{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006447488,0.001465076,0.0007685096,0.004171168,0.0004181166,0.001939182,0.0007756319,0.00102202,0.0009304082],"category_scores_gemma":[0.01642143,0.0003714988,0.0005874847,0.001536328,0.0008064866,0.001358943,0.001310821,0.00051347,0.0004094533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008402406,"about_ca_system_score_gemma":0.0006407065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002528179,"about_ca_topic_score_gemma":0.00357255,"domain_scores_codex":[0.9967837,0.0009516851,0.0002636227,0.0006691469,0.001164814,0.0001668811],"domain_scores_gemma":[0.9910978,0.004282095,0.001313401,0.00101964,0.002119057,0.0001679794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001979074,0.0003531481,0.08861388,0.001621233,0.001460338,0.000484512,0.0009336965,0.273956,0.1164619,0.002945763,0.004278174,0.5069123],"study_design_scores_gemma":[0.00005067989,0.0007174425,0.08463537,0.0001574553,0.0002759841,0.001016078,0.0003980426,0.8068306,0.09845766,0.003399173,0.003908911,0.0001525148],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7632645,0.00311351,0.2232126,0.0002190907,0.0001005463,0.0002006179,0.002415924,0.004019366,0.003453797],"genre_scores_gemma":[0.9449538,0.0004356103,0.05027867,0.00009621833,0.00005352105,0.0001001548,0.002923798,0.00032467,0.0008335724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006447488,"threshold_uncertainty_score":0.03409803,"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."}}