{"id":"W4394827596","doi":"10.1016/j.jocmr.2024.100189","title":"Reducing the Contrast Dose by 80% in Quantitative Perfusion CMR Enabled by Patch-wise Deep Learning","year":2024,"lang":"en","type":"article","venue":"Journal of Cardiovascular Magnetic Resonance","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Angiology; Medicine; Contrast (vision); Perfusion; Deep learning; Medical physics; Radiology; Nuclear medicine; Internal medicine; Artificial intelligence; Computer science","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":[0.0004626398,0.0004334087,0.0003441126,0.0001597877,0.0001125246,0.0004340746,0.0005221758,0.0006902438,0.001338895],"category_scores_gemma":[0.001161942,0.0002113378,0.000213555,0.0001679228,0.0002348257,0.0006615136,0.0005293781,0.0008900474,0.0002678738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001869622,"about_ca_system_score_gemma":0.0004039114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001187172,"about_ca_topic_score_gemma":0.001928906,"domain_scores_codex":[0.9998875,0.00003360631,0.000004977932,0.00002915894,0.00002491883,0.00001982997],"domain_scores_gemma":[0.9997981,0.0001133028,0.00001592305,0.00002272448,0.00003106263,0.00001876591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002106213,0.0005337929,0.001734979,0.0005412633,0.0001594389,0.0004268108,0.0001028624,0.07765488,0.4759801,0.003759375,0.006286427,0.4307138],"study_design_scores_gemma":[0.00007157002,0.0005630669,0.001500431,0.00003819063,0.00009961714,0.0004111118,0.00002260201,0.817265,0.1747098,0.002304937,0.002982516,0.00003119032],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3785767,0.002175538,0.611312,0.00100555,0.0002076419,0.00009116211,0.0003171286,0.002236106,0.004078144],"genre_scores_gemma":[0.8804959,0.0004315746,0.1166095,0.0002913754,0.00003857534,0.0000384034,0.0001907897,0.0002189603,0.001684714],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001338895,"threshold_uncertainty_score":0.004479051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01033005073224718,"score_gpt":0.270972420949015,"score_spread":0.2606423702167678,"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."}}