{"id":"W3157377277","doi":"10.1002/cjp2.227","title":"Reliable computational quantification of liver fibrosis is compromised by inherent staining variation","year":2021,"lang":"en","type":"article","venue":"The Journal of Pathology Clinical Research","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"NIHR Nottingham Biomedical Research Centre; Nottingham University Hospitals NHS Trust; University of Nottingham; Medical Research Council; Engineering and Physical Sciences Research Council; National Institute for Health and Care Research; Medical Research Council Canada","keywords":"Biopsy; Medicine; Stain; Liver biopsy; Gold standard (test); Clinical trial; Liver fibrosis; Pathology; Liver disease; Thresholding; Staining; Fibrosis; Artificial intelligence; Medical physics; Radiology; Computer science; Internal medicine","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":[0.01286412,0.00007089288,0.0002647149,0.0001271018,0.0001857938,0.00004846991,0.000758422,0.0001369393,0.00007057157],"category_scores_gemma":[0.001695017,0.0000537329,0.0001080903,0.0006362408,0.0002959331,0.0002395834,0.0002720402,0.000896959,0.0000257768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009997409,"about_ca_system_score_gemma":0.0006183074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002169505,"about_ca_topic_score_gemma":0.000003076772,"domain_scores_codex":[0.9951322,0.002511631,0.001016917,0.0002199993,0.0008994078,0.000219811],"domain_scores_gemma":[0.9921355,0.004366708,0.0006647854,0.0004279245,0.002322746,0.00008239274],"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":[0.003399086,0.004329617,0.02370503,0.0003726702,0.0007821414,0.000496804,0.02033373,0.03886554,0.3747263,0.02541,0.2232843,0.2842948],"study_design_scores_gemma":[0.006558084,0.006876925,0.3054114,0.0004574546,0.0001422096,0.001048198,0.001040242,0.4913873,0.08003149,0.09743075,0.0091047,0.0005112496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2856113,0.00069777,0.7076824,0.005315268,0.000430573,0.0001366911,0.000007853003,0.00001002504,0.0001080704],"genre_scores_gemma":[0.972062,0.0006367697,0.02688033,0.0001949586,0.0001031836,0.000003136886,0.000003266171,0.000005991785,0.0001103728],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6864507,"threshold_uncertainty_score":0.4458472,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2287169008945559,"score_gpt":0.4688093677811549,"score_spread":0.240092466886599,"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."}}