{"id":"W4386228640","doi":"10.48550/arxiv.2308.13488","title":"Temporal Uncertainty Localization to Enable Human-in-the-loop Analysis of Dynamic Contrast-enhanced Cardiac MRI Datasets","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"National Institutes of Health; Lilly Endowment; Eli Lilly and Company","keywords":"Segmentation; Artificial intelligence; Metric (unit); Computer science; Dynamic contrast; Contrast (vision); Magnetic resonance imaging; Pattern recognition (psychology); Cardiac magnetic resonance imaging; Computer vision; Medicine; Radiology; Engineering","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":[0.004366429,0.001115133,0.0007828268,0.001747255,0.0005307351,0.001212484,0.001391897,0.001109286,0.001185801],"category_scores_gemma":[0.01682542,0.0003324565,0.0006997882,0.0008150169,0.0006992782,0.001053306,0.001688949,0.000953604,0.0003179268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000884528,"about_ca_system_score_gemma":0.001122274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005719845,"about_ca_topic_score_gemma":0.008190338,"domain_scores_codex":[0.9978581,0.0007163389,0.0001871319,0.0005979598,0.0005075593,0.0001328904],"domain_scores_gemma":[0.9940237,0.003282489,0.0007542265,0.000639757,0.001130515,0.0001693709],"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":[0.0008783283,0.000253225,0.006435098,0.0004475508,0.0002656244,0.0004802503,0.000654182,0.5035614,0.05835164,0.006043474,0.005828362,0.4168009],"study_design_scores_gemma":[0.000009332835,0.00005706079,0.001171925,0.00001305966,0.00001312188,0.00006306286,0.00004300049,0.9817723,0.01365799,0.001970412,0.001211973,0.00001678644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05605996,0.0003347704,0.9381731,0.0001574188,0.0000482041,0.0001316986,0.0003898431,0.004013019,0.0006919418],"genre_scores_gemma":[0.4054116,0.0001367798,0.5910276,0.0001447602,0.00004282068,0.0002337923,0.001638665,0.0007577231,0.0006063814],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005719845,"threshold_uncertainty_score":0.02309215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06557988153292407,"score_gpt":0.2793319409735589,"score_spread":0.2137520594406348,"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."}}