{"id":"W4392091091","doi":"10.6019/s-biad1045","title":"HAPPY: a deep learning pipeline for mapping cell-to-tissue graphs across placenta histology whole slide images","year":2024,"lang":"en","type":"dataset","venue":"","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Histology; Pipeline (software); Artificial intelligence; Computer science; Placenta; Biology; Pathology; Medicine; Pregnancy; Fetus","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":[0.0009447639,0.00346575,0.001256525,0.003235008,0.0009847531,0.001546565,0.003354942,0.002477567,0.01660611],"category_scores_gemma":[0.002680728,0.001027511,0.00209604,0.002282734,0.0004608347,0.0007769191,0.001838874,0.001980054,0.01752742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00179235,"about_ca_system_score_gemma":0.002065161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04264789,"about_ca_topic_score_gemma":0.1045483,"domain_scores_codex":[0.9993131,0.00007690254,0.00004328769,0.0002598612,0.0001710134,0.0001358174],"domain_scores_gemma":[0.9991887,0.0002287338,0.00005817952,0.0002206891,0.0002206874,0.00008304635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00055861,0.0003057077,0.004961296,0.001333534,0.0003744733,0.0002777689,0.00008309593,0.006504575,0.0106395,0.001173821,0.8952561,0.07853141],"study_design_scores_gemma":[0.001477916,0.000550247,0.03635388,0.0006798244,0.0006614604,0.00283353,0.0004580625,0.1408634,0.04659136,0.01536515,0.7538363,0.0003289122],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01843151,0.001833619,0.0190595,0.0008695897,0.000442732,0.0005166775,0.9149576,0.03881238,0.005076364],"genre_scores_gemma":[0.01727507,0.0004454536,0.02768411,0.0003553722,0.00004303596,0.0004560777,0.9471204,0.0009384748,0.005682],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04264789,"threshold_uncertainty_score":0.08479935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01427244343969908,"score_gpt":0.2921865803064923,"score_spread":0.2779141368667932,"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."}}