{"id":"W1923884056","doi":"10.1111/jmi.12237","title":"Automated image analysis of nuclear atypia in high‐power field histopathological image","year":2015,"lang":"en","type":"article","venue":"Journal of Microscopy","topic":"AI in cancer detection","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Haematoxylin; Pattern recognition (psychology); Eosin; Digital image; Histogram; Digital pathology; Image processing; Feature (linguistics); Computer vision; Atypia; Image (mathematics); Pathology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007759492,0.0001040439,0.0004032249,0.0005167794,0.00002444159,0.00005975462,0.0006382148,0.0001001262,0.00007210478],"category_scores_gemma":[0.0001723059,0.00008795954,0.0001638534,0.001006652,0.00006703538,0.0005082155,0.0001290471,0.0002780453,0.00001642555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002527527,"about_ca_system_score_gemma":0.0001006644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005412186,"about_ca_topic_score_gemma":0.000009898861,"domain_scores_codex":[0.9986682,0.0001228922,0.0005652411,0.0001729927,0.0002975041,0.0001731923],"domain_scores_gemma":[0.9987007,0.00007224826,0.0005148332,0.0003076179,0.000306323,0.00009822535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003546087,0.0003594609,0.00755405,0.00001754809,0.0002342511,0.0004976657,0.002485802,0.0006059376,0.9470268,0.000339665,0.03909288,0.001431341],"study_design_scores_gemma":[0.008050016,0.00758233,0.4120984,0.0003372282,0.001049806,0.0008898281,0.0007051092,0.1358662,0.4145478,0.003687847,0.01389526,0.001290202],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9373486,0.0001349389,0.06056654,0.0007993584,0.0006777809,0.00004496619,0.000002309945,0.0000575016,0.0003679806],"genre_scores_gemma":[0.8622205,0.00001882466,0.1374534,0.0002487362,0.00003052967,4.644775e-7,2.664686e-7,0.000006806913,0.00002056855],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.532479,"threshold_uncertainty_score":0.3586886,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01165696434539881,"score_gpt":0.291077122236882,"score_spread":0.2794201578914832,"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."}}