{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T05:00:11Z","timestamp":1790312411028,"version":"4.1.0"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"\n Introduction<\/jats:title>\n Automated anomaly detection from chest computed tomography (CT) may support research on pulmonary image triage without requiring exhaustive abnormal annotations. Supervised methods depend on costly expert labels, while many existing normal-only methods rely predominantly on a single anomaly cue. In pulmonary CT, heterogeneous lesion appearance and variation across slices and acquisition sources may reduce the reliability of single-cue scoring. This study develops a codebook-guided framework that integrates complementary cues for abnormality detection and spatial heatmap generation.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n The framework combines residual vector-quantized reconstruction, transformer-based token discrimination learned through codebook-guided latent perturbation, and quantization-distance scoring. The primary benchmark combined three public CT datasets. Slice-level evaluation used a visually screened, lesion-enriched subset, whereas patient-level evaluation retained all valid lung-containing slices and aggregated the highest 10% of slice scores by their mean. Patient-level thresholds were calibrated using normal validation patients only. Quantitative localization was additionally evaluated on 100 LIDC-IDRI cases containing nodules marked by at least three radiologists.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The proposed method achieved a slice-level AUROC of 0.9218. At the patient level, it achieved an AUROC of\n \n \n 0.9187<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.0123<\/mml:mn>\n <\/mml:math>\n <\/jats:inline-formula>\n , balanced accuracy of\n \n \n 0.7521<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.0354<\/mml:mn>\n <\/mml:math>\n <\/jats:inline-formula>\n , and F1-score of\n \n \n 0.9297<\/mml:mn>\n \u00b1<\/mml:mo>\n 0.0052<\/mml:mn>\n <\/mml:math>\n <\/jats:inline-formula>\n ; the patient-stratified bootstrap 95% confidence interval for AUROC was 0.8786\u20130.9727. Disease-wise patient-level AUROC ranged from 0.8470 for COVID-19 to 0.9747 for community-acquired pneumonia. On the external LIDC-IDRI localization cohort, the proposed method achieved a P-AUROC of 0.9155, the highest observed value among the evaluated methods.\n <\/jats:p>\n <\/jats:sec>\n \n Discussion<\/jats:title>\n The findings indicate that multi-cue normality modeling remains effective after patient-level aggregation and provides quantitative localization capability on an external nodule cohort. Same-source comparisons within COVID-CT-MD reduce, but do not eliminate, concern about dataset-source confounding. Because the study used retrospective public datasets and lacked prospective patient-level external validation, the results should be interpreted as methodological evidence rather than clinical validation.<\/jats:p>\n <\/jats:sec>","DOI":"10.3389\/fmed.2026.1927996","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:28:03Z","timestamp":1790310483000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Codebook-guided multi-cue normality modeling for pulmonary CT anomaly detection"],"prefix":"10.3389","volume":"13","author":[{"given":"Huizhong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, Faculty of Science, The University of Sydney","place":["Sydney, NSW, Australia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens","year":"2017","journal-title":"Med Image Anal"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3539","DOI":"10.1109\/JBHI.2020.3030853","article-title":"M3Lung-Sys: a deep learning system for multi-class lung pneumonia screening from CT imaging","volume":"24","author":"Qian","year":"2020","journal-title":"IEEE J Biomed Health Inform"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2572","DOI":"10.1109\/TMI.2020.2994908","article-title":"Prior-attention residual learning for more discriminative COVID-19 screening in CT images","volume":"39","author":"Wang","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"key":"B4","doi-asserted-by":"publisher","first-page":"2463","DOI":"10.1109\/TMI.2021.3079709","article-title":"Joint learning of 3D lesion segmentation and classification for explainable COVID-19 diagnosis","volume":"40","author":"Wang","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"B5","doi-asserted-by":"publisher","first-page":"4080","DOI":"10.1038\/s41467-020-17971-2","article-title":"Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets","volume":"11","author":"Harmon","year":"2020","journal-title":"Nat Commun"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2626","DOI":"10.1109\/TMI.2020.2996645","article-title":"Inf-Net: automatic COVID-19 lung infection segmentation from CT images","volume":"39","author":"Fan","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"key":"B7","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1148\/radiol.2020192224","article-title":"Preparing medical imaging data for machine learning","volume":"295","author":"Willemink","year":"2020","journal-title":"Radiology"},{"key":"B8","doi-asserted-by":"publisher","first-page":"101935","DOI":"10.1016\/j.artmed.2020.101935","article-title":"Handling imbalanced medical image data: a deep-learning-based one-class classification approach","volume":"108","author":"Gao","year":"2020","journal-title":"Artif Intell Med"},{"key":"B9","author":"Schlegl","year":""},{"key":"B10","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.media.2019.01.010","article-title":"f-AnoGAN: fast unsupervised anomaly detection with generative adversarial networks","volume":"54","author":"Schlegl","year":"2019","journal-title":"Med Image Anal"},{"key":"B11","author":"Baur","year":""},{"key":"B12","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1007\/s10278-020-00413-2","article-title":"Unsupervised deep anomaly detection in chest radiographs","volume":"34","author":"Nakao","year":"2021","journal-title":"J Digit Imaging"},{"key":"B13","author":"Bao","year":""},{"key":"B14","author":"van den Oord","year":""},{"key":"B15","doi-asserted-by":"publisher","first-page":"1032","DOI":"10.1109\/TMI.2020.3045295","article-title":"MAMA Net: multi-scale attention memory autoencoder network for anomaly detection","volume":"40","author":"Chen","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"B16","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1109\/TMI.2021.3118223","article-title":"Proxy-bridged image reconstruction network for anomaly detection in medical images","volume":"41","author":"Zhou","year":"2022","journal-title":"IEEE Trans Med Imaging"},{"key":"B17","author":"Wolleb","year":""},{"key":"B18","author":"Defard","year":""},{"key":"B19","author":"Roth","year":""},{"key":"B20","author":"Salehi","year":""},{"key":"B21","author":"Rudolph","year":""},{"key":"B22","author":"Li","year":""},{"key":"B23","author":"Liu","year":""},{"key":"B24","author":"Liu","year":""},{"key":"B25","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1038\/s41597-021-00900-3","article-title":"COVID-CT-MD, COVID-19 computed tomography scan dataset applicable in machine learning and deep learning","volume":"8","author":"Afshar","year":"2021","journal-title":"Sci Data"},{"key":"B26","author":"Li","year":""},{"key":"B27","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/s41597-025-04838-8","article-title":"An integrated mycobacterial CT imaging dataset with multispecies information","volume":"12","author":"Han","year":"2025","journal-title":"Sci Data"},{"key":"B28","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1118\/1.3528204","article-title":"The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans","volume":"38","author":"Armato III","year":"2011","journal-title":"Med Phys"},{"key":"B29","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1186\/s41747-020-00173-2","article-title":"Automatic lung segmentation in routine imaging is primarily a data diversity problem, not a methodology problem","volume":"4","author":"Hofmanninger","year":"2020","journal-title":"Eur Radiol Exp"},{"key":"B30","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.neunet.2021.12.008","article-title":"UTRAD: anomaly detection and localization with U-transformer","volume":"147","author":"Chen","year":"2022","journal-title":"Neural Netw"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1927996\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T04:28:03Z","timestamp":1790310483000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1927996\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"references-count":30,"alternative-id":["10.3389\/fmed.2026.1927996"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1927996","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]},"article-number":"1927996"}}