{"id":"W2580480204","doi":"10.1016/j.media.2017.01.009","title":"A deep learning approach for the analysis of masses in mammograms with minimal user intervention","year":2017,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":342,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Artificial intelligence; Segmentation; Computer science; Deep learning; Pattern recognition (psychology); Classifier (UML); Mammography; Bayesian probability; Visualization; Test set; Machine learning; Breast cancer","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001383239,0.0001118433,0.0004153567,0.0005542514,0.0002215825,0.0002467833,0.001244996,0.00007220101,0.00009142111],"category_scores_gemma":[0.0005245175,0.00007164352,0.0005061179,0.00215417,0.0002310494,0.0004207476,0.000222334,0.0002079539,8.86334e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004626481,"about_ca_system_score_gemma":0.00002610645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001011953,"about_ca_topic_score_gemma":0.002438138,"domain_scores_codex":[0.9983015,0.0001256223,0.000347569,0.0003919894,0.000620665,0.0002126643],"domain_scores_gemma":[0.9983851,0.0002393532,0.0003787386,0.0008012974,0.0001355332,0.00006001044],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001131957,0.0003548292,0.2773192,0.00007582446,0.01305734,0.00002414859,0.001030628,0.03178151,0.0000806455,0.0001955004,0.00003838651,0.6759288],"study_design_scores_gemma":[0.0003227363,0.00006774389,0.1108156,0.00001056731,0.003110214,9.609045e-7,0.0001869159,0.8851016,0.0001352697,0.0000173842,0.0001509269,0.00008012694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03008858,0.0001277033,0.9689425,0.0004941961,0.00002806774,0.0001156323,8.670978e-7,0.00002463617,0.0001778751],"genre_scores_gemma":[0.9486552,0.00002620026,0.05104491,0.0000294543,0.00002563145,0.00008480731,0.00001172613,0.000006048583,0.0001159688],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9185666,"threshold_uncertainty_score":0.2921538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01522990514961771,"score_gpt":0.2996650691174222,"score_spread":0.2844351639678045,"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."}}