{"id":"W3003953721","doi":"10.59275/j.melba.2021-8678","title":"A Heteroscedastic Uncertainty Model for Decoupling Sources of MRI Image Quality","year":2021,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Nvidia; F. Hoffmann-La Roche; Alzheimer's Society; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Computer science; Artificial intelligence; Probabilistic logic; Segmentation; Data mining; Machine learning; Heteroscedasticity; Uncertainty quantification; Robustness (evolution); Image quality; Noise (video); Quality (philosophy); Pattern recognition (psychology); Image (mathematics)","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.009861782,0.0005059663,0.001264466,0.0004130683,0.0004987174,0.0003290709,0.003090968,0.0002186532,0.000009348427],"category_scores_gemma":[0.005727358,0.0003698091,0.0009103561,0.0003305241,0.0004817003,0.0004117063,0.002252797,0.002876642,4.365624e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000181495,"about_ca_system_score_gemma":0.000711335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000134198,"about_ca_topic_score_gemma":0.000007096745,"domain_scores_codex":[0.9949695,0.0007546973,0.001934866,0.0005557297,0.001120638,0.0006645288],"domain_scores_gemma":[0.9904662,0.004007982,0.003500273,0.0007394996,0.001033644,0.0002524077],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002215425,0.0001084349,0.0006433186,0.0007715645,0.0002674019,0.00001181184,0.003045839,0.978115,0.0023838,0.0002940233,0.00006899701,0.01406825],"study_design_scores_gemma":[0.0014137,0.0001450907,0.0001087866,0.0007948451,0.000300011,0.0001227898,0.0003212271,0.9916354,0.0002478854,0.004342117,0.0002034531,0.0003646536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03811066,0.001456225,0.9545729,0.004203389,0.00111781,0.0004247673,0.00002369049,0.00007689834,0.00001372446],"genre_scores_gemma":[0.6570058,0.00007649804,0.3421811,0.0001564427,0.0004294853,0.00001392308,0.00003484571,0.00005867177,0.00004317655],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6188952,"threshold_uncertainty_score":0.9998754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02763975736512384,"score_gpt":0.3395162783419846,"score_spread":0.3118765209768607,"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."}}