{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,20]],"date-time":"2026-11-20T00:08:32Z","timestamp":1795133312382,"version":"4.10.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:00:00Z","timestamp":1758844800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:00:00Z","timestamp":1758844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Vellore Institute of Technology, Vellore"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Tuberculosis (TB) is a serious infectious disease that remains a global health challenge. While chest X-rays (CXRs) are widely used for TB detection, manual interpretation can be subjective and time-consuming. Automated classification of CXRs into TB and non-TB cases can significantly support healthcare professionals in timely and accurate diagnosis. This paper introduces a hybrid deep learning approach for classifying CXR images. The solution is based on the CoAtNet framework, which combines the strengths of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). The model is pre-trained on the large-scale ImageNet dataset to ensure robust generalization across diverse images. The evaluation is conducted on the IN-CXR tuberculosis dataset from ICMR-NIRT, which contains a comprehensive collection of CXR images of both normal and abnormal categories. The hybrid model achieves a binary classification accuracy of 86.39% and an ROC-AUC score of 93.79%, outperforming tested baseline models that rely exclusively on either CNNs or ViTs when trained on this dataset. Furthermore, the integration of Local Interpretable Model-agnostic Explanations (LIME) enhances the interpretability of the model\u2019s predictions. This combination of reliable performance and transparent, interpretable results strengthens the model\u2019s role in AI-driven medical imaging research. Code will be made available upon request.<\/jats:p>","DOI":"10.1186\/s12880-025-01901-z","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T10:15:15Z","timestamp":1758881715000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Enhanced CoAtNet based hybrid deep learning architecture for automated tuberculosis detection in human chest X-rays"],"prefix":"10.1186","volume":"25","author":[{"given":"Gunjan","family":"Siddharth","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ananya","family":"Ambekar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naveenkumar","family":"Jayakumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,26]]},"reference":[{"key":"1901_CR1","unstructured":"World Health Organization. Global tuberculosis report 2024. World Health Organization. 2024. https:\/\/www.who.int\/teams\/global-tuberculosis-programme\/tb-reports\/global-tuberculosis-report-2024."},{"key":"1901_CR2","unstructured":"Dai Z, Liu H, Le QV, Tan M. CoAtNet: Marrying convolution and attention for all data sizes. Adv Neural Inf Process Syst. 2021;34:3965\u201377."},{"key":"1901_CR3","doi-asserted-by":"crossref","unstructured":"Ucan M, Kaya B, Kaya M. Generating medical reports with a novel deep learning architecture. Int J Imag Syst And Technol. 2025;35(2):e70062.","DOI":"10.1002\/ima.70062"},{"key":"1901_CR4","doi-asserted-by":"crossref","unstructured":"Alshmrani GMM, Ni Q, Jiang R, Pervaiz H, Elshennawy NM. A deep learning architecture for multi-class lung diseases classification using chest X-ray (CXR) images. Alexandria Eng J. 2023;64:923\u201335.","DOI":"10.1016\/j.aej.2022.10.053"},{"key":"1901_CR5","doi-asserted-by":"crossref","unstructured":"Nafisah SI, Muhammad G. Tuberculosis detection in chest radiograph using convolutional neural network architecture and explainable artificial intelligence. Neural Comput Appl. 2024;36(1):111\u201331.","DOI":"10.1007\/s00521-022-07258-6"},{"key":"1901_CR6","doi-asserted-by":"crossref","unstructured":"Sharma V, Nillmani G, K S, Shukla KK. Deep learning models for tuberculosis detection and infected region visualization in chest X-ray images. Intell Med. 2024;4(2):104\u201313.","DOI":"10.1016\/j.imed.2023.06.001"},{"key":"1901_CR7","doi-asserted-by":"crossref","unstructured":"Islam MK, Rahman MM, Ali MS, Mahim SM, Miah MS. Enhancing lung abnormalities detection