{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:15:17Z","timestamp":1793132117315,"version":"4.5.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:00:00Z","timestamp":1767916800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:00:00Z","timestamp":1767916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"University of Essex GCRF QR Engagement Fund provided by Research England","award":["G026"],"award-info":[{"award-number":["G026"]}],"id":[{"id":"https:\/\/ror.org\/02wxr8x18","id-type":"ROR","asserted-by":"crossref"}]},{"name":"University of Essex GCRF QR Engagement Fund provided by Research England","award":["G026"],"award-info":[{"award-number":["G026"]}],"id":[{"id":"https:\/\/ror.org\/02wxr8x18","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Thai Health Systems Research Institute","award":["HSRI 63-147"],"award-info":[{"award-number":["HSRI 63-147"]}],"id":[{"id":"https:\/\/ror.org\/04yz0nm53","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Thai Health Systems Research Institute","award":["HSRI 63-147"],"award-info":[{"award-number":["HSRI 63-147"]}],"id":[{"id":"https:\/\/ror.org\/04yz0nm53","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Tuberculosis (TB) remains a major global health challenge, causing approximately 1.4 million deaths annually. In many high-burden regions, limited access to expert radiological interpretation leads to delayed or missed diagnoses. To address this, we propose a cost-effective, automated TB screening method suitable for under-resourced settings. Our method integrates a Convolutional Autoencoder Neural Network and a Multi-Scale Convolutional Neural Network with deep layer aggregation into an ensemble learning architecture for robust TB detection from chest radiographs. The framework was evaluated on two public datasets and one private dataset, achieving 99% sensitivity and 94% specificity on the Shenzhen dataset, and consistently high accuracy across all datasets. Expert radiologists reviewed a subset of the predictions, confirming the clinical relevance and diagnostic reliability of the model. The ensemble approach demonstrated strong generalisability, effectively identifying active pulmonary TB in chest X-rays from a globally representative cohort. It also outperformed existing classifiers, achieving a state-of-the-art Area Under the Receiver Operating Characteristic of 0.98. These results highlight the potential of our approach as a practical and scalable tool for TB screening, particularly in low- and middle-income countries where radiological resources are limited.<\/jats:p>","DOI":"10.1038\/s41598-025-30792-x","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T13:54:48Z","timestamp":1767966888000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Ensemble deep learning architectures for detecting pulmonary tuberculosis in chest X-rays"],"prefix":"10.1038","volume":"16","author":[{"given":"Alba","family":"Garc\u00eda Seco de Herrera","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ekin","family":"Yagis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nichapat","family":"Pinpo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vahid","family":"Abolghasemi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jarutas","family":"Andritsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sitthichok","family":"Chaichulee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yashin","family":"Dicente Cid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thammasin","family":"Ingviya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,9]]},"reference":[{"key":"30792_CR1","unstructured":"(WHO), W. H.\u00a0O. Global tuberculosis report 2024 (2024). Licence: CC BY-NC-SA 3.0 IGO."},{"key":"30792_CR2","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1148\/rg.2017160032","volume":"37","author":"AC Nachiappan","year":"2017","unstructured":"Nachiappan, A. C. et al. Pulmonary tuberculosis: Role of radiology in diagnosis and management. Radiographics 37, 52\u201372 (2017).","journal-title":"Radiographics"},{"key":"30792_CR3","unstructured":"(WHO), W. H.\u00a0O. WHO consolidated guidelines on tuberculosis module 2: Screening \u2013 systematic screening for tuberculosis disease (2021). Accessed on 6th November 2024."},{"key":"30792_CR4","doi-asserted-by":"crossref","unstructured":"Ju, C., Bibaut, A.