{"id":"W1994454819","doi":"10.1016/j.compmedimag.2014.06.017","title":"A data-driven approach to prostate cancer detection from dynamic contrast enhanced MRI","year":2014,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia Hospital; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Principal component analysis; Dynamic contrast-enhanced MRI; Computer science; Prostate cancer; Artificial intelligence; Pattern recognition (psychology); Data set; Contrast (vision); Magnetic resonance imaging; Prostatectomy; Cross-validation; Support vector machine; Dynamic contrast; Medical imaging; Cancer; Medicine; Radiology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003976997,0.0002271771,0.0004910472,0.0001493895,0.00009725634,0.00006699627,0.0002981467,0.0001067349,0.00002646269],"category_scores_gemma":[0.0001604229,0.0001973372,0.00005384411,0.0003094566,0.0002405974,0.0001084538,0.0002792288,0.0004295742,0.000005380442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004833581,"about_ca_system_score_gemma":0.0001104406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003551938,"about_ca_topic_score_gemma":0.0001702904,"domain_scores_codex":[0.9979126,0.0001026808,0.0003357824,0.0007607287,0.0005307479,0.0003574721],"domain_scores_gemma":[0.9982971,0.0002450077,0.00008880556,0.0006288994,0.0001079516,0.00063223],"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":[0.0005658354,0.0004847776,0.006562236,0.0004572005,0.0003636033,0.00003741841,0.001507199,0.0001231687,0.01456092,0.0001276526,0.009376759,0.9658332],"study_design_scores_gemma":[0.003908826,0.00008758742,0.009936717,0.0006583798,0.0001776922,0.00003452521,0.00004135084,0.9479642,0.0004298891,0.0002337441,0.03624982,0.0002772684],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1644665,0.0008130563,0.8201652,0.01255653,0.0008583603,0.0005947791,0.0001801703,0.0002231669,0.0001422551],"genre_scores_gemma":[0.9691024,0.002991481,0.01933833,0.007507642,0.0005460524,0.0001494903,0.0003015473,0.00004293795,0.00002004719],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.965556,"threshold_uncertainty_score":0.8047176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01545669801641704,"score_gpt":0.2988926169371321,"score_spread":0.2834359189207151,"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."}}