{"id":"W4394688228","doi":"10.1016/j.eswa.2024.123923","title":"One-step abductive multi-target learning with diverse noisy samples and its application to tumour segmentation for breast cancer","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Segmentation; Artificial intelligence; Machine learning; Breast cancer; Pattern recognition (psychology); Cancer; Computer vision; Medicine; Internal 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":[0.0002054989,0.00018269,0.0001733114,0.0001559381,0.0004215839,0.0003192431,0.0002897401,0.00004934237,0.000003469398],"category_scores_gemma":[0.00001029102,0.0001512501,0.00002117112,0.0005309171,0.00002751508,0.0005100544,0.00006252679,0.0001304222,0.0000390107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001255341,"about_ca_system_score_gemma":0.0000894035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006531951,"about_ca_topic_score_gemma":0.0001040862,"domain_scores_codex":[0.9985055,0.00005942318,0.0002146759,0.0007638879,0.0002380014,0.0002185591],"domain_scores_gemma":[0.9990383,0.0001148001,0.0001259103,0.0003471005,0.0002291943,0.0001446963],"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":[0.0002946173,0.0006138596,0.009208514,0.001667198,0.0005584058,0.00000331291,0.02275019,0.05151178,0.1587899,0.34573,0.002290588,0.4065816],"study_design_scores_gemma":[0.0008131397,0.0002041132,0.01102957,0.0003535296,0.00005335174,0.00006610945,0.002608242,0.8856149,0.001592489,0.00005991277,0.09697014,0.0006345065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009699694,0.001158791,0.9925004,0.002217902,0.0000620686,0.002477949,0.0001626036,0.0004061725,0.00004419959],"genre_scores_gemma":[0.8411977,0.00006101979,0.1431968,0.00008675329,0.0002614245,0.0146147,0.0001900643,0.00003623056,0.0003553361],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8493036,"threshold_uncertainty_score":0.6167801,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02848520687439513,"score_gpt":0.3033992285075345,"score_spread":0.2749140216331394,"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."}}