{"id":"W4393270996","doi":"10.1038/s41467-024-46986-2","title":"Mapping cell-to-tissue graphs across human placenta histology whole slide images using deep learning with HAPPY","year":2024,"lang":"en","type":"article","venue":"Nature Communications","topic":"AI in cancer detection","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Common Fund; NIH Office of the Director; National Institute of Mental Health; National Heart, Lung, and Blood Institute; Eunice Kennedy Shriver National Institute of Child Health and Human Development; European Regional Development Fund; National Institutes of Health; National Cancer Institute; Eesti Teadusagentuur; National Human Genome Research Institute; Wellcome Trust; NIHR Oxford Biomedical Research Centre; Research Councils UK; National Institute on Drug Abuse; Engineering and Physical Sciences Research Council; National Institute of Neurological Disorders and Stroke; National Institute for Health and Care Research; Bill and Melinda Gates Foundation; Li Ka Shing Foundation; Wellcome","keywords":"Histology; Placenta; Artificial intelligence; Segmentation; Biology; Human placenta; Computer science; Pathology; Pattern recognition (psychology); Medicine; Pregnancy; Fetus; 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":[0.0003302763,0.0001822043,0.0001731113,0.0002687681,0.001243696,0.0003710316,0.002241283,0.0002142858,0.00000654648],"category_scores_gemma":[0.00004165832,0.0001826386,0.00005240221,0.001372221,0.0001613821,0.0004846343,0.001056226,0.001699698,0.00004534106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003217883,"about_ca_system_score_gemma":0.00007398616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001332269,"about_ca_topic_score_gemma":0.0008053561,"domain_scores_codex":[0.9985318,0.0002050106,0.0002302306,0.0004648211,0.0002197026,0.0003484166],"domain_scores_gemma":[0.9975378,0.0002743703,0.00009912733,0.001860071,0.0001393318,0.00008932433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003669619,0.0003826326,0.008603706,0.0004029885,0.0003423381,0.0001251072,0.06089901,0.0172086,0.652821,0.08153899,0.01751337,0.1601256],"study_design_scores_gemma":[0.0004408193,0.0002690696,0.004407596,0.0004921128,0.00004748532,0.0002991106,0.00169931,0.09678644,0.01791102,0.002146352,0.8745571,0.000943629],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0357199,0.02496709,0.9243234,0.008220217,0.00100241,0.0005362316,0.00001304727,0.001238592,0.003979096],"genre_scores_gemma":[0.8457483,0.00008488177,0.153393,0.0002466571,0.00004377086,0.00004397282,0.00001460969,0.00002815075,0.0003966511],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8570437,"threshold_uncertainty_score":0.9565631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02193260740453406,"score_gpt":0.3323284584564394,"score_spread":0.3103958510519053,"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."}}