{"id":"W4309927410","doi":"10.1101/2022.11.21.517353","title":"HAPPY: A deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":5,"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; National Human Genome Research Institute; Wellcome Trust; NIHR Oxford Biomedical Research Centre; European Regional Development Fund; National Institutes of Health; National Cancer Institute; Eesti Teadusagentuur; National Institute on Drug Abuse; Engineering and Physical Sciences Research Council; Bill and Melinda Gates Foundation; Li Ka Shing Foundation; National Institute of Neurological Disorders and Stroke; National Institute for Health and Care Research","keywords":"Histology; Placenta; Segmentation; Biology; Artificial intelligence; Pipeline (software); Computer science; Pathology; Pattern recognition (psychology); Anatomy; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001585457,0.001218357,0.0006166289,0.001932347,0.0005334314,0.001818601,0.002341636,0.001423266,0.007711277],"category_scores_gemma":[0.003989321,0.001094245,0.001338368,0.0008996311,0.0004903395,0.0009615683,0.002032624,0.001757242,0.004345308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001232874,"about_ca_system_score_gemma":0.00134057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008863242,"about_ca_topic_score_gemma":0.01689238,"domain_scores_codex":[0.9995209,0.00009100895,0.00002257688,0.0001739077,0.0001291812,0.00006255019],"domain_scores_gemma":[0.9992294,0.0003167867,0.00008481852,0.0001500374,0.0001534452,0.00006556293],"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":[0.0005637348,0.0001876359,0.01002773,0.0008824121,0.0006221205,0.0006341953,0.0004432635,0.1617566,0.09005611,0.01108055,0.1618843,0.5618615],"study_design_scores_gemma":[0.0000487731,0.00006831525,0.003656464,0.00005371917,0.00003724604,0.0003179372,0.00008664516,0.9414793,0.02145175,0.01624966,0.01650117,0.00004905317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02269129,0.0008249527,0.8906004,0.000793923,0.0001047447,0.0002198804,0.009597111,0.07321662,0.001951008],"genre_scores_gemma":[0.2053506,0.0008136528,0.745967,0.001095915,0.00009147407,0.0006932408,0.02853375,0.007516577,0.009937815],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008863242,"threshold_uncertainty_score":0.02579683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01418540696296984,"score_gpt":0.2477884252820209,"score_spread":0.2336030183190511,"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."}}