0.000001917159,0.00001286893,0.0000582889,0.0004062047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.122073,"threshold_uncertainty_score":0.9999471,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4380046642","doi":"10.1117/1.jmi.10.3.034003","title":"Automatic measurement of kidney dimensions in two-dimensional ultrasonography is comparable to expert sonographers","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Pediatric Urology and Nephrology Studies","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; University of British Columbia","funders":"Kidney Foundation of Canada","keywords":"Medicine; Ultrasonography; Radiology; Medical physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03154680535333353,"gpt":0.3431633781709748,"spread":0.3116165728176413,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002515119,0.0001433555,0.0006090562,0.0009319342,0.00007262261,0.000003940305,0.0001738927,0.00006862236,0.0002957432],"category_scores_gemma":[0.001780014,0.0001084109,0.0002155788,0.0009958353,0.0002485093,0.00007082442,0.00007716002,0.0005309797,0.00001864583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004201152,"about_ca_system_score_gemma":0.0004996457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004247495,"about_ca_topic_score_gemma":0.000007328966,"domain_scores_codex":[0.9971445,0.0001170559,0.0007685723,0.0001608755,0.001442935,0.0003660932],"domain_scores_gemma":[0.9983768,0.0002960923,0.0002227859,0.0001400543,0.0002577742,0.0007064887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002822781,0.000503714,0.360958,0.00005143694,0.0007469575,0.0008249503,0.001980019,0.00007266381,0.006873105,0.00001146096,0.6206039,0.007091587],"study_design_scores_gemma":[0.03681818,0.001549765,0.8136034,0.004613441,0.002005479,0.00387976,0.005999883,0.0879183,0.005710942,0.001200641,0.03564555,0.001054671],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9070246,0.003109598,0.0001258771,0.08892058,0.0005067812,0.0001337964,0.000002002773,0.00003074889,0.0001460634],"genre_scores_gemma":[0.9762422,0.0004941336,0.001209949,0.02183791,0.0001884019,0.000006949629,0.000001413957,0.00001214055,0.000006914774],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5849583,"threshold_uncertainty_score":0.4420869,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400454076","doi":"10.1117/1.jmi.11.4.044002","title":"Projected pooling loss for red nucleus segmentation with soft topology constraints","year":2024,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Montreal Neurological Institute and Hospital","funders":"Chinese Government Scholarship; Assistance publique-Hôpitaux de Paris; Agence Nationale de la Recherche; Association France Parkinson; European Commission; China Scholarship Council; EU Joint Programme – Neurodegenerative Disease Research; Biogen; Yale University","keywords":"Medicine; Pooling; Segmentation; Topology (electrical circuits); Nucleus; Artificial intelligence; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.01518282694581315,"gpt":0.3083966653326332,"spread":0.2932138383868201,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00105874,0.00008659382,0.0002158107,0.0003429594,0.00006709046,0.0001997444,0.0005800975,0.00004856293,0.0001975309],"category_scores_gemma":[0.0006764191,0.00005246645,0.00009742232,0.0007420763,0.0001990287,0.0004735022,0.00008963807,0.0002791006,0.00000484591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004218021,"about_ca_system_score_gemma":0.000228078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001019391,"about_ca_topic_score_gemma":0.000001678182,"domain_scores_codex":[0.9984868,0.00005552871,0.000386788,0.000189991,0.0006586181,0.0002222462],"domain_scores_gemma":[0.9989917,0.0004218719,0.0001465134,0.0001053959,0.0001591235,0.0001753884],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002456528,0.00006216165,0.0007957108,0.00004068005,0.0001528515,0.001293941,0.0002544512,0.00002607029,0.000272605,0.007106118,0.003913064,0.9860578],"study_design_scores_gemma":[0.003622977,0.0005757426,0.001408852,0.0008510546,0.0003807634,0.01093907,0.001251212,0.9147089,0.001104876,0.01909744,0.04552434,0.0005347942],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006068367,0.0004833309,0.9611319,0.03164645,0.000459751,0.000062895,0.000004165536,0.00004599617,0.00009716832],"genre_scores_gemma":[0.9397969,0.00007793158,0.05868536,0.001009135,0.0003622243,0.00000340805,0.000004552232,0.000006692141,0.00005385632],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.985523,"threshold_uncertainty_score":0.2162825,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2562549310","doi":"10.1117/1.jmi.3.4.044005","title":"Shape