{"id":"W4362531944","doi":"10.1016/j.compbiomed.2023.106882","title":"Automatic segmentation of prostate cancer metastases in PSMA PET/CT images using deep neural networks with weighted batch-wise dice loss","year":2023,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"Prostate Cancer Treatment and Research","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research; National Institutes of Health; University of British Columbia; Mitacs; Microsoft","keywords":"Dice; Prostate cancer; Segmentation; Sørensen–Dice coefficient; Convolutional neural network; Context (archaeology); Artificial intelligence; Computer science; Deep learning; Pattern recognition (psychology); Prostate; Artificial neural network; Nuclear medicine; Image segmentation; Medicine; Cancer; Internal medicine; Mathematics","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":[0.000287772,0.0001471849,0.0004396735,0.000348077,0.0000416047,0.000003192709,0.00005374259,0.00001888738,0.0000248223],"category_scores_gemma":[0.00001585331,0.00008975277,0.00001789829,0.0006391571,0.0005025899,0.00005553185,0.00004768971,0.0001704804,3.467783e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000075397,"about_ca_system_score_gemma":0.00005391822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000460242,"about_ca_topic_score_gemma":0.0001150763,"domain_scores_codex":[0.9989428,0.0001251206,0.0002802756,0.0002511082,0.0001036442,0.0002970547],"domain_scores_gemma":[0.9994611,0.0002093054,0.0000896793,0.0001093236,0.00004999356,0.00008055456],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009786617,0.0001119864,0.9179434,0.0004325182,0.0001896678,0.002493516,0.001105646,0.001115278,0.002186148,0.00003170434,0.0001666959,0.07324477],"study_design_scores_gemma":[0.01626397,0.001933307,0.2631575,0.001925288,0.0002413125,0.0005762269,0.001013165,0.7129049,0.001448798,0.000271544,0.00003786117,0.0002261438],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922355,0.004638487,0.0006452326,0.001662185,0.000199378,0.0005620595,0.000009615445,0.0000342124,0.00001331169],"genre_scores_gemma":[0.9951267,0.002931768,0.001431458,0.0001749997,0.00006834578,0.00004610082,0.0001860279,0.00001165826,0.00002296099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7117896,"threshold_uncertainty_score":0.3660012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02558636373627095,"score_gpt":0.3643789750250105,"score_spread":0.3387926112887396,"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."}}