{"id":"W2343327095","doi":"10.1109/jbhi.2015.2503720","title":"Circular Mixture Modeling of Color Distribution for Blind Stain Separation in Pathology Images","year":2015,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Stain; Artificial intelligence; Hue; Pattern recognition (psychology); Computer science; Matrix decomposition; Pixel; Non-negative matrix factorization; Segmentation; Cluster analysis; Computer vision; Mathematics; Pathology; Staining; Eigenvalues and eigenvectors; Physics","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":[0.002348815,0.00005831343,0.0002230392,0.0001468319,0.00003995929,0.00002069647,0.0001417197,0.00009562751,2.44842e-7],"category_scores_gemma":[0.00009342092,0.00004606381,0.0000293661,0.0002081849,0.00005163558,0.0004315277,0.00002199527,0.0001660977,2.431036e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001723632,"about_ca_system_score_gemma":0.0005573232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009271662,"about_ca_topic_score_gemma":0.000003440711,"domain_scores_codex":[0.998503,0.00004189039,0.000969805,0.0000440722,0.0002879856,0.0001532572],"domain_scores_gemma":[0.9988008,0.00004325521,0.0006247208,0.00007268476,0.0002862715,0.0001722508],"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":[0.001910267,0.001231355,0.001484746,0.008150959,0.0001704122,0.00006798669,0.08102933,0.09324092,0.001743955,0.007877605,0.05560974,0.7474827],"study_design_scores_gemma":[0.001698393,0.001275107,0.00009620747,0.00009549061,0.000004669626,0.0001460059,0.0004322078,0.9891813,0.0002150507,0.004937816,0.001863805,0.00005392279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08991958,0.0002441652,0.9056959,0.003537446,0.0004398876,0.0001396731,0.00001449275,0.000004660193,0.00000418685],"genre_scores_gemma":[0.9407126,0.0002256381,0.0585142,0.0003831387,0.0001478254,0.000004223734,0.000008503484,0.000002434685,0.000001454315],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8959404,"threshold_uncertainty_score":0.1878428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06466379736720057,"score_gpt":0.3648212359058522,"score_spread":0.3001574385386517,"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."}}