{"id":"W3202436968","doi":"10.1007/978-3-030-87237-3_65","title":"Training Deep Networks for Prostate Cancer Diagnosis Using Coarse Histopathological Labels","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"AI in cancer detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vancouver General Hospital; Queen's University; University of British Columbia","funders":"","keywords":"Computer science; Prostate cancer; Artificial intelligence; Constraint (computer-aided design); Artificial neural network; Histopathology; Pattern recognition (psychology); Deep learning; Biopsy; Cancer; Radiology; Medicine; Pathology; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009906107,0.0006079841,0.0007391524,0.0004624725,0.0004967731,0.0005946936,0.002104864,0.0004962779,0.00003430104],"category_scores_gemma":[0.0001383479,0.0005899709,0.0002164219,0.0007754457,0.0006712373,0.0006010216,0.001062018,0.0009202571,0.000002253363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001290027,"about_ca_system_score_gemma":0.0009279944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004398269,"about_ca_topic_score_gemma":0.0002773973,"domain_scores_codex":[0.9954126,0.00006240847,0.0006252741,0.002158606,0.0007502035,0.0009908993],"domain_scores_gemma":[0.9970871,0.0007581571,0.0004476814,0.001070158,0.0004394466,0.0001974351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006912328,0.00001325873,0.00006923729,0.00002971095,0.000008421494,0.0000839395,0.0007912287,0.2778689,0.00005521965,0.001305859,0.00001181771,0.7197555],"study_design_scores_gemma":[0.0003191741,0.0001897103,0.0000376262,0.0005687826,0.00002398868,0.000109915,5.796356e-7,0.9730152,0.0006077351,0.0209059,0.003487086,0.0007342882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002065021,0.003622219,0.9891076,0.0005367327,0.005336716,0.0007918687,0.00001507111,0.000198749,0.0001845575],"genre_scores_gemma":[0.07056958,0.0006105726,0.9232849,0.002961721,0.00174436,0.000464615,0.000009839868,0.00009253246,0.0002619035],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7190213,"threshold_uncertainty_score":0.9996552,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05455803568230379,"score_gpt":0.2911745036587221,"score_spread":0.2366164679764183,"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."}}