{"id":"W2767947179","doi":"10.1371/journal.pone.0187501","title":"Using quantitative features extracted from T2-weighted MRI to improve breast MRI computer-aided diagnosis (CAD)","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Cure Brain Cancer Foundation; Government of Ontario; Ontario Institute for Cancer Research","keywords":"Receiver operating characteristic; Computer-aided diagnosis; CAD; Breast MRI; Computer science; Magnetic resonance imaging; Medicine; Artificial intelligence; Breast imaging; BI-RADS; Radiology; Pattern recognition (psychology); Breast cancer; Mammography; Machine learning; Cancer","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002149415,0.000751354,0.0007602412,0.002993859,0.0001761363,0.001227026,0.0003717622,0.0006197391,0.0004489759],"category_scores_gemma":[0.00839753,0.000203972,0.0006703636,0.001415193,0.0002606361,0.0008934512,0.0003718212,0.0005055423,0.0003278608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003182488,"about_ca_system_score_gemma":0.0002776087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001672158,"about_ca_topic_score_gemma":0.001813815,"domain_scores_codex":[0.9991177,0.0002035769,0.0001124695,0.0001822005,0.0003211502,0.00006298951],"domain_scores_gemma":[0.9952074,0.002668952,0.0007657845,0.0002961976,0.001001762,0.00005991713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008414147,0.0006498626,0.1297763,0.0005064525,0.0004933344,0.0004063899,0.0001634363,0.05079316,0.104555,0.0007916717,0.002771377,0.7082515],"study_design_scores_gemma":[0.00008527082,0.001396537,0.1868754,0.00009531908,0.0004856303,0.001830487,0.0001141115,0.7399554,0.06375569,0.001641408,0.003592971,0.0001717526],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6062158,0.002949104,0.3838565,0.0003844479,0.0001997661,0.0002868449,0.00110838,0.002459302,0.002539824],"genre_scores_gemma":[0.8967364,0.0006056429,0.1009311,0.00012114,0.00009188698,0.00008469328,0.0008565796,0.00006688988,0.0005054991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002993859,"threshold_uncertainty_score":0.01136732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09626431066257528,"score_gpt":0.3319289482148775,"score_spread":0.2356646375523022,"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."}}