complexes: the intersection of label orderings and star convexity constraints in continuous max-flow medical image segmentation","year":2016,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Segmentation; Convexity; Geodesic; Image warping; Artificial intelligence; Image segmentation; Topology (electrical circuits); Computer vision; Computer science; Mathematics; Algorithm; Combinatorics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01509246697781281,"gpt":0.3053388576886157,"spread":0.2902463907108029,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003924637,0.0001293439,0.0003306118,0.000162988,0.00004804603,0.00007316344,0.0008061022,0.00007839486,0.0007600478],"category_scores_gemma":[0.002405452,0.00007412482,0.00005519979,0.0002175789,0.001195653,0.0008034721,0.0002633207,0.0004555759,0.000002926984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009706347,"about_ca_system_score_gemma":0.000287214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004462212,"about_ca_topic_score_gemma":0.00001174467,"domain_scores_codex":[0.9965193,0.0003022294,0.000942194,0.0001922767,0.001815002,0.0002289542],"domain_scores_gemma":[0.9980279,0.000717625,0.0005271253,0.0001609791,0.0002589383,0.0003073901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002223654,0.0001052129,0.002261308,0.00003774064,0.00002345208,0.0002176038,0.0009354332,5.373619e-8,0.02402055,0.0004451414,0.001347632,0.9705836],"study_design_scores_gemma":[0.02930968,0.0009468825,0.03048085,0.01031434,0.000121984,0.009167102,0.008850281,0.7434289,0.1465078,0.01877386,0.000968247,0.001130007],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08137193,0.0001326232,0.8987439,0.01921335,0.0002990382,0.00013036,0.000002170998,0.00003017722,0.0000764236],"genre_scores_gemma":[0.8955202,0.0003553331,0.1012948,0.002672262,0.0001288285,0.000005970669,8.732221e-7,0.00001225465,0.000009479682],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9694536,"threshold_uncertainty_score":0.832199,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388660673","doi":"10.1117/1.jmi.10.6.066001","title":"Automated aortic segmentation and quantification of hemodynamic parameters from 4D flow MRI using deep learning techniques","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; University of Guelph","funders":"Siemens Healthineers","keywords":"Medicine; Hemodynamics; Segmentation; Bicuspid aortic valve; Magnetic resonance imaging; Hausdorff distance; Aortic valve; Artificial intelligence; Ground truth; Cardiology; Radiology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01691461368463151,"gpt":0.3781518188137209,"spread":0.3612372051290894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004105606,0.0000794673,0.0002636792,0.0001945894,0.00005086077,0.00002676542,0.00004069825,0.00004176409,0.00002183792],"category_scores_gemma":[0.0003109748,0.00006487405,0.0002041173,0.0001863574,0.0000743637,0.0001162008,0.00002395996,0.0001673146,0.000001409964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007292855,"about_ca_system_score_gemma":0.00008351817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009548242,"about_ca_topic_score_gemma":4.734212e-7,"domain_scores_codex":[0.9987093,0.0000676011,0.0004000929,0.0001025026,0.0006058645,0.0001146226],"domain_scores_gemma":[0.9992573,0.0001216629,0.0002812165,0.00007021243,0.0001058603,0.0001638022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001802625,0.0001784677,0.4939509,0.0001731408,0.0008229478,0.0002841097,0.0005710291,0.001085016,0.06195973,0.000004836682,0.00009901663,0.4406905],"study_design_scores_gemma":[0.0009184553,0.00003477584,0.1341599,0.0005561502,0.0005948411,0.00007263011,0.0006929165,0.8595163,0.003336389,0.00006317445,0.00000493416,0.00004959881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9566543,0.0005729062,0.04189362,0.000575628,0.0001233022,0.00009444688,0.000003255016,0.00007706595,0.000005463918],"genre_scores_gemma":[0.9885281,0.0004578494,0.0108402,0.00005937062,0.00005579327,0.000001595375,0.00004134328,0.00001388583,0.000001869776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8584312,"threshold_uncertainty_score":0.2645487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4396894282","doi":"10.1117/1.jmi.11.3.036001","title":"Open-source graphical user