{"id":"W4410954986","doi":"10.1016/j.jocmr.2025.101920","title":"Referenceless 4D flow cardiovascular magnetic resonance with deep learning","year":2025,"lang":"en","type":"article","venue":"Journal of Cardiovascular Magnetic Resonance","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Linköpings Universitet; Alberta Law Foundation","keywords":"Medicine; Angiology; Magnetic resonance imaging; Cardiac magnetic resonance; Nuclear magnetic resonance; Cardiology; Radiology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001182417,0.0008263178,0.0005660192,0.000740891,0.0002136648,0.0007288276,0.00116784,0.001262133,0.001791257],"category_scores_gemma":[0.002506647,0.0004125666,0.0006957577,0.0004981065,0.0004836881,0.0006355824,0.0009653019,0.001129155,0.0008360238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005936733,"about_ca_system_score_gemma":0.0008067678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004225482,"about_ca_topic_score_gemma":0.003842082,"domain_scores_codex":[0.9997349,0.00007356713,0.00001460781,0.00007701128,0.00006380424,0.00003607302],"domain_scores_gemma":[0.9995052,0.0002325907,0.00007306686,0.00007112075,0.00008918347,0.00002892245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002853348,0.0001414551,0.00322243,0.0001771551,0.0001328907,0.0001849153,0.00004676835,0.6615315,0.005845994,0.003722342,0.005174444,0.3195348],"study_design_scores_gemma":[0.000009658872,0.00003224867,0.0002587099,0.00001240086,0.000009476968,0.00004778172,0.000002411103,0.9953498,0.001560954,0.00205577,0.0006534382,0.000007389875],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04046299,0.001685111,0.9523271,0.0005075003,0.0001061942,0.00006956888,0.0005338768,0.002780985,0.001526639],"genre_scores_gemma":[0.6785771,0.0009699382,0.3142423,0.0005733266,0.0001425586,0.0002156579,0.001611034,0.0002552463,0.003412975],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004225482,"threshold_uncertainty_score":0.008401811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008606397094834064,"score_gpt":0.2439154414967204,"score_spread":0.2353090444018864,"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."}}