{"id":"W4412433844","doi":"10.1016/j.media.2025.103711","title":"CLASS-M: Adaptive stain separation-based contrastive learning with pseudo-labeling for histopathological image classification","year":2025,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; ARUP Laboratories; National Institutes of Health; Huntsman Cancer Institute; University of Utah","keywords":"Artificial intelligence; Class (philosophy); Pattern recognition (psychology); Stain; Computer science; Computer vision; Image (mathematics); Mathematics; Pathology; Medicine; Staining","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":[0.001378488,0.0008847214,0.0007635415,0.0009675688,0.0003488902,0.0007719689,0.002938276,0.001345814,0.002478475],"category_scores_gemma":[0.002238826,0.0004618915,0.001247429,0.0007052164,0.0007319542,0.001248854,0.001244569,0.001550034,0.00128296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008438242,"about_ca_system_score_gemma":0.0008643183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002380528,"about_ca_topic_score_gemma":0.003934828,"domain_scores_codex":[0.999471,0.0001145625,0.00002032303,0.000193088,0.0001477332,0.00005322677],"domain_scores_gemma":[0.9992072,0.0003125282,0.00008082431,0.0001906705,0.0001619609,0.00004670838],"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":[0.0004632372,0.0003733934,0.004185996,0.0001900817,0.0001874445,0.0001261652,0.0001182826,0.1607874,0.02554356,0.008590625,0.01301822,0.7864155],"study_design_scores_gemma":[0.00001164787,0.00004905134,0.0003994842,0.000006840909,0.00001063871,0.00004883728,0.000004944641,0.9896086,0.00535077,0.002911756,0.001587812,0.000009680647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01604497,0.0003277092,0.9771855,0.0001753054,0.00005332529,0.0001516948,0.0002163255,0.004776451,0.00106864],"genre_scores_gemma":[0.3042736,0.0002952005,0.6858374,0.0005258509,0.0001227216,0.0005568205,0.001374351,0.0006498599,0.006364184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002938276,"threshold_uncertainty_score":0.008291364,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01408807863486378,"score_gpt":0.3105851636818431,"score_spread":0.2964970850469793,"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."}}