{"id":"W3050025544","doi":"10.48550/arxiv.2008.07770","title":"Fully automated deep learning based segmentation of normal, infarcted and edema regions from multiple cardiac MRI sequences","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Segmentation; Convolutional neural network; Deep learning; Myocardial infarction; Medicine; Artificial intelligence; Test set; Computer science; Magnetic resonance imaging; Steady-state free precession imaging; Pattern recognition (psychology); Cardiology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008885534,0.00124991,0.000679885,0.00174395,0.0002694804,0.000766383,0.0009047769,0.0009794557,0.0009076392],"category_scores_gemma":[0.001384446,0.00048,0.0006541169,0.0006940449,0.0003118356,0.0007294922,0.001119025,0.0005512294,0.0006579515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005766224,"about_ca_system_score_gemma":0.0009528801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00645835,"about_ca_topic_score_gemma":0.01518014,"domain_scores_codex":[0.9995506,0.00006648251,0.00003512267,0.0001555449,0.00009909379,0.00009301653],"domain_scores_gemma":[0.9994628,0.0001238782,0.0001044196,0.00009607751,0.0001684532,0.00004446252],"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":[0.0008160491,0.0003832287,0.01359753,0.0002446621,0.0002449565,0.0004675989,0.0001624632,0.1247406,0.1051554,0.001256596,0.005135743,0.7477952],"study_design_scores_gemma":[0.00001888389,0.0001212642,0.007103685,0.0000378594,0.00006211805,0.0003520469,0.0000429293,0.9543924,0.03399662,0.001836249,0.002013472,0.00002244279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3055398,0.001946239,0.6813117,0.0004219779,0.0001133412,0.0002732442,0.001868831,0.005404163,0.003120643],"genre_scores_gemma":[0.7256842,0.0007316335,0.2615781,0.0002876326,0.00008618279,0.0001360303,0.006133503,0.0002705924,0.005092083],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00645835,"threshold_uncertainty_score":0.01284152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04278068332476507,"score_gpt":0.2123940217769567,"score_spread":0.1696133384521917,"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."}}