{"id":"W3165497806","doi":"10.1016/j.ajpath.2021.05.005","title":"Deep-Learning–Driven Quantification of Interstitial Fibrosis in Digitized Kidney Biopsies","year":2021,"lang":"en","type":"article","venue":"American Journal Of Pathology","topic":"Systemic Sclerosis and Related Diseases","field":"Medicine","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"William Osler Health System; Queen's University","funders":"National Center for Advancing Translational Sciences; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; Bundesministerium für Bildung und Forschung; Boston University; National Institute on Aging; Deutsche Forschungsgemeinschaft; American Heart Association; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Pathology; Fibrosis; Kidney; Medicine; Computer science; Internal medicine","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":[0.0008044342,0.000370456,0.0003629396,0.0007419031,0.0001555049,0.0007673256,0.0004379673,0.0007871696,0.0008603955],"category_scores_gemma":[0.001647038,0.0002876741,0.0003640807,0.0004202895,0.0002271945,0.0003421812,0.0004353507,0.0005051615,0.0003194484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003913241,"about_ca_system_score_gemma":0.0005665165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003621028,"about_ca_topic_score_gemma":0.007533224,"domain_scores_codex":[0.9997674,0.00005458897,0.00001292238,0.00005675137,0.00007367443,0.00003476793],"domain_scores_gemma":[0.9995795,0.0001718874,0.00005875013,0.00004315346,0.0001176522,0.00002909641],"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":[0.001082581,0.0003742221,0.04412945,0.0006818627,0.0003403619,0.000619882,0.0002226253,0.3261076,0.1770707,0.002999479,0.005500774,0.4408706],"study_design_scores_gemma":[0.00001585684,0.00006759938,0.01278326,0.00004727513,0.00003194539,0.0003868024,0.00002837015,0.9570828,0.02729033,0.001299973,0.000947436,0.00001833682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.502469,0.001991557,0.4883218,0.0004489048,0.0001054404,0.0001276098,0.001699977,0.002874076,0.001961602],"genre_scores_gemma":[0.8838708,0.000464925,0.1121404,0.0001619837,0.00004262075,0.00006486597,0.001334384,0.0001386231,0.00178136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003621028,"threshold_uncertainty_score":0.007199943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01339383305853649,"score_gpt":0.2730203032684548,"score_spread":0.2596264702099184,"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."}}