{"id":"W4388282590","doi":"10.1016/j.cmpb.2023.107910","title":"Assessing privacy leakage in synthetic 3-D PET imaging using transversal GAN","year":2023,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; BC Cancer Foundation","keywords":"Computer science; Machine learning; Artificial intelligence; Inference; Fidelity; Generative model; Segmentation; Generative grammar; Data mining","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004247824,0.0002730718,0.0004760996,0.0009078512,0.0001385091,0.000419789,0.0007145137,0.000063691,0.000003568756],"category_scores_gemma":[0.0001151777,0.0002476126,0.00005646897,0.002656579,0.0002296833,0.000892768,0.0004971799,0.0005031296,0.000002033431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008270091,"about_ca_system_score_gemma":0.00005968935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001377871,"about_ca_topic_score_gemma":0.000003950429,"domain_scores_codex":[0.9969427,0.0008434433,0.0005287463,0.0007522466,0.0002928799,0.0006400003],"domain_scores_gemma":[0.9986689,0.0005751516,0.000127644,0.0004623937,0.0000344844,0.0001313917],"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":[0.000005328022,0.00004754064,0.01335392,0.00008817254,0.000008576654,0.0005433752,0.002994133,0.00179068,0.001447147,0.0005569861,0.000004716073,0.9791594],"study_design_scores_gemma":[0.001014278,0.00006965938,0.01346792,0.0005028047,0.00001026373,0.0001768782,0.00032815,0.981015,0.00006402419,0.002145889,0.0009261473,0.0002789446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1228388,0.0002408957,0.8741468,0.001282976,0.0008802341,0.0002651459,1.741688e-7,0.0002877778,0.00005725539],"genre_scores_gemma":[0.3942291,0.00001791009,0.6054851,0.00009602404,0.0001382793,0.000007526476,0.000004414568,0.00001822637,0.000003457839],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9792244,"threshold_uncertainty_score":0.9999976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08766871363078618,"score_gpt":0.4167928898280828,"score_spread":0.3291241761972966,"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."}}