{"id":"W4414423977","doi":"10.1016/j.ejrai.2025.100042","title":"Transforming CT imaging with deep learning: Noise reduction, artifact management, and clinical applications – A comprehensive review","year":2025,"lang":"en","type":"article","venue":"European Journal of Radiology Artificial Intelligence","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University Health Network; University of Toronto; St. Michael's Hospital","funders":"GE Healthcare","keywords":"Artifact (error); Noise (video); Medical imaging; Computed tomography; Noise reduction","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":[0.001101771,0.0001298308,0.0003818255,0.0001540439,0.0001580073,0.0000171182,0.0001673895,0.00001490794,0.00003483826],"category_scores_gemma":[0.0001047273,0.00009897594,0.0001027666,0.0003261438,0.0005283374,0.00006753914,0.00003348188,0.000626568,0.00001660813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002357681,"about_ca_system_score_gemma":0.00004235013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001091871,"about_ca_topic_score_gemma":2.315426e-7,"domain_scores_codex":[0.9982398,0.000327339,0.0009119522,0.0002392061,0.0001130962,0.0001686339],"domain_scores_gemma":[0.9989506,0.0001361237,0.0003064587,0.0002099963,0.0002473083,0.0001495393],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001707528,0.0002033113,0.003341216,0.0004726049,0.0002333781,0.0003624643,0.00007084621,0.00002992123,0.001700942,0.007115348,0.003006788,0.9832924],"study_design_scores_gemma":[0.0009209195,0.001734211,0.01161061,0.01011164,0.003395448,0.03017786,0.002179205,0.003361481,0.006091368,0.007561978,0.9221442,0.000711136],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01983688,0.01263006,0.9463092,0.01621445,0.0001131039,0.0008450474,7.170948e-7,0.00007742412,0.003973117],"genre_scores_gemma":[0.8884508,0.06070733,0.04785573,0.002351501,0.0002903459,0.00002749972,0.000007883403,0.00002902862,0.0002798605],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9825813,"threshold_uncertainty_score":0.4036122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04583740334157864,"score_gpt":0.3677366761738911,"score_spread":0.3218992728323124,"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."}}