{"id":"W4394807477","doi":"10.1016/j.jocmr.2024.100142","title":"Automatic Snr-driven Quality Control of 2D Phase-contrast Flow MR Imaging Using Closed-loop Feedback Between Image Reconstruction and Data Acquisition","year":2024,"lang":"en","type":"article","venue":"Journal of Cardiovascular Magnetic Resonance","topic":"Characterization and Applications of Magnetic Nanoparticles","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Siemens (Canada)","funders":"","keywords":"Medicine; Phase contrast microscopy; Angiology; Contrast (vision); Image quality; Data acquisition; Artificial intelligence; Computer vision; Closed loop; Loop (graph theory); Radiology; Image (mathematics); Computer science; Internal medicine; Mathematics; Optics","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":[0.001038586,0.0001782835,0.0005804796,0.0001598985,0.00005287782,0.0001473426,0.0002631277,0.00006044962,0.00007260625],"category_scores_gemma":[0.00008441124,0.0001752755,0.0002471598,0.0002727713,0.0001336587,0.0005935222,0.00004503277,0.000190446,0.000003894943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005261814,"about_ca_system_score_gemma":0.00005409121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007387863,"about_ca_topic_score_gemma":3.403916e-7,"domain_scores_codex":[0.998122,0.0001438028,0.0008838706,0.0002384559,0.0004190204,0.0001928969],"domain_scores_gemma":[0.9988687,0.0001501378,0.0001465512,0.0005548901,0.0001810593,0.00009864209],"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":[0.00001261497,0.00002036145,0.0004333827,0.0002884399,0.0002448357,0.00001496223,0.00007007064,0.001226902,0.06639306,0.00001940064,0.0000817551,0.9311942],"study_design_scores_gemma":[0.002852359,0.00006548855,0.02418161,0.0006514963,0.0009707465,0.000428087,0.00008501173,0.9559538,0.00463009,0.0001502493,0.00977059,0.0002604825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8071591,0.09437115,0.09753482,0.0001192877,0.0002737405,0.0002490374,0.0001785676,0.00006596022,0.00004831143],"genre_scores_gemma":[0.9787958,0.002950995,0.01784416,0.00001104823,0.0003391874,0.000004595492,0.00001606003,0.00003360775,0.000004561981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9547269,"threshold_uncertainty_score":0.714753,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01849300029191797,"score_gpt":0.2739082019027953,"score_spread":0.2554152016108773,"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."}}