{"id":"W2937675582","doi":"10.1007/s11548-019-01950-0","title":"Deep neural maps for unsupervised visualization of high-grade cancer in prostate biopsies","year":2019,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; Queen's University","funders":"Canadian Institutes of Health Research; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; Ontario Trillium Foundation","keywords":"Prostate cancer; Artificial intelligence; Computer science; Prostate biopsy; Biopsy; Pattern recognition (psychology); Medicine; Radiology; Deep learning; Cluster analysis; Cancer; 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":[0.0004599473,0.0007299028,0.0003313449,0.001160515,0.0003256211,0.001332966,0.0005940132,0.000771488,0.002107132],"category_scores_gemma":[0.002039374,0.0003731942,0.0004535049,0.0007085766,0.0002480146,0.0005384602,0.001052615,0.001066787,0.0004174063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006998826,"about_ca_system_score_gemma":0.001296503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01210758,"about_ca_topic_score_gemma":0.0210729,"domain_scores_codex":[0.9998546,0.00003702285,0.000006582019,0.00002513891,0.00004332759,0.00003325953],"domain_scores_gemma":[0.9995009,0.0002649948,0.00004736631,0.00003820143,0.0001080551,0.0000404497],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001204677,0.0002999109,0.01156114,0.0004457906,0.0001653986,0.0005757656,0.0007383685,0.2699679,0.05801044,0.01084827,0.01824661,0.6279358],"study_design_scores_gemma":[0.00001522491,0.00003279371,0.003161425,0.00004478728,0.00001506348,0.0001371603,0.0000744968,0.9760098,0.0130251,0.00560029,0.00186318,0.00002066195],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2280044,0.001582802,0.7538188,0.001251666,0.0001171388,0.0001661007,0.002502181,0.008806009,0.003750975],"genre_scores_gemma":[0.7494344,0.0008036365,0.243377,0.0001723124,0.00006364868,0.0001326207,0.001376456,0.0006821897,0.003957879],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01210758,"threshold_uncertainty_score":0.0240742,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01911277960313687,"score_gpt":0.2977899060760231,"score_spread":0.2786771264728862,"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."}}