{"id":"W4412688249","doi":"10.1016/j.knosys.2025.114123","title":"BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averaging","year":2025,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Bayesian probability; Computer science; Artificial intelligence; Test (biology); Bayesian inference; Pattern recognition (psychology); Machine learning; Statistics; Data mining; Mathematics; Geology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001839239,0.001310488,0.001941992,0.00131402,0.0005299975,0.00162204,0.002757014,0.002024042,0.004864249],"category_scores_gemma":[0.006774277,0.0009378028,0.001623625,0.001143672,0.0006079284,0.001983517,0.00254318,0.003044582,0.002674177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001097219,"about_ca_system_score_gemma":0.00247992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01286641,"about_ca_topic_score_gemma":0.01876061,"domain_scores_codex":[0.9988523,0.0002269596,0.00006875813,0.0002861752,0.0004481959,0.0001176911],"domain_scores_gemma":[0.9980317,0.0009671735,0.0001300108,0.0003160177,0.0004451177,0.0001100219],"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":[0.0006350946,0.0002797773,0.001132281,0.0001582664,0.0002521064,0.0001190142,0.00009178385,0.1794936,0.01377685,0.005047539,0.01801905,0.7809947],"study_design_scores_gemma":[0.0000147947,0.00003395982,0.0001837676,0.000007455032,0.00002076801,0.00004070303,0.000005985084,0.9914691,0.003259664,0.003760863,0.001190079,0.00001272795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004181257,0.0003881166,0.9833869,0.0002322444,0.0000791359,0.00007874322,0.000333875,0.01059052,0.0007292677],"genre_scores_gemma":[0.1908216,0.0003552524,0.8001952,0.0005725517,0.000207934,0.0003578098,0.002068846,0.001198382,0.004222492],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01286641,"threshold_uncertainty_score":0.02558303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02890409014786394,"score_gpt":0.338301466179972,"score_spread":0.3093973760321081,"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."}}