{"meta":{"query_hash":"85434eb68102","filters":{"venue":"Medical Imaging 2019: Computer-Aided Diagnosis"},"cohort_total":3,"direct_labels_cover":0,"predictions_cover":3,"exported":3,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/85434eb68102","api":"https://metacan.xera.ac/api/v1/cohort?venue=Medical+Imaging+2019%3A+Computer-Aided+Diagnosis"},"results":[{"id":"W2921108820","doi":"10.1117/12.2512819","title":"Reliability of computer-aided diagnosis tools with multi-center MR datasets: impact of training protocol","year":2019,"lang":"en","type":"article","venue":"Medical Imaging 2019: Computer-Aided Diagnosis","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; Ontario Brain Institute; Calgary Laboratory Services; University of Calgary","funders":"","keywords":"Computer science; Protocol (science); Cross-validation; Artificial intelligence; Classifier (UML); Data set; CAD; Computer-aided diagnosis; Reliability (semiconductor); Data mining; Data collection; Set (abstract data type); Pattern recognition (psychology); Machine learning; Medicine; Statistics; Mathematics; Pathology","score_opus":0.026107668268694196,"score_gpt":0.31950672220234855,"score_spread":0.29339905393365434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921108820","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94460416,0.001030505,0.04897362,0.00024524375,0.00022263186,0.0012711139,0.0012097736,0.00081977685,0.00162321],"genre_scores_gemma":[0.9803048,0.00011808908,0.015456495,0.00015677956,0.000034198616,0.000947241,0.0023045551,0.00021408104,0.00046376116],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9380031,0.03834768,0.0066841412,0.010335016,0.005844273,0.0007856653],"domain_scores_gemma":[0.7251103,0.19756792,0.014004272,0.036963966,0.025322119,0.001031458],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07626033,0.0012184955,0.0009842344,0.0009848544,0.0007323728,0.0016127902,0.0018692235,0.001894557,0.001049782],"category_scores_gemma":[0.19729523,0.00076800963,0.0010906123,0.0011687251,0.0024094824,0.0014610216,0.0020499835,0.0012113716,0.0008048053],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.052459553,0.004369586,0.5038283,0.0021744205,0.005766558,0.0006820921,0.0048020547,0.11375487,0.056433793,0.0011659225,0.0066066077,0.2479563],"study_design_scores_gemma":[0.0017578937,0.019361163,0.6768566,0.0005971571,0.0028820806,0.0017614246,0.0014950878,0.19490668,0.0890304,0.0026296247,0.008155608,0.00056630356],"about_ca_topic_score_codex":0.002958578,"about_ca_topic_score_gemma":0.0022993356,"teacher_disagreement_score":0.07626033,"about_ca_system_score_codex":0.0009352752,"about_ca_system_score_gemma":0.0011635139,"threshold_uncertainty_score":0.40330797},"labels":[],"label_agreement":null},{"id":"W2921127880","doi":"10.1117/12.2513063","title":"Use of convolutional neural networks to predict risk of masking by mammographic density","year":2019,"lang":"en","type":"article","venue":"Medical Imaging 2019: Computer-Aided Diagnosis","topic":"AI in cancer detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Sunnybrook Hospital","funders":"","keywords":"Masking (illustration); Convolutional neural network; Computer science; Transfer of learning; Mammography; Artificial intelligence; Pattern recognition (psychology); Breast cancer; Medicine; Cancer; Internal medicine","score_opus":0.008057301152431104,"score_gpt":0.2213516015046537,"score_spread":0.21329430035222258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921127880","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8622997,0.0007038494,0.1321774,0.00029267394,0.00007079363,0.00008768666,0.00050474773,0.0013751184,0.0024880487],"genre_scores_gemma":[0.97611266,0.00011336242,0.02205721,0.000050307386,0.000013925256,0.000033261713,0.0004714339,0.00001850107,0.0011293165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997311,0.000067254216,0.000023783901,0.000068484085,0.00005918856,0.000050079372],"domain_scores_gemma":[0.99877626,0.0007874705,0.00012563207,0.000072954484,0.0002040128,0.000033739198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012472342,0.0008905656,0.00038217386,0.000938818,0.00016077669,0.00046242366,0.00049191737,0.000539448,0.0006795216],"category_scores_gemma":[0.0031949545,0.00029520498,0.00047846304,0.00036501625,0.00022179291,0.00047961232,0.00039885155,0.0005434414,0.00020401203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012384289,0.00040528076,0.106728934,0.00010545645,0.00049966807,0.00034362322,0.00009792495,0.58090824,0.02631372,0.0009043507,0.0020325936,0.2804217],"study_design_scores_gemma":[0.000005675745,0.00005514423,0.009337384,0.000006404666,0.000027982327,0.00003697953,0.0000065859454,0.98664594,0.0033972666,0.00035187535,0.00012124752,0.000007430619],"about_ca_topic_score_codex":0.008590633,"about_ca_topic_score_gemma":0.0076811067,"teacher_disagreement_score":0.008590633,"about_ca_system_score_codex":0.0008397607,"about_ca_system_score_gemma":0.0005030576,"threshold_uncertainty_score":0.01708126},"labels":[],"label_agreement":null},{"id":"W2921622031","doi":"10.1117/12.2512550","title":"PI-RADS guided discovery radiomics for characterization of prostate lesions with diffusion-weighted MRI","year":2019,"lang":"en","type":"article","venue":"Medical Imaging 2019: Computer-Aided Diagnosis","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Radiomics; Diffusion MRI; Prostate; BI-RADS; Multiparametric MRI; Magnetic resonance imaging; Medicine; Computer science; Radiology; Internal medicine","score_opus":0.0068312632274489605,"score_gpt":0.2622688284657198,"score_spread":0.2554375652382708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921622031","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083248794,0.00060087425,0.912206,0.00029232874,0.000028709632,0.00015369116,0.00031485045,0.002318683,0.0008361094],"genre_scores_gemma":[0.6486431,0.0003154203,0.34872365,0.00013133424,0.00006235934,0.0001291954,0.00078523793,0.00009691675,0.0011128433],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991186,0.00033503654,0.00004898158,0.00019469864,0.0002294485,0.00007328301],"domain_scores_gemma":[0.99845195,0.0006809258,0.00026406164,0.00028130267,0.00025173687,0.00006991774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019503922,0.000835978,0.0010090523,0.0020659608,0.00023625314,0.0008406358,0.0009166429,0.00070755905,0.0006949132],"category_scores_gemma":[0.0045952722,0.0003293313,0.0008552798,0.0008671634,0.00054707995,0.00067819207,0.0009663113,0.00077995413,0.00072065427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084234896,0.00038130386,0.026293423,0.00026919344,0.00025327384,0.0004118296,0.00015315157,0.15301532,0.0595938,0.004267549,0.0031968455,0.751322],"study_design_scores_gemma":[0.000023607665,0.00021551049,0.004960645,0.000013451754,0.00005277953,0.00041900532,0.000028346978,0.9745973,0.014969375,0.0035054057,0.0011793794,0.00003537383],"about_ca_topic_score_codex":0.0012820985,"about_ca_topic_score_gemma":0.001806705,"teacher_disagreement_score":0.0020659608,"about_ca_system_score_codex":0.00036952883,"about_ca_system_score_gemma":0.0007102127,"threshold_uncertainty_score":0.010314822},"labels":[],"label_agreement":null}]}