{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T06:00:58Z","timestamp":1785477658135,"version":"3.56.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"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":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Chest X-ray is the standard screening tool for pulmonary diseases, enabling early detection and timely intervention of lung lesions. Due to scarce and costly abnormal labeling of chest X-rays, unsupervised anomaly detection trained only with normal images has become a major research focus, especially, reconstruction-based methods are favored for learning normal data patterns and making it easier to visualize abnormal regions. Although the current reconstruction-based methods of chest X-rays have achieved good result, they have three problems. Firstly, over-reliance on pixel-level alignment in the spatial domain hinders the capture of global information. Secondly, single-layer feature comparison between original and reconstructed images lacks multi-layer and multi-image analysis, resulting in poor feature consistency. Thirdly, using reconstruction error as anomaly score struggles to balance sensitivity to anomalies and fidelity to normal. Using a reconstruction-based approach trained only on normal images, this study improves rapid screening of thoracic abnormalities and shifts screening criteria toward earlier detection of chest lesions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose an architecture DualA-AD including Dual-domain Adversarial Learning (DAL), Feature Constraint Module (FCM) and Distributed Anomaly Score (DAS). In the training stage, DAL captures image details and global information by integrating spatial and frequency domains for dual-domain adversarial reconstruction. While FCM improves feature consistency between reconstructed and original image by analyzing multi-layer feature difference within individual images and similarity differences across multiple images. In the testing stage, DAS enhances image discriminability by fitting a discriminator\u2019s output on the training set as the real distribution and quantifying the deviation of images from this distribution. On three mainstream public chest X-ray datasets, the model was trained using only normal chest X-rays and evaluated on their respective test sets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Result<\/jats:title>\n                    <jats:p>In the experiments on three datasets, DualA-AD achieved the best AUC, ACC, and F1 scores against classical, general, and specialized baselines, with AUC improvements over the SOTA of 0.93, 0.77, and 0.48%, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>DualA-AD improves the accuracy for distinguishing normal and abnormal chest X-rays. The method provides an efficient scheme for fast, low-cost intelligent detection of lung abnormalities, with great potential for computer-aided chest radiographic diagnosis and early prevention and management of pulmonary disorders.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1757295","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T05:39:11Z","timestamp":1785476351000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-domain adversarial learning and feature constraint for unsupervised anomaly detection in chest X-rays"],"prefix":"10.3389","volume":"13","author":[{"given":"Na","family":"Liang","sequence":"first","affiliation":[{"name":"College of Computer Science, Chongqing University","place":["Chongqing, China"]},{"name":"Chongqing Traditional Chinese Medicine Hospital","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yehong","family":"Tong","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengliang","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Chongqing University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Centre for Medical Big Data and Artificial Intelligence, The First Affiliated Hospital (Southwest Hospital) of Army Medical University (Third Military Medical University)","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1016\/j.chest.2022.01.014","article-title":"Global impact of respiratory disease: what can we do, together, to make a difference","volume":"161","author":"Levine","year":"2022","journal-title":"Chest"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"12607","DOI":"10.1007\/s10462-023-10457-9","article-title":"Review on chest pathogies detection systems using deep learning techniques","volume":"56","author":"Rehman","year":"2023","journal-title":"Artif Intell Rev"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1109\/TMI.2020.3040950","article-title":"Viral pneumonia screening on chest x-rays using confidence-aware anomaly detection","volume":"40","author":"Zhang","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"key":"ref4","first-page":"2097","author":"Wang","year":"2017"},{"key":"ref5","first-page":"25","author":"Nie","year":"2023"},{"key":"ref6","first-page":"10632","author":"Liu","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"107086","DOI":"10.1016\/j.isci.2023.107086","article-title":"Anatomy-aware