{"id":"W4412163704","doi":"10.1158/1557-3265.aimachine-b028","title":"Abstract B028: Assessing variability in training deep models in delineating Prostate gland anatomy between clinical experts","year":2025,"lang":"en","type":"article","venue":"Clinical Cancer Research","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Prostate gland; Prostate cancer; Prostate; Medicine; Anatomy; Pathology; Biology; Medical physics; Cancer; Internal medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02421468,0.0009891179,0.0006808709,0.001303275,0.0006101191,0.00154416,0.001369237,0.002183123,0.001413914],"category_scores_gemma":[0.08404483,0.0004513352,0.0007954509,0.0007285449,0.001263825,0.001205148,0.001925036,0.001677244,0.0006130975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001215328,"about_ca_system_score_gemma":0.0008862055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003729193,"about_ca_topic_score_gemma":0.002761677,"domain_scores_codex":[0.9880005,0.006548369,0.0008567796,0.002610528,0.001654464,0.000329504],"domain_scores_gemma":[0.9138556,0.06536034,0.004665933,0.007049454,0.007435447,0.001633247],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0089963,0.0009100378,0.2538618,0.0008814436,0.002623304,0.0007330094,0.002045273,0.4232343,0.02323425,0.002442213,0.01411546,0.2669226],"study_design_scores_gemma":[0.0002225689,0.00184149,0.07035647,0.0001646298,0.0003271847,0.0007413629,0.0004509802,0.889687,0.02848244,0.004880317,0.002677168,0.0001683743],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8864243,0.001296739,0.1066103,0.0007127929,0.0002155781,0.0001647748,0.0009519692,0.001192345,0.002431212],"genre_scores_gemma":[0.9794487,0.00008028008,0.01806043,0.0002312923,0.00005196095,0.00008430453,0.001365173,0.0001354717,0.0005423047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02421468,"threshold_uncertainty_score":0.128061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3101267683933944,"score_gpt":0.5719112199459427,"score_spread":0.2617844515525484,"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."}}