{"id":"W3012097287","doi":"10.1002/mp.14134","title":"Automatic prostate segmentation using deep learning on clinically diverse 3D transrectal ultrasound images","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":86,"is_retracted":false,"has_abstract":true,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Prostate; Brachytherapy; 3D ultrasound; Prostate biopsy; Segmentation; Artificial intelligence; Computer science; Prostate brachytherapy; Prostate cancer; Medicine; Medical imaging; Ultrasound; Radiology; Medical physics; Radiation therapy; Cancer","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":[0.0001441625,0.0001739941,0.0003247882,0.00001536547,0.0001053718,0.00002485522,0.00006157516,0.00006871294,0.0004048914],"category_scores_gemma":[0.0003624104,0.0001386768,0.0001217159,0.0001611927,0.0001189047,0.00008842463,0.00002113875,0.0003758733,0.00008885819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001171675,"about_ca_system_score_gemma":0.0001331253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001485139,"about_ca_topic_score_gemma":8.021119e-7,"domain_scores_codex":[0.9983993,0.00006910332,0.0003300163,0.000309348,0.0006506532,0.0002416455],"domain_scores_gemma":[0.9990578,0.0002812561,0.0001043794,0.0001020781,0.00004962145,0.0004048843],"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":[0.0004592176,0.001188995,0.09580514,0.0004603245,0.0003674778,0.000493232,0.005619963,0.0005536395,0.004365933,0.00001697279,0.0004753097,0.8901938],"study_design_scores_gemma":[0.08484241,0.04649411,0.2240381,0.007674037,0.007192858,0.0003050106,0.007357219,0.2739744,0.3385784,0.00208621,0.003347639,0.004109642],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862208,0.0001198499,0.01011627,0.00216044,0.0001497169,0.0005833279,0.00001662005,0.0001649998,0.0004679139],"genre_scores_gemma":[0.994745,0.0003150186,0.001424309,0.002926341,0.0004080614,0.0000308308,0.0001051304,0.00002974314,0.00001552919],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8860841,"threshold_uncertainty_score":0.5655077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03274618185966075,"score_gpt":0.3238530647181995,"score_spread":0.2911068828585387,"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."}}