{"id":"W4408205304","doi":"10.47852/bonviewjdsis52024868","title":"Experts' Cognition-driven Safe Noisy Labels Learning for Precise Segmentation of Residual Tumor in Breast Cancer","year":2025,"lang":"en","type":"article","venue":"Journal of Data Science and Intelligent Systems","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Breast cancer; Machine learning; Artificial intelligence; Cognition; Conceptualization; Segmentation; Residual; Generalization; Natural language processing; Cancer; Medicine; Algorithm; 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":[0.003300075,0.001055834,0.001171477,0.001064063,0.0007189268,0.001536284,0.001979487,0.0016918,0.001189674],"category_scores_gemma":[0.009375148,0.0004470326,0.001503536,0.0005554153,0.001252057,0.002162474,0.002576692,0.001847281,0.0003842639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001360225,"about_ca_system_score_gemma":0.002176071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005994596,"about_ca_topic_score_gemma":0.009417512,"domain_scores_codex":[0.9978784,0.0005841333,0.000110544,0.0007873619,0.0004331461,0.0002064194],"domain_scores_gemma":[0.9960193,0.001987339,0.0004119351,0.0005161992,0.0007676579,0.0002976932],"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":[0.0009741263,0.0005027373,0.02439348,0.0004888224,0.0003363176,0.0004773331,0.001782064,0.376074,0.01970681,0.01262079,0.00904893,0.5535945],"study_design_scores_gemma":[0.00002754808,0.00009123874,0.001373593,0.00002562806,0.00004756024,0.0000596992,0.0001170826,0.98369,0.003684279,0.009727943,0.00113154,0.00002393286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08608449,0.0005704028,0.9089774,0.000771532,0.00008683551,0.0001235262,0.0002291923,0.001552553,0.001604084],"genre_scores_gemma":[0.7916185,0.000322344,0.2030376,0.0008041321,0.0001357726,0.0001976042,0.001293677,0.0001906982,0.00239972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005994596,"threshold_uncertainty_score":0.01745266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04692141047577228,"score_gpt":0.3507744324729029,"score_spread":0.3038530219971306,"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."}}