{"id":"W2774163924","doi":"10.5430/jbgc.v8n1p1","title":"Automated segmentation of cardiac adipose tissue in Dixon magnetic resonance images","year":2017,"lang":"en","type":"article","venue":"Journal of Biomedical Graphics and Computing","topic":"Cardiovascular Disease and Adiposity","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Hausdorff distance; Segmentation; Magnetic resonance imaging; Similarity (geometry); Volume (thermodynamics); Artificial intelligence; Tracing; Nuclear medicine; Observer (physics); Mathematics; Computer science; Pattern recognition (psychology); Computer vision; Medicine; Image (mathematics); Physics; Radiology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.000574346,0.00007325619,0.0003628223,0.0001709623,0.00008454642,0.00002805616,0.00008258602,0.00006684463,0.000002759607],"category_scores_gemma":[0.000098564,0.00005898432,0.0001573291,0.0001185732,0.000200531,0.00005961105,0.00005465704,0.0001900101,1.328731e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000824691,"about_ca_system_score_gemma":0.00004872986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002799198,"about_ca_topic_score_gemma":6.353241e-7,"domain_scores_codex":[0.9990268,0.00005427803,0.0003666353,0.00009550799,0.0003406033,0.0001161145],"domain_scores_gemma":[0.999307,0.00004527224,0.0002629399,0.0001500742,0.00007930919,0.0001554413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002497845,0.0003682995,0.2196468,0.0004246539,0.0003129791,0.000548478,0.0003098437,0.000003548054,0.06093191,0.0001312774,0.0004133549,0.7166591],"study_design_scores_gemma":[0.001486586,0.000409909,0.9887599,0.0007520361,0.0002700072,0.0001362538,0.00005210542,0.003816217,0.003391496,0.00008026822,0.0007749778,0.00007020814],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9755521,0.02346083,0.0002225049,0.0004440653,0.0001656032,0.00008744931,0.000005206156,0.000008662479,0.0000535127],"genre_scores_gemma":[0.9976104,0.001311457,0.0008677885,0.00004181718,0.0001531481,2.428276e-7,0.000002702774,0.0000054876,0.00000690073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7691132,"threshold_uncertainty_score":0.2405311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008792466992943981,"score_gpt":0.2814932664521431,"score_spread":0.2727007994591991,"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."}}