self-supervised learning for anomaly detection in chest radiographs","volume":"26","author":"Sato","year":"2023","journal-title":"Iscience"},{"key":"ref8","first-page":"529","volume-title":"Medical Image Computing and Computer Assisted Intervention","author":"Mao","year":"2020"},{"key":"ref9","first-page":"15979","author":"He","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1016\/j.procs.2023.10.084","article-title":"Masked autoencoders for unsupervised anomaly detection in medical images","volume":"225","author":"Georgescu","year":"2023","journal-title":"Procedia Comput Sci"},{"key":"ref11","first-page":"398","author":"Yu","year":"2022"},{"key":"ref12","first-page":"195","author":"Bozorgtabar","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"ref14","first-page":"590","author":"Irvin","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1038\/s41597-022-01498-w","article-title":"Vindr-cxr: an open dataset of chest x-rays with radiologist\u2019s annotations","volume":"9","author":"Nguyen","year":"2022","journal-title":"Sci Data"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1162\/089976601750264965","article-title":"Estimating the support of a high-dimensional distribution","volume":"13","author":"Sch\u00a8olkopf","year":"2001","journal-title":"Neural Comput"},{"key":"ref17","first-page":"4393","article-title":"Deep one-class classification. In: International conference on machine learning","author":"Ruff","year":"2018"},{"key":"ref18","first-page":"9729","author":"He","year":"2020"},{"key":"ref19","first-page":"9659","author":"Li","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"168496","DOI":"10.1109\/access.2021.3136263","article-title":"One-class classifier for chest x-ray anomaly detection via contrastive patch-based percentile","volume":"9","author":"Kim","year":"2021","journal-title":"IEEE Access"},{"key":"ref21","first-page":"1","author":"Gholamipoor","year":"2022"},{"key":"ref22","first-page":"304","author":"Bercea","year":"2023"},{"key":"ref23","first-page":"23890","author":"Xiang","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"6070","DOI":"10.1109\/TPAMI.2024.3382009","article-title":"Exploiting structural consistency of chest anatomy for unsupervised anomaly detection in radiography images","volume":"46","author":"Xiang","year":"2024","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref25","first-page":"11","author":"Tian","year":"2023"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11548-023-03031-9","article-title":"High-quality semi-supervised anomaly detection with generative adversarial networks","volume":"19","author":"Sato","year":"2023","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"ref27","first-page":"3842","author":"Bhatt","year":"2021"},{"key":"ref28","first-page":"1","author":"Xie","year":"2023"},{"key":"ref29","first-page":"2910","author":"Ni","year":"2024"},{"key":"ref30","first-page":"2604","author":"Liu","year":"2019"},{"key":"ref31","first-page":"13","author":"Kriegel","year":"2011"},{"key":"ref32","first-page":"584","author":"Cai","year":"2022"},{"key":"ref33","first-page":"622","author":"Akcay","year":"2018"},{"key":"ref34","doi-asserted-by":"crossref","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":"ref35","first-page":"1705","author":"Gong","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"3641","DOI":"10.1109\/TMI.2021.3093883","article-title":"Anomaly detection for medical images using selfsupervised and translation-consistent features","volume":"40","author":"Zhao","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1102","DOI":"10.1109\/TMI.2023.3327720","article-title":"Encoder-decoder contrast for unsupervised anomaly detection in medical images","volume":"43","author":"Guo","year":"2023","journal-title":"IEEE Trans Med Imaging"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"2770","DOI":"10.1109\/TIP.2024.3381435","article-title":"Anomaly detection for medical images using heterogeneous auto-encoder","volume":"33","author":"Lu","year":"2024","journal-title":"IEEE Trans Image Process"},{"key":"ref39","first-page":"520","author":"Gu","year":"2024"},{"key":"ref40","first-page":"618","author":"Selvaraju","year":"2017"},{"key":"ref41","first-page":"1597","author":"Chen","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"102930","DOI":"10.1016\/j.media.2023.102930","article-title":"Self-supervised pseudo multi-class pre-training for unsupervised anomaly detection and segmentation in medical images","volume":"90","author":"Tian","year":"2023","journal-title":"Med Image Anal"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1757295\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T05:39:12Z","timestamp":1785476352000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1757295\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":42,"alternative-id":["10.3389\/fmed.2026.1757295"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1757295","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"article-number":"1757295"}}