{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01946381,0.001510317,0.003895957,0.003718647,0.0008823519,0.003991158,0.004076988,0.004038068,0.003298911],"category_scores_gemma":[0.1138789,0.00157965,0.00265141,0.002146002,0.00341543,0.005482666,0.003291099,0.00482221,0.0002977821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00340932,"about_ca_system_score_gemma":0.002687022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00879884,"about_ca_topic_score_gemma":0.005557161,"domain_scores_codex":[0.9898604,0.005830999,0.0008649142,0.001660511,0.001321463,0.0004617706],"domain_scores_gemma":[0.8446219,0.1418973,0.00480972,0.003194559,0.004397388,0.001079117],"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":[0.0004985468,0.0001699598,0.003755272,0.0004689009,0.0004317595,0.0003957152,0.0005272513,0.8308529,0.0006303526,0.1047846,0.0009876553,0.05649707],"study_design_scores_gemma":[0.00002127216,0.00003378182,0.0002597557,0.00004604609,0.00004503919,0.00002823686,0.00001757879,0.9389464,0.0002171355,0.0602343,0.0001367767,0.00001372336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02596651,0.0006821865,0.9707443,0.001428517,0.00003647143,0.0001027855,0.0002118321,0.0001784835,0.0006489138],"genre_scores_gemma":[0.7670823,0.0007240264,0.2288107,0.0003466069,0.0002449621,0.0003921332,0.0005837376,0.00008125734,0.001734226],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01946381,"threshold_uncertainty_score":0.1029357,"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."}}