{"id":"W1971950380","doi":"10.1016/j.crad.2009.08.003","title":"Can breast MRI computer-aided detection (CAD) improve radiologist accuracy for lesions detected at MRI screening and recommended for biopsy in a high-risk population?","year":2009,"lang":"en","type":"article","venue":"Clinical Radiology","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Medicine; Breast cancer; Radiology; Biopsy; Breast MRI; CAD; Magnetic resonance imaging; Histopathology; Population; Mammography; Cancer; Pathology; Internal medicine","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":[0.004964379,0.0006082057,0.001282645,0.001350663,0.0003613013,0.001121686,0.0010307,0.002524741,0.002925043],"category_scores_gemma":[0.05552721,0.0003918133,0.0009664936,0.001282675,0.0005215356,0.001802241,0.0004172629,0.000958001,0.001133599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005231164,"about_ca_system_score_gemma":0.0007759165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006948081,"about_ca_topic_score_gemma":0.01065868,"domain_scores_codex":[0.9975662,0.001365117,0.0001992794,0.0002756644,0.0004204138,0.0001733395],"domain_scores_gemma":[0.9797119,0.01425682,0.001706596,0.0009576974,0.002757938,0.0006091189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002678098,0.001180638,0.7768562,0.0003105469,0.0004160281,0.0003317476,0.0001444144,0.001498195,0.0008966206,0.0003641983,0.007562911,0.2077605],"study_design_scores_gemma":[0.0005940619,0.003230626,0.9584608,0.0002796936,0.001837141,0.002417157,0.0003916099,0.02079083,0.002521974,0.001604195,0.00779352,0.00007844737],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9196905,0.01905456,0.007690137,0.03838679,0.001546032,0.0001408683,0.0009092462,0.0003708406,0.01221097],"genre_scores_gemma":[0.9826989,0.003744304,0.007468204,0.00379994,0.001148443,0.00004105101,0.0003734269,0.00002085611,0.0007050112],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006948081,"threshold_uncertainty_score":0.02625448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04897406672437752,"score_gpt":0.3777899924662604,"score_spread":0.3288159257418829,"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."}}