{"id":"W3157026294","doi":"10.59275/j.melba.2021-a6fd","title":"Recalibration of Aleatoric and EpistemicRegression Uncertainty in Medical Imaging","year":2021,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"European Regional Development Fund; European Commission","keywords":"Uncertainty quantification; Computer science; Regression; Inference; Calibration; Bayesian probability; Dropout (neural networks); Machine learning; Sensitivity analysis; Predictive inference; Artificial intelligence; Monte Carlo method; Bayesian inference; Econometrics; Statistics; Uncertainty analysis; Mathematics; Frequentist inference","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":[0.003646031,0.0002186949,0.0005375674,0.0003314682,0.0001150238,0.0001591188,0.001185773,0.0001286433,0.00001850133],"category_scores_gemma":[0.001544094,0.0001392626,0.0001333544,0.000383417,0.0002587557,0.0003110162,0.001066622,0.001684244,1.702429e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006683463,"about_ca_system_score_gemma":0.0006105825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001252958,"about_ca_topic_score_gemma":0.000005553688,"domain_scores_codex":[0.9971328,0.000484787,0.001006249,0.0002773423,0.0008239878,0.0002747717],"domain_scores_gemma":[0.9973793,0.0007468504,0.001165138,0.0002656808,0.0002507954,0.0001922506],"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":[0.0001586232,0.0002296436,0.02715387,0.001755206,0.00009248446,0.000341338,0.003945339,0.002223877,0.00269608,0.001555433,0.0004605382,0.9593875],"study_design_scores_gemma":[0.0008618381,0.00006734017,0.001867457,0.004001748,0.00004479096,0.0009885037,0.0002232194,0.9846851,0.0002311123,0.006055295,0.0007793911,0.0001941767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03492722,0.01027829,0.9320402,0.02186983,0.0006696995,0.0001403347,0.000002540841,0.000022402,0.00004947114],"genre_scores_gemma":[0.9851345,0.001284154,0.01313146,0.0002147055,0.0001893257,0.000003072242,0.00001371511,0.000016206,0.00001289119],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9824613,"threshold_uncertainty_score":0.7317297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009173376499591528,"score_gpt":0.2787949627953283,"score_spread":0.2696215862957367,"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."}}