{"id":"W3092474017","doi":"10.1016/j.compmedimag.2020.101795","title":"Multislice left ventricular ejection fraction prediction from cardiac MRIs without segmentation using shared SptDenNet","year":2020,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Natural Science Foundation of Chongqing; National Natural Science Foundation of China","keywords":"Ejection fraction; Segmentation; Computer science; Softmax function; Artificial intelligence; Pattern recognition (psychology); Fraction (chemistry); Image segmentation; Deep learning; Heart failure; Medicine; Cardiology","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":[0.0002446028,0.0002253119,0.0004578979,0.0001371287,0.0001847794,0.0001185539,0.00005964937,0.000141845,0.00003346943],"category_scores_gemma":[0.0005042496,0.0002245144,0.0001711296,0.0002797515,0.0001400717,0.0002525417,0.00007846625,0.0004827065,0.000007083577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006430537,"about_ca_system_score_gemma":0.0000894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000322252,"about_ca_topic_score_gemma":7.688552e-7,"domain_scores_codex":[0.9981136,0.0001357657,0.0003645987,0.0004897281,0.0006423951,0.0002539337],"domain_scores_gemma":[0.9987746,0.0002064819,0.0001283594,0.0001800233,0.0001647299,0.0005457675],"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":[0.0002296025,0.0001273115,0.9556831,0.0001643886,0.0002772732,0.0002319248,0.0006237658,0.00006011727,0.01511375,0.00001107934,0.004587104,0.02289064],"study_design_scores_gemma":[0.004449307,0.00009606338,0.1823445,0.0005204069,0.0008280061,0.0001956251,0.0003851444,0.8021934,0.001163287,0.00006172552,0.007449553,0.0003129923],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6496003,0.00177216,0.3437781,0.002741849,0.001274513,0.0003608145,0.00009089267,0.0003412651,0.00004008045],"genre_scores_gemma":[0.9782504,0.0009417012,0.01389089,0.003933625,0.002089315,0.000009819903,0.0008339072,0.00004665313,0.000003650673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8021333,"threshold_uncertainty_score":0.9155433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0172539242376901,"score_gpt":0.2797746010280586,"score_spread":0.2625206767903685,"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."}}