{"id":"W4412780893","doi":"10.1161/circimaging.125.018691","title":"AI-Enhanced Fetal CMR: Deep Learning Super-Resolution Improves Prenatal Cardiac Diagnosis","year":2025,"lang":"en","type":"letter","venue":"Circulation Cardiovascular Imaging","topic":"Fetal and Pediatric Neurological Disorders","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Medicine; Fetus; Cardiac magnetic resonance; Cardiology; Fetal echocardiography; Fetal heart; Internal medicine; Prenatal diagnosis; Radiology; Magnetic resonance imaging; Pregnancy","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":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0004762008,0.0006764672,0.0014156,0.0004816185,0.0003483166,0.0001531556,0.0002220512,0.0007221559,0.00009284908],"category_scores_gemma":[0.0005797289,0.0006671698,0.00345601,0.0006387971,0.0001704012,0.0003098689,0.0001823006,0.003009053,0.00008897813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002520092,"about_ca_system_score_gemma":0.0001544184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001487386,"about_ca_topic_score_gemma":8.260177e-7,"domain_scores_codex":[0.9954434,0.0005205019,0.0006482974,0.001337307,0.001243543,0.0008069308],"domain_scores_gemma":[0.9981827,0.0002445667,0.000164808,0.0009098219,0.0003564483,0.0001417134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001469339,0.0001639695,0.04031118,0.005572956,0.008500956,0.001777931,0.0003308089,0.01858998,0.0009607362,0.00002037787,0.314671,0.6089532],"study_design_scores_gemma":[0.001833849,0.00007756353,0.02959154,0.0003286708,0.00543873,0.0001035729,0.00005025098,0.01153273,0.0002366535,0.0001568211,0.9495816,0.001067981],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.02541393,0.2255675,0.1186657,0.583982,0.01077422,0.008676024,0.0002601047,0.003143406,0.02351705],"genre_scores_gemma":[0.7101493,0.003741048,0.0003275794,0.2681692,0.009954808,0.0008258094,0.005385628,0.0002435111,0.001203091],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.6847354,"threshold_uncertainty_score":0.9995779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008304923997091755,"score_gpt":0.2244955312431948,"score_spread":0.216190607246103,"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."}}