and classification using a deep convolutional neural network and GRU with explainable AI: a promising approach for accurate diagnosis. Mach Learn Appl. 2023;14:100492.","DOI":"10.1016\/j.mlwa.2023.100492"},{"key":"1901_CR8","doi-asserted-by":"crossref","unstructured":"Tu Z, Talebi H, Zhang H, Yang F, Milanfar P, Bovik A, Li Y. Maxvit: multi-axis vision transformer. European conference on computer vision. Cham: Springer Nature Switzerland; 2022 October (pp. 459\u201379).","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"1901_CR9","doi-asserted-by":"crossref","unstructured":"Vanitha K, Mahesh TR, Kumar VV, Guluwadi S. Enhanced tuberculosis detection using vision transformers and explainable AI with a grad-CAM approach on chest X-rays. BMC Med Imag. 2025;25(1):96.","DOI":"10.1186\/s12880-025-01630-3"},{"key":"1901_CR10","doi-asserted-by":"crossref","unstructured":"Islam MK, Rahman MM, Ali MS, Mahim SM, Miah MS. Enhancing lung abnormalities diagnosis using hybrid DCNN-ViT-GRU model with explainable AI: a deep learning approach. Image Vision Comput. 2024;142:104918.","DOI":"10.1016\/j.imavis.2024.104918"},{"key":"1901_CR11","unstructured":"Singh S. Computer-aided diagnosis of thoracic diseases in chest X-rays using hybrid cnn-transformer architecture. 2024. arXiv preprint arXiv: 2404.11843."},{"issue":"24","key":"1901_CR12","doi-asserted-by":"publisher","first-page":"14775","DOI":"10.1007\/s00521-024-09884-8","volume":"36","author":"M Balamurugan","year":"2024","unstructured":"Balamurugan M, Balamurugan R. An efficient deep neural network model for tuberculosis detection using chest X-ray images. Neural Comput Appl. 2024;36(24):14775\u201396.","journal-title":"Neural Comput Appl"},{"key":"1901_CR13","doi-asserted-by":"crossref","unstructured":"Ashraf SN, Mamun MA, Abdullah HM, Alam MGR. SynthEnsemble: a fusion of CNN, vision transformer, and hybrid models for multi-label chest X-ray classification. 2023 26th International Conference on Computer and Information Technology (ICCIT). IEEE; 2023 December (pp. 1\u20136).","DOI":"10.1109\/ICCIT60459.2023.10441433"},{"key":"1901_CR14","doi-asserted-by":"crossref","unstructured":"You S, Qin Y, Yan L, Zhang H, Zhu J, Yu S, Toe TT. An improved method for pneumonia image classification based on coatnet. 2024 5th International Conference on Computer Engineering and Application (ICCEA). IEEE; 2024 April (pp. 1052\u201356).","DOI":"10.1109\/ICCEA62105.2024.10603452"},{"key":"1901_CR15","doi-asserted-by":"crossref","unstructured":"Ahmed ST, Barua S, Fahim-Ul-Islam M, Chakrabarty A. CoAtNet-lite: advancing mammogram Mass detection through lightweight CNN-Transformer fusion with attention mapping. 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT). IEEE; 2024 May (pp. 143\u201348).","DOI":"10.1109\/ICEEICT62016.2024.10534420"},{"key":"1901_CR16","doi-asserted-by":"crossref","unstructured":"Pontikos N, Woof WA, Lin S, Ghoshal B, Mendes BS, Veturi A, Michaelides M. Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene. Nat Mach Intell. 2025;1\u201312.","DOI":"10.1038\/s42256-025-01040-8"},{"issue":"23","key":"1901_CR17","doi-asserted-by":"publisher","first-page":"2754","DOI":"10.3390\/diagnostics14232754","volume":"14","author":"Y Hadhoud","year":"2024","unstructured":"Hadhoud Y, Mekhaznia T, Bennour A, Amroune M, Kurdi NA, Aborujilah AH, Al-Sarem M. From binary to multi-class classification: A two-step hybrid CNN-ViT Model for chest disease classification based on X-Ray images. Diagnostics. 2024;14(23):2754.","journal-title":"Diagnostics"},{"issue":"1","key":"1901_CR18","doi-asserted-by":"publisher","first-page":"6650","DOI":"10.1038\/s41598-025-90607-x","volume":"15","author":"X Fu","year":"2025","unstructured":"Fu X, Lin R, Du W, Tavares A, Liang Y. Explainable hybrid transformer for multi-classification of lung disease using chest X-rays. Sci Rep. 2025;15(1):6650.","journal-title":"Sci Rep"},{"issue":"4","key":"1901_CR19","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1007\/s42979-022-01655-3","volume":"4","author":"S Agrawal","year":"2023","unstructured":"Agrawal S, Honnakasturi V, Nara M, Patil N. Utilizing deep learning models and transfer learning for COVID-19 detection from X-ray images. SN Comput Sci. 2023;4(4):326.","journal-title":"SN Comput Sci"},{"key":"1901_CR20","unstructured":"Indian council of medical research (ICMR)-National institute for research in tuberculosis (NIRT). 