interface for the creation of synthetic skeletons for medical image analysis","year":2024,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Anatomy and Medical Technology","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"NHLBI Division of Intramural Research; National Heart, Lung, and Blood Institute; National Center for Advancing Translational Sciences; Additional Ventures; National Institute on Aging; National Institutes of Health; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Children's Hospital of Philadelphia","keywords":"Medicine; Open source; Graphical user interface; Interface (matter); Image (mathematics); Computer graphics (images); Computer vision; Software; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.007015937136375504,"gpt":0.3146355252275641,"spread":0.3076195880911886,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002770444,0.0001235889,0.0004398113,0.00034277,0.00005912278,0.00006826578,0.001043915,0.0001917404,0.0003974777],"category_scores_gemma":[0.003233008,0.00007639519,0.0004063919,0.000557312,0.0004013879,0.0001672251,0.0001331868,0.0007387415,0.000001781737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004148652,"about_ca_system_score_gemma":0.0001540151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001073791,"about_ca_topic_score_gemma":0.00001059217,"domain_scores_codex":[0.9980453,0.0000410687,0.0007011369,0.000137896,0.000823686,0.0002508765],"domain_scores_gemma":[0.9972878,0.00206413,0.00009236999,0.000168767,0.0001216703,0.0002653372],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007266741,0.0001268684,0.0002117975,0.0004849821,0.002760924,0.0001102988,0.0004016333,0.0004132656,0.0004916199,0.01298806,0.04485704,0.9370809],"study_design_scores_gemma":[0.0005716634,0.00003808254,0.00004294099,0.0004942666,0.0008982244,0.0001710608,0.0003592417,0.7331721,0.0008908047,0.001867247,0.2614082,0.00008620558],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003979621,0.005913845,0.9477761,0.04137121,0.0005413421,0.0001826639,0.000006718777,0.00006671844,0.0001618005],"genre_scores_gemma":[0.9945965,0.001742702,0.002905141,0.0002926601,0.000330781,0.00002885191,0.000002742464,0.00003389133,0.00006672137],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9906169,"threshold_uncertainty_score":0.4352102,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2580932265","doi":"10.1117/1.jmi.4.1.014001","title":"Deformable image registration for tissues with large displacements","year":2017,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; Hospital for Sick Children","keywords":"Medicine; Image registration; Computer vision; Artificial intelligence; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01604647998131307,"gpt":0.3625156567639504,"spread":0.3464691767826373,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002278525,0.00009538332,0.0001862346,0.0000793904,0.0003027658,0.000582942,0.001451162,0.00003699205,0.00006356282],"category_scores_gemma":[0.001101423,0.00006497674,0.00005875426,0.00004329531,0.0001347957,0.002622166,0.0001628357,0.0002280644,0.000004137141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004542103,"about_ca_system_score_gemma":0.0001879758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001254415,"about_ca_topic_score_gemma":0.00000496034,"domain_scores_codex":[0.9978284,0.00003594618,0.000428115,0.0001380788,0.001321394,0.0002480658],"domain_scores_gemma":[0.9982384,0.00007896162,0.0007596025,0.000367781,0.000284029,0.0002712098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001151167,0.0003805187,0.004776379,0.0001892267,0.0001039673,0.0008309144,0.0009112983,0.000001564302,0.003786199,0.006682388,0.1116788,0.8705437],"study_design_scores_gemma":[0.01878499,0.001012877,0.005282316,0.003411321,0.0001766574,0.002835759,0.0009129812,0.7169039,0.1516889,0.01333128,0.08459923,0.001059837],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000635947,0.00009062127,0.9838641,0.01421786,0.0002849442,0.0001257425,0.000001283747,0.0000330143,0.0007465041],"genre_scores_gemma":[0.2249965,0.0001707027,0.7715139,0.002199469,0.0005647077,0.00001798641,0.000004109389,0.00002058753,0.0005119542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8694838,"threshold_uncertainty_score":0.5621323,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4321097043","doi":"10.1117/1.jmi.10.1.016002","title":"In vivo measurements of lung function using respiratory-gated micro-computed tomography in a smoke-exposure model of