{"id":"W3093420096","doi":"10.1016/j.compbiomed.2020.104053","title":"Improving prostate cancer classification in H&E tissue micro arrays using Ki67 and P63 histopathology","year":2020,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Spinal Cord Injury BC; University of British Columbia; University of British Columbia Hospital","funders":"Canadian Institutes of Health Research; Prostate Cancer Canada","keywords":"Prostate cancer; Prostatectomy; Stain; Histopathology; H&E stain; Artificial intelligence; Medicine; Pathology; Prostate; Biopsy; Receiver operating characteristic; Digital pathology; Cancer; Pattern recognition (psychology); Computer science; Immunohistochemistry; Staining; Internal medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008253838,0.0004279534,0.000423733,0.001492105,0.000347753,0.001183263,0.0003894529,0.0006623034,0.002290974],"category_scores_gemma":[0.001597308,0.0003673233,0.00041735,0.0007366678,0.0001525849,0.0006294628,0.0004947556,0.0003656503,0.001741863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000235996,"about_ca_system_score_gemma":0.000293949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003013741,"about_ca_topic_score_gemma":0.00954439,"domain_scores_codex":[0.9994687,0.00009039199,0.00004216852,0.0001187108,0.0002004061,0.00007955534],"domain_scores_gemma":[0.9990156,0.0003002618,0.00009087563,0.0001061951,0.0004477079,0.00003941185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000540878,0.00013685,0.07720513,0.0002006141,0.0001837318,0.0001796298,0.0001494191,0.004312315,0.5630154,0.0003378127,0.003184529,0.3505537],"study_design_scores_gemma":[0.00004810182,0.0004415903,0.2705893,0.0000600269,0.0005858574,0.001007132,0.0006495623,0.2407495,0.4724651,0.001398475,0.01191446,0.00009092517],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.720597,0.00269854,0.2619075,0.00074357,0.0002439037,0.0001384332,0.001758472,0.004910854,0.007001771],"genre_scores_gemma":[0.8173015,0.001044596,0.1702083,0.0004241254,0.0001722804,0.0001006475,0.001474551,0.000262669,0.009011272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003013741,"threshold_uncertainty_score":0.007664025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04887575959474036,"score_gpt":0.334170937419649,"score_spread":0.2852951778249087,"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."}}