{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:33:46Z","timestamp":1787924026911,"version":"build-2784847793"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"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:p>\n                    Tuberculosis (TB) is a global infectious disease, and chest x-ray (CXR) examination is a primary screening method. However, manual image interpretation can suffer from low diagnostic efficiency, poor consistency, and limitations imposed by the experience of the interpreters, necessitating the development of intelligent identification tools. This study aims to construct and validate a deep learning ensemble model-based CXR image recognition system for TB, achieving accurate and intelligent screening. The Shenzhen TB CXR public dataset was used as the training dataset, randomly divided into training and test datasets; the Montgomery public dataset was used as an independent external validation dataset. Nine convolutional neural network models (DenseNet201, EfficientNetB7, EfficientNetV2S, InceptionResNetV2, MobileNetV3Large, NASNetLarge, ResNet50V2, VGG19, and Xception) were built using the PyTorch framework and benchmarked. The optimal model was selected using the F1 score as the core metric. Furthermore, using the raw scores of the individual models as input features, four ensemble strategies\u2014linear regression, logistic regression, performance-weighted averaging, and eXtreme Gradient Boosting (XGBoost)\u2014were constructed to evaluate the classification performance and generalization ability of each model. The results show that all nine individual models can distinguish between normal and TB CXR images (all\n                    <jats:italic>P<\/jats:italic>\n                    \u2009&amp;lt;\u20090.001). The VGG19 model performed best on the independent validation dataset, with an area under the curve (AUC) of 0.853 and an F1 score of 0.793. The ensemble models further improved classification performance. The performance-weighted averaging ensemble model achieved an AUC of 0.880 and F1 score of 0.861 on the independent validation dataset, outperforming the optimal individual model and other ensemble strategies. The performance-weighted averaging ensemble model constructed in this study can accurately identify pulmonary TB CXR images and has high generalization performance. It can provide an intelligent tool for primary-level pulmonary TB screening. In the future, it can be further prospectively validated in multi-center, large-sample clinical datasets to promote its clinical translation and application.\n                  <\/jats:p>","DOI":"10.3389\/fmed.2026.1903513","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:07:21Z","timestamp":1787922441000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An ensemble model approach for identifying pulmonary tuberculosis on chest X-ray"],"prefix":"10.3389","volume":"13","author":[{"given":"Weiying","family":"Qin","sequence":"first","affiliation":[{"name":"Department of Radiology, Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine","place":["Nanjing, China"]},{"name":"Jiangsu Province Academy of Traditional Chinese Medicine","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingxin","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine","place":["Nanjing, China"]},{"name":"Jiangsu Province Academy of Traditional Chinese Medicine","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Jing","sequence":"additional","affiliation":[{"name":"Department of Radiology, Affiliated Hospital of Integrated Traditional Chinese and Western Medicine, Nanjing University of Chinese Medicine","place":["Nanjing, China"]},{"name":"Jiangsu Province Academy of Traditional Chinese Medicine","place":["Nanjing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"107325","DOI":"10.1016\/j.ijid.2024.107325","article-title":"Insights from the 2024 WHO global Tuberculosis report\u2014more comprehensive action, innovation, and investments required for achieving WHO End TB goals","volume":"150","author":"Goletti","year":"2025","journal-title":"Int J Infect Dis"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e605","DOI":"10.1016\/S2589-7500(24)00118-3","article-title":"Computer-aided detection of tuberculosis from chest radiographs in a tuberculosis prevalence survey in South Africa: external validation and modeled impacts of commercially available artificial intelligence software","volume":"6","author":"Qin","year":"2024","journal-title":"Lancet Digit Health"},{"key":"B3","doi-asserted-by":"publisher","first-page":"10.1056\/AIoa2400018","DOI":"10.1056\/aioa2400018","article-title":"Prospective multi-site validation of AI to detect tuberculosis and chest-x-ray abnormalities","volume":"1","author":"Kazemzadeh","year":"2024","journal-title":"NEJM AI"},{"key":"B4","doi-asserted-by":"publisher","first-page":"3223","DOI":"10.21037\/jtd-2025-604","article-title":"A systematic review and meta-analysis of