{"id":"W2003280360","doi":"10.1007/s10278-012-9506-2","title":"Feature Selection in Computer-Aided Breast Cancer Diagnosis via Dynamic Contrast-Enhanced Magnetic Resonance Images","year":2012,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"Sunnybrook Health Science Centre; Queen's University; Sunnybrook Hospital; Royal Military College of Canada; Department of National Defence","funders":"","keywords":"Feature selection; Magnetic resonance imaging; Artificial intelligence; Support vector machine; Pattern recognition (psychology); Receiver operating characteristic; Computer science; Computer-aided diagnosis; Feature (linguistics); Breast cancer; CAD; Classifier (UML); Cross-validation; Area under curve; Contrast (vision); Cancer; Medicine; Radiology; Machine learning","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":[0.0002231509,0.0002420495,0.0005151265,0.000320165,0.00004502291,0.0001336087,0.0001379863,0.00006568789,0.0001221941],"category_scores_gemma":[0.00005166539,0.0002140523,0.0001712602,0.0004730273,0.00008335869,0.001704944,0.00004374278,0.0005438884,0.000009757429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006737802,"about_ca_system_score_gemma":0.0001236599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003627996,"about_ca_topic_score_gemma":0.00002017472,"domain_scores_codex":[0.9983333,0.00003930137,0.0004786284,0.0002051685,0.0004230309,0.000520554],"domain_scores_gemma":[0.9987541,0.0001764029,0.0003520037,0.0001233683,0.0003354463,0.000258651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001561067,0.0002945051,0.6298748,0.00005782974,0.0000286184,0.00005361009,0.0001574735,0.00004279768,0.003758285,8.820033e-7,0.007753258,0.3578218],"study_design_scores_gemma":[0.002902007,0.0002007842,0.9805561,0.001506121,0.000135888,0.002338943,0.00006022837,0.001929738,0.006896296,0.00005393305,0.003153759,0.000266207],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9234302,0.03759134,0.009402485,0.02687833,0.00143837,0.0005522676,0.0001298773,0.00007122366,0.0005058868],"genre_scores_gemma":[0.9943817,0.00208785,0.001902457,0.0005649538,0.0008517658,0.00004732158,0.000003639293,0.000045717,0.0001145464],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3575556,"threshold_uncertainty_score":0.8728797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006210633881149552,"score_gpt":0.2709622072529851,"score_spread":0.2647515733718355,"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."}}