{"id":"W3007406909","doi":"10.1101/2020.02.25.965038","title":"Predicting Endometrial Cancer Subtypes and Molecular Features from Histopathology Images Using Multi-resolution Deep Learning Models","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"AI in cancer detection","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University","keywords":"Subtyping; Histopathology; Endometrial cancer; Computational biology; Mutation; Digital pathology; Pathology; Computer science; Biology; Artificial intelligence; Cancer; Medicine; Gene; Internal medicine; Genetics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006332863,0.0007459931,0.0003665072,0.0007761954,0.0001357069,0.0007085483,0.0006401403,0.0006118763,0.001450283],"category_scores_gemma":[0.001099791,0.0003576011,0.0006908588,0.0003296743,0.0001993038,0.0005595725,0.0006995505,0.0006199609,0.000437652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006965389,"about_ca_system_score_gemma":0.0006828344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007524813,"about_ca_topic_score_gemma":0.01120365,"domain_scores_codex":[0.9997768,0.00004457219,0.00001352594,0.00007763431,0.0000553199,0.00003224474],"domain_scores_gemma":[0.9997655,0.00006967363,0.00004500265,0.00003426332,0.00006196481,0.00002358662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002922023,0.0001562412,0.01765949,0.0001821277,0.0001889556,0.0002922721,0.00006594039,0.6739298,0.04689324,0.001697326,0.005855239,0.2527872],"study_design_scores_gemma":[0.000004271772,0.00001238422,0.0007721587,0.00000650259,0.00001048842,0.0000194668,0.000005620631,0.9953207,0.002768683,0.0006131328,0.0004604434,0.000006017252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2887628,0.002065209,0.6978645,0.00108226,0.00015188,0.0001318172,0.001689254,0.004659113,0.003593122],"genre_scores_gemma":[0.86867,0.0007409652,0.1228624,0.0003310927,0.00004290814,0.0001088339,0.001901489,0.0001237368,0.005218626],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007524813,"threshold_uncertainty_score":0.01496202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02808674659727654,"score_gpt":0.2431534007750545,"score_spread":0.215066654177778,"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."}}