{"id":"W4408519581","doi":"10.1109/trpms.2025.3551946","title":"Generative Inpainting-Based Anomaly Detection for CT Liver Tumor Detection","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Radiation and Plasma Medical Sciences","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Institute of Biomedical Imaging and Bioengineering; National Cancer Institute","keywords":"Inpainting; Anomaly detection; Artificial intelligence; Anomaly (physics); Pattern recognition (psychology); Generative grammar; Computer science; Computer vision; Image (mathematics); Physics","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":[0.0006854788,0.0001406505,0.00013366,0.0003804686,0.001165835,0.0001833508,0.0003018421,0.00007699412,0.00003417035],"category_scores_gemma":[0.00005306019,0.0001251809,0.000086405,0.001029793,0.0002127463,0.0003216006,0.000002976822,0.0001860252,0.000007511122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007473854,"about_ca_system_score_gemma":0.0002000387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009301883,"about_ca_topic_score_gemma":0.0003326398,"domain_scores_codex":[0.9986016,0.00009109432,0.0002691549,0.0004822352,0.0003371453,0.0002187583],"domain_scores_gemma":[0.9990941,0.0004496325,0.00009927004,0.0001598862,0.00006108199,0.0001360709],"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":[0.0000169775,0.0001001944,0.00002355127,0.00001790466,0.00001330418,0.00000145548,0.00005158402,0.002428291,0.001483303,0.004254392,0.00006957099,0.9915395],"study_design_scores_gemma":[0.0003471551,0.0002572861,0.0002331286,0.00001833898,0.00001109538,0.00001263446,0.00001882746,0.7438845,0.2495466,0.0007007342,0.004851756,0.0001179465],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03711501,0.00003122983,0.9590256,0.002373876,0.0004978197,0.0004220498,0.000006571098,0.0002748085,0.0002530113],"genre_scores_gemma":[0.9883815,0.00004412549,0.009855759,0.001192861,0.00004174305,0.0003400634,7.210434e-7,0.000004307685,0.0001388907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9914215,"threshold_uncertainty_score":0.8966776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01556604288351071,"score_gpt":0.266098715260233,"score_spread":0.2505326723767223,"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."}}