{"id":"W7116802821","doi":"10.1016/b978-0-443-14109-6.00030-4","title":"Clinical applications of machine learning in breast MRI","year":2025,"lang":"en","type":"book-chapter","venue":"Advances in magnetic resonance technology and applications","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Breast MRI; Breast cancer; Segmentation; Deep learning; Breast imaging; Patient care; Magnetic resonance imaging","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":[0.0008029217,0.0007277317,0.0004627345,0.001088771,0.0001723581,0.001215906,0.0007118593,0.0009114878,0.01536879],"category_scores_gemma":[0.00194681,0.0003011232,0.0003772723,0.00106244,0.0005966531,0.001152105,0.000697666,0.001459908,0.006527164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004143977,"about_ca_system_score_gemma":0.0003671374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005379149,"about_ca_topic_score_gemma":0.001144798,"domain_scores_codex":[0.9997317,0.00008107012,0.00001321302,0.00002865634,0.0001338251,0.00001149497],"domain_scores_gemma":[0.9989496,0.0008500614,0.00002167255,0.00003918147,0.0001143793,0.00002515156],"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":[0.00003038338,0.00006125472,0.0003124174,0.0009569746,0.00002978537,0.0002756386,0.0001324293,0.006719253,0.002572895,0.07516826,0.1205208,0.79322],"study_design_scores_gemma":[0.000009413446,0.00006583133,0.001062209,0.0009124717,0.000022371,0.002637933,0.0000830175,0.02101232,0.002868662,0.1450012,0.8262867,0.00003785332],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.002803405,0.4432099,0.2459196,0.008833329,0.004069209,0.0001000425,0.0003546103,0.001036954,0.2936729],"genre_scores_gemma":[0.04359546,0.3657526,0.2259964,0.005009972,0.006184191,0.0001429622,0.000673526,0.0006170771,0.3520278],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01536879,"threshold_uncertainty_score":0.05141371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007930839427681077,"score_gpt":0.3170309212918799,"score_spread":0.3091000818641988,"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."}}