{"id":"W3043602140","doi":"10.1136/gutjnl-2019-319866","title":"Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning","year":2020,"lang":"en","type":"article","venue":"Gut","topic":"AI in cancer detection","field":"Computer Science","cited_by":272,"is_retracted":false,"has_abstract":true,"ca_institutions":"Discovery Centre","funders":"NIHR Oxford Biomedical Research Centre; Medical Research Council; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; Wellcome Trust; Academy of Medical Sciences; Biomedical Research Council; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Cancer Research UK; National Science Foundation","keywords":"Colorectal cancer; Random forest; Grading (engineering); Medicine; Tumour heterogeneity; Precision medicine; Gene expression profiling; Pathology; Oncology; Internal medicine; Artificial intelligence; Computational biology; Bioinformatics; Cancer; Biology; Gene expression; Gene; Computer science; Genetics","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":[0.0001030765,0.00008498266,0.0001185069,0.00004773926,0.00006862889,0.00003699615,0.0002419597,0.00005286098,0.00001881296],"category_scores_gemma":[0.00008863315,0.00009465934,0.00004690409,0.000446732,0.00006459409,0.00008542235,0.00005511222,0.0001446113,0.00001381944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001171934,"about_ca_system_score_gemma":0.0001801133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001236646,"about_ca_topic_score_gemma":0.00001531382,"domain_scores_codex":[0.9991133,0.00008879673,0.0001741088,0.0002684402,0.000211434,0.0001439453],"domain_scores_gemma":[0.9994178,0.00004983904,0.0001716356,0.0001498562,0.0001504468,0.00006038238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003197293,0.000008698417,0.001882874,0.00002948657,0.00001223045,0.000007641499,0.0003005895,0.02431005,0.9624467,0.0002706186,0.00003389925,0.01066521],"study_design_scores_gemma":[0.0002080634,0.0000741685,0.003342665,0.00001192714,0.00001060426,0.000002482288,0.00002717912,0.8473352,0.1485718,0.00004664686,0.0002777984,0.00009147747],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4479643,0.0001226412,0.5504913,0.0008739746,0.0001538389,0.00008681689,0.000001101156,0.00009085804,0.0002151896],"genre_scores_gemma":[0.9469616,0.000004185184,0.05279454,0.0001768048,0.00003938771,0.000008572273,0.000001305035,0.0000107705,0.000002802182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8230251,"threshold_uncertainty_score":0.3860096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03426763760177132,"score_gpt":0.2807247083307751,"score_spread":0.2464570707290037,"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."}}