{"id":"W4288033811","doi":"10.3389/fcvm.2022.894503","title":"Predicting post-contrast information from contrast agent free cardiac MRI using machine learning: Challenges and methods","year":2022,"lang":"en","type":"article","venue":"Frontiers in Cardiovascular Medicine","topic":"Cardiac Imaging and Diagnostics","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Circle Cardiovascular Imaging","funders":"National Heart, Lung, and Blood Institute; Barts Health NHS Trust; European Commission; Department of Health and Social Care; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Wellcome; Barts Charity; European Regional Development Fund; UK Research and Innovation; Wellcome Trust","keywords":"Contrast (vision); Artificial intelligence; Segmentation; Support vector machine; Medical diagnosis; Myocardial infarction; Feature (linguistics); Computer science; Medicine; Pattern recognition (psychology); Decision tree; Magnetic resonance imaging; Radiology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003361811,0.00150101,0.0007421224,0.001149908,0.0003897337,0.001392532,0.001564787,0.001727148,0.001183457],"category_scores_gemma":[0.006750647,0.0003500534,0.0008327346,0.0009153905,0.0004741821,0.001347291,0.0008497973,0.001509945,0.0007740824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006345928,"about_ca_system_score_gemma":0.0008918879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002742157,"about_ca_topic_score_gemma":0.003066844,"domain_scores_codex":[0.9984888,0.0005241584,0.0001283604,0.0004418698,0.0003107998,0.0001060235],"domain_scores_gemma":[0.9963269,0.002051012,0.0003120728,0.0004989811,0.0006759425,0.0001351169],"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":[0.000649562,0.00124603,0.07808853,0.0004952119,0.0003974891,0.0003790406,0.0001170791,0.2039798,0.01303094,0.002276624,0.0146788,0.684661],"study_design_scores_gemma":[0.00002768004,0.0001855519,0.0114513,0.00006461213,0.00004541091,0.000173594,0.00006341875,0.9725495,0.00765679,0.005038586,0.002709465,0.00003413461],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3824841,0.008468595,0.5934476,0.004821415,0.0005081278,0.0005208881,0.003936134,0.002131421,0.003681582],"genre_scores_gemma":[0.7467743,0.001455175,0.2421484,0.0005151287,0.0003231242,0.0003612085,0.00636672,0.0001089704,0.001946922],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003361811,"threshold_uncertainty_score":0.01777917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01469180725378792,"score_gpt":0.2611498325893621,"score_spread":0.2464580253355742,"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."}}