2019-2021). IN-CXR: an open dataset of Chest Radiography. https:\/\/www.nirt.res.in\/html\/xray.html"},{"key":"1901_CR21","unstructured":"Indian council of medical research (ICMR)-National institute for research in tuberculosis (NIRT). Natl TB Preval Survey In India 2019-2021. Summary Report. Ministry Of Health And Fam Welf, Government of India. 2021. https:\/\/www.nirt.res.in\/pdf\/books\/National%20TB%20Prevalence%20Survey-2019-2021-Summary%20Report.pdf."},{"key":"1901_CR22","unstructured":"World Health Organization. National TB prevalence surveys. Global tuberculosis report 2022. 2022, 24. https:\/\/www.who.int\/teams\/global-programme-on-tuberculosis-and-lung-health\/tb-reports\/global-tuberculosis-report-2022\/tb-disease-burden\/2.4-tb-prevalence-surveys."},{"key":"1901_CR23","doi-asserted-by":"crossref","unstructured":"Chauhan A, Parmar M, Dash GC, Solanki H, Chauhan S, Sharma J, Pati S. The prevalence of tuberculosis infection in India: a systematic review and meta-analysis. Indian J Med Res 157(2 Amp;3). 2023;135\u201351.","DOI":"10.4103\/ijmr.ijmr_382_23"},{"key":"1901_CR24","doi-asserted-by":"crossref","unstructured":"Giridharan P, Selvaraju S, Rao R, Rade K, Thiruvengadam K, Asthana S, Bhargava B. Recurrence of pulmonary tuberculosis in India: findings from the 2019\u20132021 nationwide community-based TB prevalence survey. PLoS One. 2023;18(12):e0294254.","DOI":"10.1371\/journal.pone.0294254"},{"key":"1901_CR25","doi-asserted-by":"crossref","unstructured":"Shah H, Patel J, Rai S, Sen A. Advancing tuberculosis elimination in India: a qualitative review of current strategies and areas for improvement in tuberculosis preventive treatment. IJID Reg. 2025;14:100556.","DOI":"10.1016\/j.ijregi.2024.100556"},{"key":"1901_CR26","doi-asserted-by":"crossref","unstructured":"Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. Mobilenetv2: Inverted residuals and linear bottlenecks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018 (pp. 4510\u201320).","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1901_CR27","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016 (pp. 770\u201378.","DOI":"10.1109\/CVPR.2016.90"},{"key":"1901_CR28","unstructured":"Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. International conference on machine learning. PMLR; 2019 May (pp. 6105\u201314)."},{"key":"1901_CR29","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Houlsby N. An image is worth 16x16. 2020 words: transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929."}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01901-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-025-01901-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-025-01901-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T10:15:22Z","timestamp":1758881722000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedimaging.biomedcentral.com\/articles\/10.1186\/s12880-025-01901-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,26]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1901"],"URL":"https:\/\/doi.org\/10.1186\/s12880-025-01901-z","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,26]]},"assertion":[{"value":"2 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study is a secondary analysis of the publicly available IN-CXR dataset, which was collected by the Indian Council of Medical Research (ICMR)-National Institute for Research in Tuberculosis (NIRT). The original data collection was conducted in accordance with the Declaration of Helsinki. All data was fully anonymized before we accessed it, and therefore, no new ethics approval or consent to participate was required for this study.\u201d.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The IN-CXR dataset used in this study is fully anonymized and publicly available. Therefore, individual consent for publication was not required.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"379"}}