{"id":"W3141548126","doi":"10.1109/access.2021.3070320","title":"Automated Segmental Analysis of Fully Quantitative Myocardial Blood Flow Maps by First-Pass Perfusion Cardiovascular Magnetic Resonance","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Circle Cardiovascular Imaging","funders":"National Heart, Lung, and Blood Institute; Medical Research Council; National Institutes of Health; University of Glasgow; British Heart Foundation","keywords":"Segmentation; Coefficient of variation; Perfusion; Magnetic resonance imaging; Pearson product-moment correlation coefficient; Correlation coefficient; Blood flow; Sørensen–Dice coefficient; Coronary artery disease; Nuclear medicine; Computer science; Artificial intelligence; Medicine; Myocardial perfusion imaging; Image segmentation; Mathematics; Cardiology; Radiology; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001260417,0.0001662889,0.0006139368,0.000138615,0.000104902,0.00002606745,0.0001794505,0.00009969353,0.0001210135],"category_scores_gemma":[0.00003375301,0.0001606028,0.00050345,0.001463581,0.00008415696,0.0001236513,0.00008596619,0.0001308987,0.000005766308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005497499,"about_ca_system_score_gemma":0.00006844258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001579241,"about_ca_topic_score_gemma":0.00004189173,"domain_scores_codex":[0.9985758,0.00005203781,0.000329032,0.00043186,0.0003989498,0.0002123365],"domain_scores_gemma":[0.9988608,0.00006351103,0.00008684766,0.0006131412,0.0002835428,0.00009213654],"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":[0.001013764,0.005404843,0.06503956,0.0008029378,0.01254473,0.001312385,0.002313025,0.05643393,0.5885999,0.001063489,0.08767061,0.1778008],"study_design_scores_gemma":[0.005741014,0.0009516363,0.09773604,0.0004343696,0.02462049,0.0001354299,0.0006219019,0.1384644,0.6099157,0.0002622785,0.1200233,0.001093526],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9097651,0.02244521,0.06347777,0.0005852727,0.000132922,0.0008838254,0.0009610521,0.0005475088,0.001201306],"genre_scores_gemma":[0.9509469,0.003293688,0.0441651,0.0002464729,0.00007772387,0.0002079186,0.0006711175,0.0000440935,0.000346985],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1767073,"threshold_uncertainty_score":0.6549191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01757146673718313,"score_gpt":0.3128388425103251,"score_spread":0.2952673757731419,"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."}}