{"id":"W2898898617","doi":"10.1016/j.media.2018.10.011","title":"A graph-based lesion characterization and deep embedding approach for improved computer-aided diagnosis of nonmass breast MRI lesions","year":2018,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; Sunnybrook Health Science Centre","funders":"National Institute for Materials Science; Canadian Cancer Society; Ontario Institute for Cancer Research","keywords":"Artificial intelligence; Embedding; Computer-aided diagnosis; Graph; Breast MRI; Pattern recognition (psychology); Computer-aided; Computer science; Lesion; Computer vision; Medicine; Theoretical computer science; Breast cancer; Pathology; Mammography; Internal medicine","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":[0.0002603986,0.0007878686,0.0007332003,0.001478688,0.0002582099,0.0005341934,0.0009690555,0.000940063,0.001226755],"category_scores_gemma":[0.0006983535,0.0002864928,0.0007783841,0.0007692867,0.0002426626,0.0007096596,0.0008453046,0.0006963232,0.0005898055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003279083,"about_ca_system_score_gemma":0.0005483982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006280093,"about_ca_topic_score_gemma":0.01055184,"domain_scores_codex":[0.999815,0.00003014209,0.00001201214,0.00005825837,0.00004906483,0.00003539997],"domain_scores_gemma":[0.999709,0.00009660279,0.00003534532,0.00003436538,0.00009927788,0.00002534094],"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":[0.00041841,0.0003579023,0.003275027,0.000200961,0.0001758594,0.0003707178,0.000128053,0.1346334,0.08222912,0.003120703,0.005997124,0.7690927],"study_design_scores_gemma":[0.000006200844,0.00004537203,0.0008177757,0.00000747387,0.00003418817,0.0001083451,0.00002141838,0.9903089,0.006316072,0.001646464,0.0006785087,0.000009217237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09492202,0.001004734,0.8997731,0.0003768986,0.00007896021,0.00009900655,0.0005171722,0.001807508,0.001420604],"genre_scores_gemma":[0.6424257,0.0007419219,0.3496286,0.0003272353,0.0001013259,0.0001047014,0.001695,0.0002241787,0.004751301],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006280093,"threshold_uncertainty_score":0.01248705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01694372814630471,"score_gpt":0.3100155083522342,"score_spread":0.2930717802059295,"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."}}