chronic obstructive pulmonary disease","year":2023,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Chronic Obstructive Pulmonary Disease (COPD) Research","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Paul's Hospital; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; British Columbia Lung Association","keywords":"Medicine; Air trapping; Expiration; Lung; Lung volumes; Functional residual capacity; Respiratory system; Pulmonary function testing; COPD; Parenchyma; Respiratory disease; In vivo; Nuclear medicine; Pathology; Radiology; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.03998631834507434,"gpt":0.3274924866775676,"spread":0.2875061683324933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002028396,0.0002449978,0.0007421908,0.002063067,0.00004401326,0.0000121643,0.0003376344,0.0001321546,0.000155619],"category_scores_gemma":[0.0006154681,0.0002268828,0.0003141201,0.002104237,0.0003672406,0.0004273378,0.0001773368,0.0009319563,8.356347e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009355589,"about_ca_system_score_gemma":0.002328259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001053512,"about_ca_topic_score_gemma":0.000009084896,"domain_scores_codex":[0.9947063,0.000305613,0.001392725,0.0003397197,0.002724875,0.000530762],"domain_scores_gemma":[0.9977394,0.0001292822,0.0005749237,0.0003030903,0.0006474752,0.0006058399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00209723,0.0009277244,0.8111969,0.001912604,0.0002552426,0.002645133,0.0002531519,0.006799747,0.1604459,0.00001523223,0.0002455777,0.01320554],"study_design_scores_gemma":[0.004141256,0.00005536852,0.4257722,0.002829209,0.0002094289,0.0000847661,0.0002568907,0.5627138,0.003384834,0.0003849999,0.00001855451,0.0001486288],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9906356,0.006155247,0.001681362,0.0006747542,0.0003392209,0.0004106724,0.00002474119,0.00001803197,0.00006042257],"genre_scores_gemma":[0.9992913,0.000068078,0.0002144059,0.0001197246,0.0002439153,0.000005119542,0.000006620733,0.00004234542,0.000008469006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.555914,"threshold_uncertainty_score":0.9252012,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402687642","doi":"10.1117/1.jmi.11.5.054502","title":"HarmonyTM: multi-center data harmonization applied to distributed learning for Parkinson’s disease classification","year":2024,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Hotchkiss Brain Institute; Women and Children’s Health Research Institute; University of Alberta; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Parkinson Association of Alberta; Alzheimer's Disease Neuroimaging Initiative; Institut de Valorisation des Données; Canada Research Chairs; Parkinson Vereniging; Consortium canadien en neurodégénérescence associée au vieillissement","keywords":"Medicine; Harmonization; Center (category theory); Parkinson's disease; Disease; Artificial intelligence; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.06497534120814781,"gpt":0.3572609854352498,"spread":0.292285644227102,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007366741,0.0001513801,0.0002603002,0.0001945279,0.00009274416,0.0001249864,0.000264263,0.00004948456,0.0001083012],"category_scores_gemma":[0.0008965348,0.0001162114,0.0001106759,0.0002118768,0.00002953086,0.0002260094,0.0001017792,0.0003177623,0.00003579795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001631543,"about_ca_system_score_gemma":0.0003835904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002186961,"about_ca_topic_score_gemma":4.960983e-7,"domain_scores_codex":[0.9980772,0.00003969075,0.0004558264,0.0003305374,0.0008545793,0.0002421748],"domain_scores_gemma":[0.9984508,0.00009261208,0.00013901,0.0002424406,0.0001591957,0.0009159829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001888912,0.002825649,0.06080938,0.0009109896,0.0008531671,0.002738363,0.0004317084,0.0000774508,0.004859715,0.0005119749,0.07282308,0.8512696],"study_design_scores_gemma":[0.004449585,0.00004233647,0.03054317,0.0008934952,0.0005755271,0.0001143361,0.0002177106,0.5443946,0.0001356204,0.00007270565,0.4184277,0.000133213],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02173544,0.002153433,0.951978,0.02273623,0.0006953888,0.0004463239,0.0001575679,0.00006768225,0.00003000166],"genre_scores_gemma":[0.9928928,0.0003004324,0.004432774,0.0008584521,0.0005899042,0.00002536945,0.0007890876,0.00003823149,0.00007294332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9711574,"threshold_uncertainty_score":0.4738962,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1849982166","doi":"10.1117/1.jmi.3.1.011004","title":"Consistency