{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001993436,0.00008306019,0.0002100222,0.0004623267,0.0001347058,0.0001812191,0.001011557,0.00002640814,0.00000385423],"category_scores_gemma":[0.0001474651,0.00006912569,0.00002115098,0.0007964016,0.0001338147,0.002836142,0.0002335578,0.0001104968,5.153221e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002111406,"about_ca_system_score_gemma":0.0005914446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001603426,"about_ca_topic_score_gemma":0.00003239801,"domain_scores_codex":[0.9983263,0.00007076665,0.0006190348,0.0002827513,0.0005310725,0.0001700657],"domain_scores_gemma":[0.9983039,0.0001603747,0.0005197814,0.0002604283,0.0006970684,0.00005838005],"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":[0.0007486704,0.0005353275,0.05173056,0.001399235,0.0002256189,0.00002558817,0.009551349,0.0261718,0.3494766,0.004266154,0.01655543,0.5393137],"study_design_scores_gemma":[0.002440933,0.001029991,0.01020258,0.006283125,0.0001113635,0.0004517992,0.01116778,0.7822847,0.174336,0.000664255,0.01046696,0.0005605508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1613913,0.002231683,0.8310239,0.001422973,0.00281483,0.0007912801,0.00009346345,0.00001635864,0.0002141648],"genre_scores_gemma":[0.9950384,0.000650168,0.004048654,0.0000664109,0.0001201589,0.00002091421,0.000002741679,0.000003667487,0.00004880709],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8336471,"threshold_uncertainty_score":0.2818864,"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."}}