{"id":"W4206461547","doi":"10.1093/noajnl/vdac001","title":"Integrating morphologic and molecular histopathological features through whole slide image registration and deep learning","year":2022,"lang":"en","type":"article","venue":"Neuro-Oncology Advances","topic":"AI in cancer detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Princess Margaret Cancer Foundation","keywords":"Workflow; Digital pathology; Scale-invariant feature transform; Computer science; Artificial intelligence; ATRX; Pathology; Pipeline (software); Deep learning; Pattern recognition (psychology); Feature extraction; Biology; Medicine; Database","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003498854,0.0001584475,0.000209392,0.00006104439,0.0006461671,0.00007348446,0.0003129717,0.00007639472,0.00001020194],"category_scores_gemma":[0.0003616213,0.0001499349,0.00003176112,0.0002322976,0.0002542258,0.0006651554,0.0004745612,0.0007592466,0.000001744089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001355795,"about_ca_system_score_gemma":0.00003433256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009749081,"about_ca_topic_score_gemma":0.00001696363,"domain_scores_codex":[0.9981361,0.0005696652,0.000208885,0.0006527274,0.0001910393,0.0002415695],"domain_scores_gemma":[0.9991301,0.0003459349,0.0002298753,0.0002130307,0.00003762654,0.00004337612],"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":[0.00008996793,0.00007417105,0.001907072,0.00002793236,0.000008039276,0.001424137,0.00230091,0.003062939,0.6225389,0.01638733,0.0004472136,0.3517314],"study_design_scores_gemma":[0.002369412,0.01140621,0.00921246,0.00002565739,0.00006854595,0.01358052,0.00388333,0.03931309,0.03672052,0.1234232,0.7586634,0.001333667],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3353715,0.01600193,0.6301371,0.007949248,0.001557334,0.0005073406,0.000003645501,0.0006232767,0.007848611],"genre_scores_gemma":[0.8610237,0.0006914884,0.1352621,0.002668001,0.00007178493,0.0001690333,0.000004861967,0.00001530839,0.00009378254],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7582161,"threshold_uncertainty_score":0.611417,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0101506632032242,"score_gpt":0.2726875042782666,"score_spread":0.2625368410750424,"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."}}