artificial intelligence software for tuberculosis diagnosis using chest x-ray imaging","volume":"17","author":"Han","year":"2025","journal-title":"J Thorac Dis"},{"key":"B5","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1038\/s41746-025-01832-7","article-title":"Population-scale cross-sectional observational study for AI-powered TB screening on one million CXRs","volume":"8","author":"Munjal","year":"2025","journal-title":"npj Digit Med"},{"key":"B6","doi-asserted-by":"publisher","first-page":"e83041","DOI":"10.2196\/83041","article-title":"AI-powered chest x-ray for diagnosing pulmonary tuberculosis in county and township health care facilities in yichang: retrospective, real-world study","volume":"27","author":"Jiang","year":"2025","journal-title":"J Med Internet Res"},{"key":"B7","doi-asserted-by":"publisher","first-page":"e43154","DOI":"10.2196\/43154","article-title":"Machine and deep learning for tuberculosis detection on chest x-rays: systematic literature review","volume":"25","author":"Hansun","year":"2023","journal-title":"J Med Internet Res"},{"key":"B8","doi-asserted-by":"publisher","first-page":"3501","DOI":"10.21037\/qims-23-1600","article-title":"Application of convolutional neural networks in medical images: a bibliometric analysis","volume":"14","author":"Jia","year":"2024","journal-title":"Quant Imaging Med Surg"},{"key":"B9","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1148\/radiol.212213","article-title":"Deep learning detection of active pulmonary tuberculosis at chest radiography matched the clinical performance of radiologists","volume":"306","author":"Kazemzadeh","year":"2023","journal-title":"Radiology"},{"key":"B10","doi-asserted-by":"publisher","first-page":"14917","DOI":"10.1038\/s41598-024-65703-z","article-title":"A deep learning-based algorithm for pulmonary tuberculosis detection in chest radiography","volume":"14","author":"Chen","year":"2024","journal-title":"Sci Rep"},{"key":"B11","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/s10278-023-00952-4","article-title":"Deep learning-based diagnosis of pulmonary tuberculosis on chest x-ray in the emergency department: a retrospective study","volume":"37","author":"Wang","year":"2024","journal-title":"J Imaging Inform Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"0426","DOI":"10.34133\/research.0426","article-title":"Development and external validation of an artificial intelligence-based method for scalable chest radiograph diagnosis: a multi-country cross-sectional study","volume":"7","author":"Liu","year":"2024","journal-title":"Research"},{"key":"B13","doi-asserted-by":"publisher","first-page":"3501","DOI":"10.1007\/s00330-022-09315-z","article-title":"Multicentre external validation of a commercial artificial intelligence software to analyze chest radiographs in health screening environments with low disease prevalence","volume":"33","author":"Kim","year":"2023","journal-title":"Eur Radiol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s10586-022-03664-6","article-title":"A multichannel EfficientNet deep learning-based stacking ensemble approach for lung disease detection using chest x-ray images","volume":"26","author":"Ravi","year":"2023","journal-title":"Cluster Comput"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1391184","DOI":"10.3389\/fmed.2024.1391184","article-title":"A robust ensemble deep learning framework for accurate diagnoses of tuberculosis from chest radiographs","volume":"11","author":"Sun","year":"2024","journal-title":"Front Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"110424","DOI":"10.1016\/j.patcog.2024.110424","article-title":"Federated learning for medical image analysis: a survey","volume":"151","author":"Guan","year":"2024","journal-title":"Pattern Recognit"},{"key":"B17","doi-asserted-by":"publisher","first-page":"e69068","DOI":"10.2196\/69068","article-title":"Diagnostic performance of artificial intelligence\u2013based methods for tuberculosis detection: systematic review","volume":"27","author":"Hansun","year":"2025","journal-title":"J Med Internet Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1242","DOI":"10.1038\/s41598-025-30792-x","article-title":"Ensemble deep learning architectures for detecting pulmonary tuberculosis in chest x-rays","volume":"16","author":"Garc\u00eda Seco de Herrera","year":"2026","journal-title":"Sci Rep"},{"key":"B19","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3390\/data7070095","article-title":"Annotations of lung abnormalities in Shenzhen chest x-ray dataset for computer-aided screening of pulmonary diseases","volume":"7","author":"Yang","year":"2022","journal-title":"Data"},{"key":"B20","doi-asserted-by":"publisher","first-page":"475","DOI":"10.3978\/j.issn.2223-4292.2014.11.20","article-title":"Two public chest x-ray datasets for computer-aided screening of pulmonary diseases","volume":"4","author":"Jaeger","year":"2014","journal-title":"Quant Imaging Med