{"id":"W4320712900","doi":"10.1109/access.2023.3244741","title":"Generative Adversarial Networks for Anomaly Detection in Biomedical Imaging: A Study on Seven Medical Image Datasets","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Tehran University of Medical Sciences and Health Services","keywords":"Computer science; Anomaly detection; Medical imaging; Artificial intelligence; Modalities; Ground truth; Generative grammar; Field (mathematics); Anomaly (physics); Machine learning; Software deployment; Image (mathematics); Deep learning; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0006525543,0.0001387342,0.0001637853,0.0003000406,0.0001916913,0.0002093164,0.001137824,0.00009016378,0.00001078057],"category_scores_gemma":[0.00007746292,0.0001284288,0.00005355934,0.001279399,0.00006034358,0.0005414455,0.0002802991,0.0002189278,0.00002381673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006618667,"about_ca_system_score_gemma":0.00007179697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001560381,"about_ca_topic_score_gemma":0.0001285923,"domain_scores_codex":[0.9983948,0.00009061078,0.0003024358,0.0005470765,0.0003673059,0.0002977359],"domain_scores_gemma":[0.9990944,0.0001742685,0.00008714972,0.0004684563,0.00004723379,0.0001284358],"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":[0.0004162765,0.003985577,0.006616776,0.00005259871,0.0001794767,0.0006586602,0.002301154,0.002175064,0.008470044,0.00314454,0.1641892,0.8078106],"study_design_scores_gemma":[0.001501399,0.0003930888,0.01230583,0.00001930098,0.00001118915,0.00001414117,0.000101627,0.9708196,0.007008983,0.001483833,0.006042135,0.0002988972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05435858,0.000003863449,0.9425121,0.001234089,0.0005598755,0.0008285021,0.00003789146,0.0004227277,0.00004234763],"genre_scores_gemma":[0.9967091,0.000005910996,0.001631889,0.0003741109,0.0004074628,0.0007850017,0.00005493623,0.00001357372,0.00001799392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9686445,"threshold_uncertainty_score":0.5237175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03027084576530132,"score_gpt":0.3587337700926335,"score_spread":0.3284629243273322,"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."}}