of visual assessments of mammographic breast density from vendor-specific “for presentation” images","year":2015,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Digital Radiography and Breast Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Nova Scotia Health Authority; Dalhousie University","funders":"","keywords":"Medicine; Mammography; Confidence interval; Presentation (obstetrics); Medical physics; Breast cancer; Consistency (knowledge bases); Visual inspection; Vendor; Breast imaging; Radiology; Nuclear medicine; Artificial intelligence; Cancer","retraction":null,"screen_n_in":null,"score":{"opus":0.02717679340584257,"gpt":0.3525493570773175,"spread":0.325372563671475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001068072,0.0001400643,0.0005951575,0.0004070613,0.00002804791,0.00003141844,0.0002092458,0.00005438799,0.00005290471],"category_scores_gemma":[0.0004082972,0.0001116172,0.0003789846,0.0003246344,0.0004370826,0.000402613,0.00005224088,0.0002978714,8.522714e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003227854,"about_ca_system_score_gemma":0.0004079145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006850262,"about_ca_topic_score_gemma":8.617401e-7,"domain_scores_codex":[0.9970924,0.00007103493,0.000900948,0.0001493186,0.001574878,0.0002114214],"domain_scores_gemma":[0.9973959,0.0003096931,0.0006778558,0.000146182,0.0009775603,0.00049276],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001252199,0.001363636,0.7040052,0.000250904,0.0006115776,0.0004952232,0.0002871616,0.000002304788,0.00867233,0.000148608,0.008109769,0.2748011],"study_design_scores_gemma":[0.02539307,0.001071128,0.9137473,0.005402423,0.001494547,0.01231132,0.006945326,0.004560269,0.01936172,0.006373532,0.002820926,0.0005184561],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.962855,0.003216859,0.02796392,0.003880003,0.0007125717,0.0002134612,0.00007332558,0.00001605795,0.001068778],"genre_scores_gemma":[0.9954919,0.0001202435,0.003825458,0.0001450404,0.000367746,0.000001584813,0.00001808875,0.00001661153,0.0000133036],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2742827,"threshold_uncertainty_score":0.4551618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2613447076","doi":"10.1117/1.jmi.4.4.041305","title":"Discovery radiomics via evolutionary deep radiomic sequencer discovery for pathologically proven lung cancer detection","year":2017,"lang":"en","type":"preprint","venue":"Journal of Medical Imaging","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Sunnybrook Health Science Centre; Sunnybrook Hospital; University of Toronto; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nvidia","keywords":"Radiomics; Patient privacy; Computer science; Artificial intelligence; Deep learning; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01362360769182594,"gpt":0.3413864845308454,"spread":0.3277628768390194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003901569,0.0005823481,0.001527753,0.0004280548,0.0005826772,0.0007292175,0.001199202,0.0006583153,0.00003145479],"category_scores_gemma":[0.006904615,0.0004452601,0.001085789,0.00009731806,0.0007937524,0.0009205615,0.0006354471,0.004486687,0.000001321329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00150859,"about_ca_system_score_gemma":0.002746254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001378023,"about_ca_topic_score_gemma":0.00001466991,"domain_scores_codex":[0.9942474,0.0002150534,0.001758411,0.0007203842,0.002221307,0.0008374809],"domain_scores_gemma":[0.9948477,0.0006348512,0.00241173,0.0006751968,0.00060983,0.0008207156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002254359,0.0004991213,0.02660782,0.002639774,0.001605056,0.004046679,0.0003049532,0.001400713,0.02197533,0.0001616062,0.01094174,0.9275628],"study_design_scores_gemma":[0.006150073,0.000202771,0.008329931,0.007257802,0.001659181,0.007112288,0.00009434957,0.951802,0.0006732524,0.00576104,0.010143,0.0008143552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.108833,0.03277081,0.8139204,0.03100368,0.01222039,0.001012121,0.00003920397,0.00007041942,0.0001300076],"genre_scores_gemma":[0.9544445,0.02090154,0.01105891,0.001585056,0.01074097,0.0001685754,0.00007764291,0.0001971119,0.0008257395],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9504012,"threshold_uncertainty_score":0.9997999,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408315662","doi":"10.1117/1.jmi.12.s2.s22002","title":"Impact