Surg"},{"key":"B21","doi-asserted-by":"publisher","first-page":"104667","DOI":"10.1016\/j.bspc.2023.104667","article-title":"Tuberculosis chest x-ray detection using CNN-based hybrid segmentation and classification approach","volume":"84","author":"Iqbal","year":"2023","journal-title":"Biomed Signal Process Control"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e63356","DOI":"10.7759\/cureus.63356","article-title":"Self-trained convolutional neural network for improved tuberculosis detection in chest x-ray images","volume":"16","author":"Sarawagi","year":"2024","journal-title":"Cureus"},{"key":"B23","doi-asserted-by":"publisher","first-page":"100196","DOI":"10.1016\/j.ibmed.2024.100196","article-title":"Advancing tuberculosis screening: a tailored CNN approach for accurate chest x-ray analysis and practical clinical integration","volume":"11","author":"Mujeeb Rahman","year":"2025","journal-title":"Intell Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"42839","DOI":"10.1109\/ACCESS.2023.3270774","article-title":"An improved DenseNet deep neural network model for Tuberculosis detection using chest x-ray images","volume":"11","author":"Huy","year":"2023","journal-title":"IEEE Access"},{"key":"B25","doi-asserted-by":"publisher","first-page":"3216","DOI":"10.3390\/diagnostics15243216","article-title":"A lightweight hybrid deep learning model for tuberculosis detection from chest x-rays","volume":"15","author":"Owda","year":"2025","journal-title":"Diagnostics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1007\/s44163-025-00329-2","article-title":"Tuberculosis detection with customized CNN and oversampling techniques: a deep learning approach","volume":"5","author":"Shekar","year":"2025","journal-title":"Discov Artif Intell"},{"key":"B27","doi-asserted-by":"publisher","first-page":"105063","DOI":"10.1016\/j.imavis.2024.105063","article-title":"Detection of tuberculosis using customized MobileNet and transfer learning from chest x-ray image","volume":"147","author":"Shome","year":"2024","journal-title":"Image Vis Comput"},{"key":"B28","doi-asserted-by":"publisher","first-page":"106646","DOI":"10.1016\/j.compbiomed.2023.106646","article-title":"High-precision multiclass classification of lung disease through customized MobileNetV2 from chest x-ray images","volume":"155","author":"Shamrat","year":"2023","journal-title":"Comput Biol Med"},{"key":"B29","doi-asserted-by":"publisher","first-page":"14657","DOI":"10.1038\/s41598-024-64941-5","article-title":"A retrospective study of deep learning generalization across two centers and multiple models of x-ray devices using COVID-19 chest-x-rays","volume":"14","author":"Fern\u00e1ndez-Miranda","year":"2024","journal-title":"Sci Rep"},{"key":"B30","doi-asserted-by":"publisher","first-page":"11383","DOI":"10.1038\/s41598-025-95390-3","article-title":"Addressing cross-population domain shift in chest x-ray classification through supervised adversarial domain adaptation","volume":"15","author":"Musa","year":"2025","journal-title":"Sci Rep"},{"key":"B31","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1016\/j.jksuci.2023.01.014","article-title":"A comprehensive review on ensemble deep learning: opportunities and challenges","volume":"35","author":"Mohammed","year":"2023","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"4869","DOI":"10.32604\/cmc.2025.064944","article-title":"Optimized deep feature learning with hybrid ensemble for breast cancer classification","volume":"84","author":"Ogundokun","year":"2025","journal-title":"Comput Mater Contin"},{"key":"B33","doi-asserted-by":"publisher","first-page":"8803","DOI":"10.1097\/MS9.0000000000004166","article-title":"Assessing the generalizability of artificial intelligence in radiology: a systematic review of performance across different clinical data settings","volume":"87","author":"Suleman","year":"2025","journal-title":"Ann Med Surg"},{"key":"B34","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/s10278-025-01494-7","article-title":"Domain shift analysis in chest radiographs classification in a veterans healthcare administration population","volume":"39","author":"Chandrashekar","year":"2026","journal-title":"J Imaging Inform Med"},{"key":"B35","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1038\/s41746-024-01118-4","article-title":"Shortcut learning in medical AI hinders generalization: method for estimating AI model generalization without external data","volume":"7","author":"Ong Ly","year":"2024","journal-title":"npj Digit Med"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1903513\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:07:23Z","timestamp":1787922443000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1903513\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":35,"alternative-id":["10.3389\/fmed.2026.1903513"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1903513","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]},"article-number":"1903513"}}