{"id":"W2931569196","doi":"10.1109/access.2019.2907564","title":"Quantification of Full Left Ventricular Metrics via Deep Regression Learning With Contour-Guidance","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":83,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Science Foundation of Tianjin City; Natural Science Foundation of Beijing Municipality; Department of Education of Hebei Province; National Natural Science Foundation of China; National Science Foundation","keywords":"Segmentation; Artificial intelligence; Ventricle; Regression; Computer science; Pattern recognition (psychology); Component (thermodynamics); Image segmentation; Regression analysis; Deep learning; Cardiac magnetic resonance; Magnetic resonance imaging; Computer vision; Machine learning; Mathematics; Statistics; Cardiology; Medicine; Radiology","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":[0.0004721207,0.0001315868,0.0003415378,0.0002080297,0.00005922072,0.00003757282,0.0002178088,0.00007671928,0.0001077716],"category_scores_gemma":[0.0003363052,0.00009212994,0.00006382175,0.0004317645,0.00006048963,0.0001827074,0.00003242117,0.0004230152,0.0000294437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004387839,"about_ca_system_score_gemma":0.00004671436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000686745,"about_ca_topic_score_gemma":0.000002638268,"domain_scores_codex":[0.9986883,0.00007372862,0.0002912158,0.0002792516,0.0004609678,0.0002064914],"domain_scores_gemma":[0.9989266,0.0001193824,0.0003199365,0.0003177722,0.0002079623,0.0001083691],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003564015,0.0001711153,0.8297715,0.0004983385,0.000107843,0.0001070073,0.000203963,0.008445604,0.1144526,0.0001023078,0.000429856,0.04535346],"study_design_scores_gemma":[0.007338577,0.001657216,0.2548186,0.002405622,0.0004818975,0.0007576331,0.0002742363,0.609044,0.1081155,0.0001674267,0.01420241,0.0007369877],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8155696,0.0006318897,0.1819372,0.000466713,0.0002976103,0.0002717022,4.589826e-7,0.00005003707,0.0007747942],"genre_scores_gemma":[0.9972098,0.00006718154,0.001983468,0.000149768,0.0001088821,0.000004287394,0.00001931278,0.00002801354,0.0004293204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6005983,"threshold_uncertainty_score":0.375695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01608091908371773,"score_gpt":0.3147499362919007,"score_spread":0.298669017208183,"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."}}