{"id":"W2964166134","doi":"10.1016/j.compbiomed.2019.04.018","title":"Deep learning for identifying radiogenomic associations in breast cancer","year":2019,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":163,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Canadian Institute for Advanced Research; North Carolina Biotechnology Center","keywords":"Artificial intelligence; Deep learning; Transfer of learning; Computer science; Artificial neural network; Receiver operating characteristic; Magnetic resonance imaging; Breast cancer; Machine learning; Support vector machine; Pattern recognition (psychology); Cancer; Medicine; Radiology; Internal medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005864563,0.0001003513,0.0003927852,0.0002433952,0.00004797205,0.000004216171,0.00006265805,0.0001017755,0.00004273045],"category_scores_gemma":[0.0001413596,0.00008168886,0.00002994153,0.000143933,0.0001146392,0.00002898561,0.00003290911,0.0003919128,0.000002233856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001081554,"about_ca_system_score_gemma":0.00003131107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002128746,"about_ca_topic_score_gemma":0.00002166884,"domain_scores_codex":[0.9991355,0.0000631356,0.0002549842,0.0002524098,0.00005012073,0.000243838],"domain_scores_gemma":[0.9994086,0.0003333815,0.00007682339,0.00007922623,0.0000264291,0.0000755583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005848313,0.0000224614,0.952118,0.00007365814,0.00003385603,0.000007883086,0.00065866,0.000327437,0.003847746,0.0009097221,0.0001684852,0.04177359],"study_design_scores_gemma":[0.00513941,0.000151324,0.8705946,0.0004862139,0.00003463146,0.00007807334,0.0001693136,0.1201701,0.000006653175,0.0009770981,0.002086396,0.0001061189],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9683651,0.002959571,0.0135713,0.01327802,0.001060222,0.0004143459,0.000001890809,0.00002862126,0.000320927],"genre_scores_gemma":[0.9947057,0.000965222,0.002017058,0.001803261,0.0003193098,0.00002025032,0.00005670241,0.0000123452,0.0001001512],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1198427,"threshold_uncertainty_score":0.3331175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01587568645508144,"score_gpt":0.3488987366794629,"score_spread":0.3330230502243814,"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."}}