{"id":"W4321612729","doi":"10.1001/jamanetworkopen.2023.0524","title":"A Competition, Benchmark, Code, and Data for Using Artificial Intelligence to Detect Lesions in Digital Breast Tomosynthesis","year":2023,"lang":"en","type":"article","venue":"JAMA Network Open","topic":"Digital Radiography and Breast Imaging","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Data set; Artificial intelligence; Benchmark (surveying); Sensitivity (control systems); Set (abstract data type); Computer science; Test set; Code (set theory); Health care; Tomosynthesis; Machine learning; Medical physics; Medicine; Mammography; Breast cancer; Cancer; Cartography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03833707,0.002595033,0.001019237,0.003421595,0.002483001,0.003823407,0.007187783,0.002845332,0.007008065],"category_scores_gemma":[0.0791271,0.0009844952,0.001828231,0.003020725,0.001966938,0.004008627,0.006765521,0.00429609,0.007608217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004182816,"about_ca_system_score_gemma":0.009544003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01296661,"about_ca_topic_score_gemma":0.01534953,"domain_scores_codex":[0.977833,0.008048636,0.001603719,0.002321254,0.008944575,0.001248954],"domain_scores_gemma":[0.8971322,0.0312704,0.004498665,0.01766459,0.03902993,0.01040411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001868885,0.003668496,0.02236146,0.001406033,0.000295339,0.0005065344,0.00117609,0.03894777,0.01039232,0.007652243,0.5442076,0.3675172],"study_design_scores_gemma":[0.004648793,0.008528863,0.0940989,0.001683423,0.0002496333,0.001468822,0.002083646,0.3430836,0.04615914,0.0257734,0.4713409,0.000880864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"dataset","genre_scores_codex":[0.3654023,0.004081647,0.3634071,0.02423352,0.006158762,0.01596195,0.08027527,0.05707601,0.0834033],"genre_scores_gemma":[0.2437143,0.0008325276,0.494006,0.002489221,0.0005769355,0.01019585,0.2222714,0.009247127,0.01666674],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.03833707,"threshold_uncertainty_score":0.2027482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08941549269208739,"score_gpt":0.3487572924536095,"score_spread":0.2593417997615221,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}