\u00a0l. & van der Laan, M. The relative performance of ensemble methods with deep convolutional neural networks for image classification. J. Appl. Stat. 45, 2800\u20132818 (2018).","DOI":"10.1080\/02664763.2018.1441383"},{"key":"30792_CR5","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.neucom.2015.09.116","volume":"187","author":"Y Guo","year":"2016","unstructured":"Guo, Y. et al. Deep learning for visual understanding: A review. Neurocomputing 187, 27\u201348 (2016).","journal-title":"Neurocomputing"},{"key":"30792_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0249399","volume":"16","author":"T Kwon","year":"2021","unstructured":"Kwon, T. et al. Diagnostic performance of artificial intelligence model for pneumonia from chest radiography. PLOS ONE 16, 1\u201313. https:\/\/doi.org\/10.1371\/journal.pone.0249399 (2021).","journal-title":"PLOS ONE"},{"key":"30792_CR7","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.3390\/biology10111084","volume":"10","author":"Y Yan","year":"2021","unstructured":"Yan, Y., Yao, X.-J., Wang, S.-H. & Zhang, Y.-D. A survey of computer-aided tumor diagnosis based on convolutional neural network. Biology 10, 1084 (2021).","journal-title":"Biology"},{"key":"30792_CR8","doi-asserted-by":"crossref","unstructured":"Hwang, S., Kim, H.-E., Jeong, J. & Kim, H.-J. A novel approach for tuberculosis screening based on deep convolutional neural networks. In Medical imaging 2016: computer-aided diagnosis, vol. 9785, 750\u2013757 (SPIE, 2016).","DOI":"10.1117\/12.2216198"},{"key":"30792_CR9","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1148\/radiol.2017162326","volume":"284","author":"P Lakhani","year":"2017","unstructured":"Lakhani, P. & Sundaram, B. Deep learning at chest radiography: Automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 284, 574\u2013582 (2017).","journal-title":"Radiology"},{"key":"30792_CR10","doi-asserted-by":"crossref","unstructured":"Liu, C. et al. TX-CNN: Detecting tuberculosis in chest X-ray images using convolutional neural network. In 2017 IEEE international conference on image processing (ICIP), 2314\u20132318 (IEEE, 2017).","DOI":"10.1109\/ICIP.2017.8296695"},{"key":"30792_CR11","doi-asserted-by":"crossref","unstructured":"Yadav, O., Passi, K. & Jain, C.\u00a0K. Using deep learning to classify X-ray images of potential tuberculosis patients. In IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2368\u20132375 (IEEE, 2018).","DOI":"10.1109\/BIBM.2018.8621525"},{"key":"30792_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"30792_CR13","doi-asserted-by":"crossref","unstructured":"Li, L., Huang, H. & Jin, X. AE-CNN classification of pulmonary tuberculosis based on ct images. In 2018 9th International Conference on Information Technology in Medicine and Education (ITME), 39\u201342 (IEEE, 2018).","DOI":"10.1109\/ITME.2018.00020"},{"key":"30792_CR14","doi-asserted-by":"crossref","unstructured":"Norval, M., Wang, Z. & Sun, Y. Pulmonary tuberculosis detection using deep learning convolutional neural networks. In Proceedings of the 3rd International Conference on Video and Image Processing, 47\u201351 (2019).","DOI":"10.1145\/3376067.3376068"},{"key":"30792_CR15","doi-asserted-by":"publisher","first-page":"191586","DOI":"10.1109\/ACCESS.2020.3031384","volume":"8","author":"T Rahman","year":"2020","unstructured":"Rahman, T. et al. Reliable tuberculosis detection using chest X-ray with deep learning, segmentation and visualization. IEEE Access 8, 191586\u2013191601 (2020).","journal-title":"IEEE Access"},{"key":"30792_CR16","first-page":"475","volume":"4","author":"S Jaeger","year":"2014","unstructured":"Jaeger, S. et al. Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. Quant. Imag. Med. Surg. 4, 475 (2014).","journal-title":"Quant. Imag. Med. Surg."},{"key":"30792_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107252","volume":"93","author":"M Rahman","year":"2021","unstructured":"Rahman, M., Cao, Y., Sun, X., Li, B. & Hao, Y. Deep pre-trained networks as a feature extractor with XGBoost to detect tuberculosis from chest X-ray. Comput. Electr. Eng. 93, 107252 (2021).","journal-title":"Comput. Electr. Eng."},{"key":"30792_CR18","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K.\u00a0Q. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, 4700\u20134708 (2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"30792_CR19","doi-asserted-by":"crossref","unstructured":"Szegedy, C. et al. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, 1\u20139 (2015).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"30792_CR20","unstructured":"Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations (ICLR) (2015)."},{"key":"30792_CR21","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G.\u00a0E. Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25 (2012)."},{"key":"30792_CR22","doi-asserted-by":"publisher","first-page":"2538","DOI":"10.1109\/TBME.2012.2205687","volume":"59","author":"MM Fraz","year":"2012","unstructured":"Fraz, M. M. et al. An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Trans. Biomed. Eng. 59, 2538\u20132548 (2012).","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"30792_CR23","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s13246-020-00966-0","volume":"44","author":"M Ayaz","year":"2021","unstructured":"Ayaz, M., Shaukat, F. & Raja, G. Ensemble learning based automatic detection of tuberculosis in chest X-ray images using hybrid feature descriptors. Phys. Eng. Sci. Med. 44, 183\u2013194 (2021).","journal-title":"Phys. Eng. Sci. Med."},{"key":"30792_CR24","doi-asserted-by":"publisher","first-page":"27318","DOI":"10.1109\/ACCESS.2020.2971257","volume":"8","author":"S Rajaraman","year":"2020","unstructured":"Rajaraman, S. & Antani, S. K. Modality-specific deep learning model ensembles toward improving tb detection in chest radiographs. IEEE Access 8, 27318\u201327326 (2020).","journal-title":"IEEE Access"},{"key":"30792_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10723-021-09596-6","volume":"20","author":"S-H Wang","year":"2022","unstructured":"Wang, S.-H., Satapathy, S. C., Zhou, Q., Zhang, X. & Zhang, Y.-D. Secondary pulmonary tuberculosis identification via Pseudo-Zernike moment and deep stacked sparse autoencoder. J. Grid Comput. 20, 1\u201316 (2022).","journal-title":"J. Grid Comput."},{"key":"30792_CR26","doi-asserted-by":"publisher","unstructured":"El-Ghany, S.\u00a0A., Elmogy, M., A.\u00a0Mahmood, M. & Abd El-Aziz, A.\u00a0A. A robust tuberculosis diagnosis using chest X-rays based on a hybrid vision transformer and principal component analysis. Diagnostics 14, https:\/\/doi.org\/10.3390\/diagnostics14232736 (2024).","DOI":"10.3390\/diagnostics14232736"},{"key":"30792_CR27","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1186\/s12880-025-01630-3","volume":"25","author":"K Vanitha","year":"2025","unstructured":"Vanitha, K., Mahesh, T., Kumar, V. V. & Guluwadi, S. Enhanced tuberculosis detection using vision transformers and explainable AI with a Grad-CAM approach on chest X-rays. BMC Med. Imag. 25, 96. https:\/\/doi.org\/10.1186\/s12880-025-01630-3 (2025).","journal-title":"BMC Med. Imag."},{"key":"30792_CR28","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1038\/s41598-023-28079-0","volume":"13","author":"J Devasia","year":"2023","unstructured":"Devasia, J., Goswami, H., Lakshminarayanan, S., Rajaram, M. & Adithan, S. Deep learning classification of active tuberculosis lung zones wise manifestations using chest X-rays: A multi label approach. Sci. Rep. 13, 887. https:\/\/doi.org\/10.1038\/s41598-023-28079-0 (2023).","journal-title":"Sci. Rep."},{"key":"30792_CR29","doi-asserted-by":"crossref","unstructured":"Misra, P. & Yadav, A.\u00a0S. Impact of preprocessing methods on healthcare predictions. In Proceedings of 2nd International Conference on Advanced Computing and Software Engineering (ICACSE) (2019).","DOI":"10.2139\/ssrn.3349586"},{"key":"30792_CR30","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1007\/s11704-016-5203-5","volume":"10","author":"S Almuhaideb","year":"2016","unstructured":"Almuhaideb, S. & Menai, M. E. B. Impact of preprocessing on medical data classification. Front. Comput. Sci. 10, 1082\u20131102 (2016).","journal-title":"Front. Comput. Sci."},{"key":"30792_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TMI.1987.4307791","volume":"6","author":"RH Sherrier","year":"1987","unstructured":"Sherrier, R. H. & Johnson, G. Regionally adaptive histogram equalization of the chest. IEEE Trans. Med. Imag. 6, 1\u20137 (1987).","journal-title":"IEEE Trans. Med. Imag."