{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001197156,0.0002037674,0.0004221316,0.000460003,0.0003598601,0.0001833596,0.0005250771,0.0001651297,0.00007076859],"category_scores_gemma":[0.001192038,0.0001669492,0.0002055616,0.002252685,0.0002912201,0.0004124049,0.00006905846,0.0004304597,0.00001247612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004098533,"about_ca_system_score_gemma":0.0005057902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000504801,"about_ca_topic_score_gemma":0.0001045299,"domain_scores_codex":[0.9974774,0.0003294162,0.0004278569,0.0007655967,0.0006596661,0.0003400499],"domain_scores_gemma":[0.9976684,0.0008966859,0.0002389128,0.0004048412,0.0006432987,0.0001477957],"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":[0.003380933,0.002453186,0.03741879,0.0004379345,0.007507587,0.000811872,0.003505106,0.06529398,0.1088709,0.08520269,0.01441673,0.6707003],"study_design_scores_gemma":[0.0008168381,0.0002637249,0.002367788,0.00003287024,0.0005158008,0.000002161956,0.0001840544,0.9924109,0.001775438,0.0005108808,0.0009302427,0.0001893222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004119258,0.00006798036,0.9898545,0.004315848,0.00009068211,0.0003065921,0.000005376753,0.0002329512,0.001006799],"genre_scores_gemma":[0.787241,0.00001055194,0.2109731,0.0008755678,0.00006846972,0.0002734943,0.00004385531,0.00001066262,0.0005032998],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9271169,"threshold_uncertainty_score":0.680799,"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."}}