of menopause and age on breast density and background parenchymal enhancement in dynamic contrast-enhanced magnetic resonance imaging","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Digital Radiography and Breast Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Sunnybrook Health Science Centre; Health Sciences Centre; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Medicine; Magnetic resonance imaging; Breast MRI; Dynamic contrast; Contrast (vision); Menopause; Radiology; Breast density; Dynamic contrast-enhanced MRI; Parenchyma; Mammography; Nuclear magnetic resonance; Internal medicine; Pathology; Breast cancer","retraction":null,"screen_n_in":null,"score":{"opus":0.005971644301848341,"gpt":0.2968439906742671,"spread":0.2908723463724188,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008477928,0.0002030824,0.0006090728,0.0005107523,0.00004123272,0.00006602477,0.0001303021,0.00004320858,0.00004257646],"category_scores_gemma":[0.0002045694,0.0001558893,0.0001167542,0.0003467464,0.0003946174,0.0002902438,0.00007646133,0.0005195184,4.151252e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001359094,"about_ca_system_score_gemma":0.0002334235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008437994,"about_ca_topic_score_gemma":0.00001166117,"domain_scores_codex":[0.9979988,0.00006678716,0.0006873996,0.0002332573,0.0006791205,0.0003346225],"domain_scores_gemma":[0.9989877,0.0002077238,0.0002176635,0.0001452396,0.000141004,0.0003006789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008154474,0.0004306801,0.2269407,0.0001372006,0.00006631803,0.001297907,0.0001924628,0.000001123056,0.01736051,0.00007558942,0.000151343,0.7525307],"study_design_scores_gemma":[0.005561667,0.0002999504,0.9800507,0.00461177,0.0001230291,0.00295556,0.0003335711,0.004667384,0.0007396935,0.000470834,0.0000416964,0.0001440988],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9855331,0.008150093,0.002439971,0.002693357,0.0001297465,0.0001453132,0.000005079258,0.000007836307,0.0008955279],"genre_scores_gemma":[0.9984993,0.0007157179,0.000249649,0.0004397687,0.00004587278,0.000001851807,0.000001879382,0.00001082431,0.00003517613],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7531101,"threshold_uncertainty_score":0.6356982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409351262","doi":"10.1117/1.jmi.12.5.051803","title":"Correlation of objective image quality metrics with radiologists’ diagnostic confidence depends on the clinical task performed","year":2025,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Radiology practices and education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Research Nova Scotia; Dalhousie University; Exxon Mobil Corporation","keywords":"Medicine; Correlation; Image quality; Confidence interval; Quality (philosophy); Medical physics; Radiology; Task (project management); Artificial intelligence; Image (mathematics); Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.04908256126639332,"gpt":0.4387362302467725,"spread":0.3896536689803792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007912074,0.00009609894,0.0004410165,0.0001899541,0.00007838476,0.00001679,0.0002090937,0.0001115111,0.0001129216],"category_scores_gemma":[0.07602758,0.00005017139,0.0001234418,0.0003683144,0.0005480859,0.0001720208,0.00002605445,0.001248734,0.000003693275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020145,"about_ca_system_score_gemma":0.001019199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005029314,"about_ca_topic_score_gemma":0.000003117391,"domain_scores_codex":[0.997494,0.0005893303,0.0008821489,0.0001374074,0.000747589,0.0001495527],"domain_scores_gemma":[0.980476,0.01770924,0.0009435058,0.0002049153,0.000511154,0.0001552477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001201851,0.0004895095,0.9216357,0.00008070936,0.0003294602,0.0001609852,0.0005318504,0.00002668804,0.0001380314,0.002205921,0.01134512,0.06185414],"study_design_scores_gemma":[0.002567186,0.0005619351,0.980077,0.0009785288,0.0005007688,0.000893185,0.003659373,0.008604896,0.0002147153,0.0005844283,0.001276009,0.00008199803],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8686826,0.001107605,0.06163464,0.06489186,0.001015391,0.0002067554,0.000001248688,0.000008162625,0.002451798],"genre_scores_gemma":[0.9956444,0.001004112,0.0006190235,0.002359201,0.0002995624,0.000002845393,0.000002585762,0.000005198053,0.00006307959],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1269619,"threshold_uncertainty_score":0.9317554,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3130028400","doi":"10.1117/1.jmi.8.1.015501","title":"Automatic