{"id":"W4415593673","doi":"10.1109/trpms.2025.3625611","title":"Comprehensive Evaluation of Quantitative Measurements From Automated Deep Segmentations of PSMA PET/CT Images","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; BC Cancer Agency; University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Dice; Ground truth; Concordance correlation coefficient; Segmentation; Sørensen–Dice coefficient; Pattern recognition (psychology); Concordance; Correlation coefficient","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001987335,0.0002509768,0.0005410052,0.0005316581,0.0004525734,0.00003931527,0.0002731445,0.0000678439,0.001580658],"category_scores_gemma":[0.0004422938,0.0002198842,0.0001342724,0.001428493,0.001766046,0.0002060469,0.000005044501,0.0003528575,0.00001200799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001291386,"about_ca_system_score_gemma":0.001211977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007789946,"about_ca_topic_score_gemma":0.00007167074,"domain_scores_codex":[0.9950314,0.0005726237,0.001052243,0.000544795,0.00252762,0.0002713369],"domain_scores_gemma":[0.9968022,0.001596855,0.000432437,0.0002568171,0.0005948428,0.0003168105],"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":[0.0005892336,0.006420208,0.004840586,0.001248394,0.002415278,0.00003116742,0.003110034,0.02088128,0.06321854,0.004024281,0.007946665,0.8852744],"study_design_scores_gemma":[0.002996691,0.0004629031,0.00488813,0.00110814,0.001102037,0.00001652177,0.001588046,0.8748488,0.1119373,0.0006453952,0.0002222315,0.0001838457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.696951,0.001377918,0.2852042,0.01159004,0.001083924,0.001724452,0.0003701898,0.0001742821,0.001523987],"genre_scores_gemma":[0.9880396,0.00147186,0.009880749,0.0003700683,0.00002042339,0.0001200051,0.00003839544,0.000008577771,0.0000503219],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8850905,"threshold_uncertainty_score":0.999332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1075106016777865,"score_gpt":0.4150876628376801,"score_spread":0.3075770611598935,"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."}}