{"id":"W4365504611","doi":"10.1007/s10278-023-00797-x","title":"DeepBLS: Deep Feature-Based Broad Learning System for Tissue Phenotyping in Colorectal Cancer WSIs","year":2023,"lang":"en","type":"article","venue":"Journal of Digital Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Terry Fox Foundation","keywords":"Computer science; Grading (engineering); Colorectal cancer; Artificial intelligence; Stroma; Deep learning; Feature extraction; Digital pathology; Histology; Pattern recognition (psychology); Feature (linguistics); Pathology; Cancer; Medicine; Biology; Immunohistochemistry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000473161,0.0001464724,0.000261682,0.0004817665,0.0001253686,0.0005799907,0.0004610803,0.00003577519,0.000001199901],"category_scores_gemma":[0.0001940635,0.0001425657,0.0001247293,0.0008985187,0.00002729241,0.0017942,0.00009118169,0.0003291075,0.000008176278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006408638,"about_ca_system_score_gemma":0.0001816876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002233578,"about_ca_topic_score_gemma":0.0000238451,"domain_scores_codex":[0.9986383,0.00004136842,0.0003915722,0.0002315895,0.0003333703,0.0003637652],"domain_scores_gemma":[0.9988818,0.000288009,0.0004071551,0.0001065337,0.0002281014,0.00008843997],"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":[0.000138762,0.00003862948,0.03511317,0.0002698426,0.00006368237,0.0002051837,0.001360844,0.1025851,0.01222894,0.0001866551,0.0007602811,0.8470489],"study_design_scores_gemma":[0.001578414,0.0001702276,0.005054357,0.0008838864,0.00002351852,0.0002019646,0.0005963623,0.9618823,0.02560401,0.0004626521,0.003202232,0.0003400696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1140588,0.001035972,0.8802351,0.001535343,0.002152491,0.0002365097,0.000004337781,0.0002380537,0.0005033407],"genre_scores_gemma":[0.9946865,0.000009212496,0.004865572,0.00004585112,0.0003028574,0.00002118003,0.000001355028,0.00002472074,0.00004274179],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8806277,"threshold_uncertainty_score":0.5813658,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01221183604583104,"score_gpt":0.2756273847826754,"score_spread":0.2634155487368444,"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."}}