{"id":"W4388818696","doi":"10.1016/j.media.2023.103033","title":"An efficient semi-supervised quality control system trained using physics-based MRI-artefact generators and adversarial training","year":2023,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Department of Health and Social Care; National Institute for Health and Care Research; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Medical Research Council; Biogen; Engineering and Physical Sciences Research Council; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; University College London Hospitals NHS Foundation Trust; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Association","keywords":"Artificial intelligence; Computer science; Support vector machine; Process (computing); Set (abstract data type); Machine learning; Quality (philosophy); Feature (linguistics); Class (philosophy); Pattern recognition (psychology)","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001938006,0.0003082836,0.0007324685,0.0002889714,0.0002091183,0.0001070031,0.0003197639,0.0002634719,0.00008872339],"category_scores_gemma":[0.0003599813,0.0002845828,0.0005547426,0.001301334,0.0002531106,0.00001340642,0.00007234899,0.0001779615,0.000007175765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004982628,"about_ca_system_score_gemma":0.0001952051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002486794,"about_ca_topic_score_gemma":0.00008123567,"domain_scores_codex":[0.9968575,0.0006147801,0.0006017638,0.0008202016,0.0006347258,0.0004710363],"domain_scores_gemma":[0.9983975,0.0000856961,0.0001796067,0.0007192169,0.0001865171,0.0004314775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001008017,0.0001562063,0.002112351,0.0000636856,0.001851175,0.00008815573,0.0002449401,0.01493388,0.975435,0.00001182517,0.0002190473,0.004782895],"study_design_scores_gemma":[0.001432498,0.00008587725,0.0006873354,0.00001812304,0.001823369,0.000002936938,0.0006868025,0.9280018,0.06681285,0.00000368536,0.00009733191,0.0003474065],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5824649,0.00005018468,0.4170251,0.0000876832,0.00002210827,0.0001309707,0.00002803118,0.0001302788,0.00006071936],"genre_scores_gemma":[0.995762,0.00001644209,0.002661393,0.0003811394,0.000427918,0.00002710061,0.0006692063,0.00003747752,0.00001732066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9130679,"threshold_uncertainty_score":0.9999607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01800974484297407,"score_gpt":0.3180659777950156,"score_spread":0.3000562329520415,"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."}}