{"id":"W4401383183","doi":"10.1016/j.compmedimag.2024.102422","title":"Evidence modeling for reliability learning and interpretable decision-making under multi-modality medical image segmentation","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Modality (human–computer interaction); Artificial intelligence; Reliability (semiconductor); Computer science; Segmentation; Image segmentation; Image (mathematics); Machine learning; Medical decision making; Medical imaging; Pattern recognition (psychology); Computer vision; Medicine","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":[0.003841948,0.0002391055,0.0003206364,0.000211104,0.0004111484,0.000884523,0.0005733365,0.0001480045,0.00001814437],"category_scores_gemma":[0.003645609,0.0002123088,0.0001049223,0.0004732038,0.0003791646,0.001296123,0.0007673668,0.000656609,0.000003621829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005584354,"about_ca_system_score_gemma":0.0002548119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006271036,"about_ca_topic_score_gemma":0.00001426084,"domain_scores_codex":[0.9969255,0.0002367819,0.0005991777,0.0009477672,0.0008336924,0.000457072],"domain_scores_gemma":[0.9954292,0.003566798,0.00006764204,0.0003100263,0.000220403,0.0004059223],"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":[0.00006291551,0.00009921512,0.0007240704,0.0005946656,0.00004587826,0.0001381911,0.001941188,0.001376735,0.0008934659,0.02208043,0.0001768391,0.9718664],"study_design_scores_gemma":[0.0002203348,0.0000383383,0.0000567357,0.002425062,0.00001658307,0.00008302077,0.0001638292,0.9489591,0.00008595395,0.04753274,0.0001978814,0.0002204147],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03126004,0.003455683,0.9559226,0.00788106,0.0008019786,0.0002718168,0.000001411615,0.0003950054,0.0000103779],"genre_scores_gemma":[0.7820655,0.001255848,0.2156617,0.0008543487,0.0001047844,0.0000310771,0.000002594438,0.00001817002,0.000006009598],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.971646,"threshold_uncertainty_score":0.8657702,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03767035799504188,"score_gpt":0.3738711265333765,"score_spread":0.3362007685383346,"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."}}