{"id":"W2081210775","doi":"10.1007/s00428-011-1106-x","title":"Interactive digital slides with heat maps: a novel method to improve the reproducibility of Gleason grading","year":2011,"lang":"en","type":"article","venue":"Archiv für Pathologische Anatomie und Physiologie und für Klinische Medicin","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":59,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canadian Partnership Against Cancer; University of Toronto","funders":"","keywords":"Reproducibility; Grading (engineering); Computer science; Artificial intelligence; Medical physics; Medicine; Statistics; Mathematics; Biology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002629597,0.0005222779,0.001055424,0.0002630332,0.0002115098,0.00003340925,0.0005230777,0.0001951412,0.00002862084],"category_scores_gemma":[0.004076667,0.0002955752,0.0003200961,0.0007752328,0.000862197,0.0002420908,0.0004301334,0.001124712,0.00001827495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001012559,"about_ca_system_score_gemma":0.0002771861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001177461,"about_ca_topic_score_gemma":0.00006293868,"domain_scores_codex":[0.9958238,0.0003980963,0.0007895972,0.001835566,0.0004835484,0.0006693739],"domain_scores_gemma":[0.9955509,0.001319204,0.0003538314,0.00217707,0.0002846647,0.0003143726],"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":[0.05324199,0.002406865,0.04193661,0.0004907962,0.00219335,0.0002211103,0.01946175,0.0002613268,0.6826898,0.002099637,0.0008109641,0.1941858],"study_design_scores_gemma":[0.009060192,0.05702697,0.2108428,0.001650306,0.002288919,0.0006114825,0.01849534,0.003129416,0.6760096,0.01364381,0.005437317,0.001803803],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8784012,0.0007282164,0.1066843,0.001073433,0.0003775706,0.001621592,0.0001011983,0.0002671482,0.01074542],"genre_scores_gemma":[0.9469914,0.00004552316,0.05155868,0.0007521602,0.0002971804,0.0001380205,0.00004984158,0.00005090821,0.0001162293],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.192382,"threshold_uncertainty_score":0.9999496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0535172873881294,"score_gpt":0.3640648987239969,"score_spread":0.3105476113358676,"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."}}