segmentation and tracking of biological prosthetic heart valves","year":2021,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Cardiac Valve Diseases and Treatments","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Medicine; Tracking (education); Segmentation; Computer vision; Artificial intelligence; Biomedical engineering; Cardiology","retraction":null,"screen_n_in":null,"score":{"opus":0.02209697312046613,"gpt":0.3841512512949033,"spread":0.3620542781744371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003268673,0.00005956332,0.0002827901,0.00005108973,0.00002164262,0.00001472998,0.00002505218,0.00002963242,0.0002068384],"category_scores_gemma":[0.0004916643,0.00003974891,0.0003237093,0.00007254261,0.0000746632,0.00006277443,0.00002329298,0.0001216637,0.000001072091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002324412,"about_ca_system_score_gemma":0.0001883574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002433408,"about_ca_topic_score_gemma":6.747851e-8,"domain_scores_codex":[0.9989325,0.00006051347,0.0003247814,0.00007283357,0.0005182026,0.0000911901],"domain_scores_gemma":[0.999389,0.00009215881,0.000127365,0.00005512109,0.0001361327,0.0002002525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003670487,0.0003473753,0.7532625,0.0001536158,0.0002949579,0.0005494422,0.0002166361,5.098172e-7,0.007004092,0.00002921567,0.0002443583,0.2378606],"study_design_scores_gemma":[0.003109148,0.0001263568,0.9835421,0.001176315,0.0006180589,0.003745872,0.001161809,0.001715789,0.004311395,0.0003075295,0.0001235906,0.00006207669],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889821,0.005710002,0.0002896254,0.004784893,0.0001157075,0.00005729838,0.000001389841,0.000005680782,0.00005332389],"genre_scores_gemma":[0.9978507,0.0004082683,0.001189227,0.0004445152,0.00009263417,8.873132e-7,0.000003226331,0.000005249016,0.00000532428],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2377986,"threshold_uncertainty_score":0.2264735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2896371716","doi":"10.1117/1.jmi.5.4.044002","title":"Automated segmentation of cellular images using an effective region force","year":2018,"lang":"en","type":"article","venue":"Journal of Medical Imaging","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Pixel; Segmentation; Artificial intelligence; Contrast (vision); Pattern recognition (psychology); Image segmentation; Random walker algorithm; Boundary (topology); Graph; Computer vision; Set (abstract data type); Computer science; Algorithm; Mathematics; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.00834267630488138,"gpt":0.3250703750959985,"spread":0.3167276987911171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008027604,0.00008654639,0.0001770139,0.0001114268,0.00004007954,0.00001946268,0.0002058321,0.00007262135,0.00002010779],"category_scores_gemma":[0.0002916139,0.00007318606,0.0001060354,0.0001041921,0.0001934341,0.00002514561,0.00006401618,0.0001131909,4.748337e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002463301,"about_ca_system_score_gemma":0.00006422203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002681784,"about_ca_topic_score_gemma":0.000002037006,"domain_scores_codex":[0.9988477,0.0001460036,0.0003596894,0.0001249738,0.0004021071,0.0001194932],"domain_scores_gemma":[0.9989372,0.00001706483,0.0003989366,0.0001541488,0.0003859253,0.0001066956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000353179,0.00006444384,0.001258007,0.00001404589,0.00005302938,0.00004677596,0.00006009491,0.00000519092,0.9755757,0.000001326889,0.001823936,0.02106213],"study_design_scores_gemma":[0.0003960451,0.000174928,0.0002952771,0.00009555312,0.00008190384,0.000225343,0.0001259522,0.03182831,0.966467,0.00005217045,0.0001856594,0.00007186037],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6085002,0.0003304585,0.3908652,0.0001001528,0.00004135582,0.00005355393,2.471363e-7,0.00001268695,0.00009612213],"genre_scores_gemma":[0.9937517,0.0000818804,0.005531492,0.0001608218,0.0004372414,7.599724e-7,0.000006992698,0.00001351268,0.00001559034],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3853337,"threshold_uncertainty_score":0.2984441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}