{"id":"W4396779989","doi":"10.1093/ehjci/jeae123","title":"Evaluation of deep learning estimation of whole heart anatomy from automated cardiovascular magnetic resonance short- and long-axis analyses in UK Biobank","year":2024,"lang":"en","type":"article","venue":"European Heart Journal - Cardiovascular Imaging","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Innovation Cluster (Canada)","funders":"National Heart, Lung, and Blood Institute; Engineering and Physical Sciences Research Council; Siemens Healthineers; Centre For Medical Engineering, King’s College London; Wellcome Trust; Wellcome","keywords":"Biobank; Magnetic resonance imaging; Cardiac magnetic resonance; Estimation; Volume (thermodynamics); Cardiac magnetic resonance imaging; Deep learning; Cardiovascular health; Medicine; Artificial neural network; Artificial intelligence; Computer science; Disease; Radiology; Bioinformatics; Internal medicine; Engineering; Physics; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00492548,0.000782885,0.0003755839,0.0006862018,0.0002038654,0.0006715049,0.0009157778,0.0008905245,0.001202621],"category_scores_gemma":[0.01699384,0.0002964606,0.0003501489,0.0004250564,0.0004312034,0.0005367497,0.001226077,0.0005686089,0.0004174912],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001156022,"about_ca_system_score_gemma":0.0007308885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01557174,"about_ca_topic_score_gemma":0.01363026,"domain_scores_codex":[0.9983675,0.000883419,0.0001090036,0.0003055653,0.0002331857,0.0001013662],"domain_scores_gemma":[0.9933453,0.004139891,0.0006088656,0.0006436498,0.001039104,0.0002232236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006522946,0.0009027478,0.3638047,0.0004424243,0.001001204,0.0005845473,0.0004497557,0.3499057,0.01108807,0.001129463,0.008047738,0.2561207],"study_design_scores_gemma":[0.0002051845,0.000838278,0.08433673,0.00006435859,0.0001135954,0.0002248204,0.00008728752,0.907029,0.005264227,0.0006745865,0.001130418,0.00003146252],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.979539,0.0002819572,0.01736523,0.0002872434,0.00003933027,0.0001010614,0.00105156,0.0005507187,0.0007840231],"genre_scores_gemma":[0.9820373,0.000109572,0.01406229,0.00009279103,0.00001633093,0.0001111027,0.002910608,0.0000286944,0.000631375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01557174,"threshold_uncertainty_score":0.03096223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0351921759546302,"score_gpt":0.3381169199236926,"score_spread":0.3029247439690624,"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."}}