{"id":"W4307923846","doi":"10.1148/ryai.210294","title":"A Deep Learning Segmentation Pipeline for Cardiac T1 Mapping Using MRI Relaxation–based Synthetic Contrast Augmentation","year":2022,"lang":"en","type":"article","venue":"Radiology Artificial Intelligence","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Health Sciences Centre; Canada Research Chairs; University of Toronto; Sunnybrook Health Science Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Heart and Stroke Foundation of Canada","keywords":"Medicine; Segmentation; Artificial intelligence; Nuclear medicine; Contouring; Convolutional neural network; Magnetic resonance imaging; Deep learning; Fluid-attenuated inversion recovery; Contrast (vision); Pattern recognition (psychology); Radiology; Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0008378276,0.0001554185,0.0003391867,0.0002215518,0.0005985238,0.00002516503,0.0000671605,0.00006717961,0.0001599486],"category_scores_gemma":[0.001038176,0.0001786017,0.0001853172,0.00029299,0.0001213734,0.00005968485,0.00002944127,0.0003053391,0.00002712831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003529524,"about_ca_system_score_gemma":0.0001333932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003756274,"about_ca_topic_score_gemma":0.000002621108,"domain_scores_codex":[0.9983227,0.0003094917,0.0004827488,0.0003693709,0.0002054449,0.000310233],"domain_scores_gemma":[0.99844,0.0009258789,0.0002212621,0.0001702547,0.0001630525,0.00007951896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008717383,0.0002004552,0.01871201,0.0001016347,0.0001479171,0.00003300078,0.002808317,0.8211042,0.07737685,0.002064602,0.0004478925,0.07613139],"study_design_scores_gemma":[0.0003024652,0.000289093,0.001009756,0.00004395127,0.0003231629,0.0000914184,0.00608848,0.962217,0.02748162,0.0007422459,0.00117061,0.0002402058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1052607,0.0005488399,0.8912922,0.0007788294,0.001070398,0.0008208973,0.00002564465,0.00009892405,0.0001036447],"genre_scores_gemma":[0.9856501,0.00001959453,0.01282557,0.0004616284,0.0003466204,0.0002447063,0.0003439034,0.00003064519,0.000077178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8803895,"threshold_uncertainty_score":0.7283166,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04337849740061517,"score_gpt":0.3206126683002549,"score_spread":0.2772341708996398,"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."}}