{"id":"W4380576977","doi":"10.1002/gcc.23177","title":"Machine learning in computational histopathology: Challenges and opportunities","year":2023,"lang":"en","type":"review","venue":"Genes Chromosomes and Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research; Canadian Institute for Advanced Research","keywords":"Workflow; Digital pathology; Histopathology; Artificial intelligence; Computer science; Machine learning; Context (archaeology); Digitization; Medical physics; Pathology; Computer vision; Medicine; Biology","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":[0.0002282537,0.0002649536,0.0007249298,0.0002640527,0.0001015046,0.00005831774,0.0002331882,0.0001645644,0.00001020322],"category_scores_gemma":[0.000005827252,0.0002391943,0.00006473502,0.0001527796,0.00009311883,0.0001558537,0.0003182811,0.000270961,0.000004662518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001536552,"about_ca_system_score_gemma":0.0002398122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005524286,"about_ca_topic_score_gemma":0.0001289364,"domain_scores_codex":[0.9986309,0.0001434826,0.0003031403,0.0005453806,0.000153404,0.0002236392],"domain_scores_gemma":[0.9994218,0.0001303645,0.0001911255,0.0001657964,0.00002766776,0.00006326906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[5.810984e-7,0.000003772882,0.000006474807,0.003817685,0.00001838965,0.00003943438,0.0002728502,0.00006567773,8.082164e-8,0.002024705,0.00001855584,0.9937318],"study_design_scores_gemma":[0.0001159743,0.00004977665,0.00008743874,0.002246775,0.00004056398,0.0001331317,0.00003028768,0.002432535,1.336801e-7,0.0009548656,0.993637,0.0002715446],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001051292,0.9981577,0.0003426155,0.0005604132,0.000483197,0.0001826638,0.00001892254,0.0001407846,0.0001031787],"genre_scores_gemma":[0.00001604312,0.9985834,0.0003453132,0.0000499995,0.0001626533,0.0002291069,0.00001678792,0.00003136678,0.0005653217],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9936184,"threshold_uncertainty_score":0.975406,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1557736330130398,"score_gpt":0.335010630612856,"score_spread":0.1792369975998162,"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."}}