{"id":"W4412610790","doi":"10.1109/aaicv66571.2025.00060","title":"Optimizing MCMC-Driven Bayesian Neural Networks for High-Precision Medical Image Classification in Small Sample Sizes","year":2025,"lang":"en","type":"article","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov chain Monte Carlo; Computer science; Artificial intelligence; Bayesian probability; Sample (material); Pattern recognition (psychology); Artificial neural network; Sample size determination; Machine learning; Statistics; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005730162,0.001460085,0.002250492,0.001494296,0.0008615359,0.001502576,0.003126493,0.003071659,0.002302819],"category_scores_gemma":[0.01909777,0.001663994,0.001423458,0.001655321,0.001451732,0.002104164,0.001589465,0.003808635,0.001103039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003545824,"about_ca_system_score_gemma":0.002932056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02857167,"about_ca_topic_score_gemma":0.0305646,"domain_scores_codex":[0.9982627,0.0007537667,0.00009055048,0.0003923828,0.0003597234,0.0001408177],"domain_scores_gemma":[0.991061,0.00686865,0.0005381012,0.0004765154,0.0008667163,0.0001889999],"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":[0.000132849,0.00004518731,0.0007006131,0.00006438805,0.00005627934,0.00003760327,0.00003777072,0.9281728,0.0008579447,0.004156296,0.001135745,0.06460252],"study_design_scores_gemma":[0.000004492088,0.000004402642,0.00003882675,0.000003437746,0.000002388302,0.000003699326,0.000001162638,0.9980522,0.0001523811,0.001671506,0.00006294882,0.000002504214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009456153,0.0003396319,0.9883024,0.0003149465,0.00002323503,0.00006024656,0.00008943991,0.0008981358,0.0005157466],"genre_scores_gemma":[0.3124834,0.0005166998,0.6808175,0.0006907745,0.0001393616,0.0005311075,0.0009213191,0.0004378674,0.003461922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02857167,"threshold_uncertainty_score":0.05681074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02226381224629883,"score_gpt":0.2840203458086907,"score_spread":0.2617565335623919,"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."}}