},{"key":"30792_CR32","doi-asserted-by":"crossref","unstructured":"Yagis, E., Garc\u00eda Seco de Herrera, A. & Citi, L. Convolutional autoencoder based deep learning approach for alzheimer\u2019s disease diagnosis using brain mri. In 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS), 486\u2013491 (IEEE, 2021).","DOI":"10.1109\/CBMS52027.2021.00097"},{"key":"30792_CR33","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In 2015 IEEE International Conference on Computer Vision (ICCV), 1026\u20131034, https:\/\/doi.org\/10.1109\/ICCV.2015.123 (2015).","DOI":"10.1109\/ICCV.2015.123"},{"key":"30792_CR34","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2019.2938758","volume":"43","author":"S-H Gao","year":"2021","unstructured":"Gao, S.-H. et al. Res2Net: A new multi-scale backbone architecture. IEEE Trans. Pattern Anal. Mach. Intell. 43, 652\u2013662. https:\/\/doi.org\/10.1109\/TPAMI.2019.2938758 (2021).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30792_CR35","doi-asserted-by":"publisher","unstructured":"Yu, F., Wang, D., Shelhamer, E. & Darrell, T. Deep Layer Aggregation. In 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2403\u20132412, https:\/\/doi.org\/10.1109\/CVPR.2018.00255 (IEEE, Salt Lake City, UT, 2018).","DOI":"10.1109\/CVPR.2018.00255"},{"key":"30792_CR36","doi-asserted-by":"publisher","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z. & He, K. Aggregated residual transformations for deep neural networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5987\u20135995, https:\/\/doi.org\/10.1109\/CVPR.2017.634 (2017).","DOI":"10.1109\/CVPR.2017.634"},{"key":"30792_CR37","doi-asserted-by":"crossref","unstructured":"Dietterich, T.\u00a0G. Ensemble methods in machine learning. In International workshop on multiple classifier systems, 1\u201315 (Springer, 2000).","DOI":"10.1007\/3-540-45014-9_1"},{"key":"30792_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-01681-w","volume":"11","author":"E Yagis","year":"2021","unstructured":"Yagis, E. et al. Effect of data leakage in brain MRI classification using 2d convolutional neural networks. Sci. Rep. 11, 1\u201313 (2021).","journal-title":"Sci. Rep."},{"key":"30792_CR39","doi-asserted-by":"publisher","unstructured":"Consortium, T. M. Project MONAI. Zenodo https:\/\/doi.org\/10.5281\/zenodo.4323059 (2020).","DOI":"10.5281\/zenodo.4323059"},{"key":"30792_CR40","unstructured":"Ginsburg, B. et al. Stochastic gradient methods with layer-wise adaptive moments for training of deep networks. CoRR abs\/1905.11286 (2019). arXiv:1905.11286."},{"key":"30792_CR41","doi-asserted-by":"publisher","first-page":"349","DOI":"10.7861\/clinmedicine.13-4-349","volume":"13","author":"I Satia","year":"2013","unstructured":"Satia, I. et al. Assessing the accuracy and certainty in interpreting chest X-rays in the medical division. Clin. Med. 13, 349\u2013352. https:\/\/doi.org\/10.7861\/clinmedicine.13-4-349 (2013).","journal-title":"Clin. Med."},{"key":"30792_CR42","doi-asserted-by":"publisher","first-page":"20150023","DOI":"10.1259\/bjr.20150023","volume":"88","author":"E Ekpo","year":"2015","unstructured":"Ekpo, E., Egbe, N. & Akpan, B. Radiographers\u2019 performance in chest X-ray interpretation: The Nigerian experience. Br.J. Radiol. 88, 20150023 (2015).","journal-title":"Br.J. Radiol."},{"key":"30792_CR43","doi-asserted-by":"publisher","first-page":"2459","DOI":"10.1007\/s00330-013-2840-z","volume":"23","author":"CJ Waitt","year":"2013","unstructured":"Waitt, C. J. et al. The effect of a tuberculosis chest X-ray image reference set on non-expert reader performance. Eur. Radiol. 23, 2459\u20132468. https:\/\/doi.org\/10.1007\/s00330-013-2840-z (2013).","journal-title":"Eur. Radiol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-30792-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-30792-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-30792-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T21:08:20Z","timestamp":1768165700000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-30792-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,9]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["30792"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-30792-x","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,9]]},"assertion":[{"value":"13 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1242"}}