{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:27:28Z","timestamp":1792790848075,"version":"4.5.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T00:00:00Z","timestamp":1673913600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T00:00:00Z","timestamp":1673913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Jawaharlal Institute of Post Graduate Medical Education and Research","award":["JIP\/Res\/Intramural\/Phs 2\/2019-20"],"award-info":[{"award-number":["JIP\/Res\/Intramural\/Phs 2\/2019-20"]}],"id":[{"id":"https:\/\/ror.org\/02fq2px14","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>Chest X-rays are the most economically viable diagnostic imaging test for active pulmonary tuberculosis screening despite the high sensitivity and low specificity when interpreted by clinicians or radiologists. Computer aided detection (CAD) algorithms, especially convolution based deep learning architecture, have been proposed to facilitate the automation of radiography imaging modalities. Deep learning algorithms have found success in classifying various abnormalities in lung using chest X-ray. We fine-tuned, validated and tested EfficientNetB4 architecture and utilized the transfer learning methodology for multilabel approach to detect lung zone wise and image wise manifestations of active pulmonary tuberculosis using chest X-ray. We used Area Under Receiver Operating Characteristic (AUC), sensitivity and specificity along with 95% confidence interval as model evaluation metrics. We also utilized the visualisation capabilities of convolutional neural networks (CNN), Gradient-weighted Class Activation Mapping (Grad-CAM) as post-hoc attention method to investigate the model and visualisation of Tuberculosis abnormalities and discuss them from radiological perspectives. EfficientNetB4 trained network achieved remarkable AUC, sensitivity and specificity of various pulmonary tuberculosis manifestations in intramural test set and external test set from different geographical region. The grad-CAM visualisations and their ability to localize the abnormalities can aid the clinicians at primary care settings for screening and triaging of tuberculosis where resources are constrained or overburdened.<\/jats:p>","DOI":"10.1038\/s41598-023-28079-0","type":"journal-article","created":{"date-parts":[[2023,1,17]],"date-time":"2023-01-17T06:05:23Z","timestamp":1673935523000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":53,"title":["Deep learning classification of active tuberculosis lung zones wise manifestations using chest X-rays: a multi label approach"],"prefix":"10.1038","volume":"13","author":[{"given":"James","family":"Devasia","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hridayanand","family":"Goswami","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subitha","family":"Lakshminarayanan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manju","family":"Rajaram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subathra","family":"Adithan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,17]]},"reference":[{"key":"28079_CR1","unstructured":"WHO, G. Global tuberculosis report 2022. Glob Tuberc. Rep. 2022 (2022)."},{"key":"28079_CR2","doi-asserted-by":"publisher","first-page":"497","DOI":"10.2214\/ajr.146.3.497","volume":"146","author":"J Woodring","year":"1986","unstructured":"Woodring, J. et al. Update: The radiographic features of pulmonary tuberculosis. Am. J. Roentgenol. 146, 497\u2013506 (1986).","journal-title":"Am. J. Roentgenol."},{"key":"28079_CR3","first-page":"101","volume":"45","author":"J Krysl","year":"1994","unstructured":"Krysl, J., Korzeniewska-Kosela, M., M\u00fcller, N. & FitzGerald, J. Radiologic features of pulmonary tuberculosis: An assessment of 188 cases. Can. Assoc. Radiol. J. J. Assoc. Can. Radiol. 45, 101\u2013107 (1994).","journal-title":"Can. Assoc. Radiol. J. J. Assoc. Can. Radiol."},{"key":"28079_CR4","doi-asserted-by":"crossref","unstructured":"World Health Organization. WHO Consolidated Guidelines on Tuberculosis: Module 2: Screening: Systematic Screening for Tuberculosis Disease. (WHO, 2021).","DOI":"10.30978\/TB2021-2-86"},{"key":"28079_CR5","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.5588\/ijtld.11.0004","volume":"15","author":"A Van\u2019t Hoog","year":"2011","unstructured":"Van\u2019t Hoog, A. et al. High sensitivity of chest radiograph reading by clinical officers in a tuberculosis prevalence survey. Int. J. Tuberc. Lung Dis. 15, 1308\u20131314 (2011).","journal-title":"Int. J. Tuberc. Lung Dis."},{"key":"28079_CR6","doi-asserted-by":"publisher","first-page":"25265","DOI":"10.1038\/srep25265","volume":"6","author":"J Melendez","year":"2016","unstructured":"Melendez, J. et al. An automated tuberculosis screening strategy combining X-ray-based computer-aided detection and clinical information. Sci. Rep. 6, 25265 (2016).","journal-title":"Sci. Rep."},{"key":"28079_CR7","doi-asserted-by":"publisher","first-page":"6268","DOI":"10.1038\/s41598-019-42557-4","volume":"9","author":"F Pasa","year":"2019","unstructured":"Pasa, F., Golkov, V., Pfeiffer, F., Cremers, D. & Pfeiffer, D. Efficient deep network architectures for fast chest X-ray tuberculosis screening and visualization. Sci. Rep. 9, 6268 (2019).","journal-title":"Sci. Rep."},{"key":"28079_CR8","doi-asserted-by":"publisher","first-page":"1168","DOI":"10.1109\/TMI.2017.2775636","volume":"37","author":"KC Santosh","year":"2018","unstructured":"Santosh, K. C. & Antani, S. Automated chest X-ray screening: Can lung region symmetry help detect pulmonary abnormalities?. IEEE Trans. Med. Imaging 37, 1168\u20131177 (2018).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"28079_CR9","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1038\/s41746-020-0273-z","volume":"3","author":"Y-X Tang","year":"2020","unstructured":"Tang, Y.-X. et al. Automated abnormality classification of chest radiographs using deep convolutional neural networks. Npj Digit. Med. 3, 70 (2020).","journal-title":"Npj Digit. Med."},{"key":"28079_CR10","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1109\/TMI.2013.2284099","volume":"33","author":"S Jaeger","year":"2014","unstructured":"Jaeger, S. et al. Automatic tuberculosis screening using chest radiographs. IEEE Trans. Med. Imaging 33, 233\u2013245 (2014).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"28079_CR11","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/s41746-020-00322-2","volume":"3","author":"P Rajpurkar","year":"2020","unstructured":"Rajpurkar, P. et al. CheXaid: Deep learning assistance for physician diagnosis of tuberculosis using chest X-rays in patients with HIV. Npj Digit. Med. 3, 115 (2020).","journal-title":"Npj Digit. Med."},{"key":"28079_CR12","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1007\/s11548-018-1857-9","volume":"13","author":"S Jaeger","year":"2018","unstructured":"Jaeger, S. et al. Detecting drug-resistant tuberculosis in chest radiographs. Int. J. Comput. Assist. Radiol. Surg. 13, 1915\u20131925 (2018).","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"28079_CR13","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1007\/s10916-018-0991-9","volume":"42","author":"S Vajda","year":"2018","unstructured":"Vajda, S. et al. Feature selection for automatic tuberculosis screening in frontal chest radiographs. J. Med. Syst. 42, 146 (2018).","journal-title":"J. Med. Syst."},{"key":"28079_CR14","doi-asserted-by":"publisher","unstructured":"S. Rajaraman et al. A novel stacked generalization of models for improved TB detection in chest radiographs. in 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 718\u2013721. https:\/\/doi.org\/10.1109\/EMBC.2018.8512337 (2018).","DOI":"10.1109\/EMBC.2018.8512337"},{"key":"28079_CR15","doi-asserted-by":"publisher","first-page":"915","DOI":"10.3390\/app11199289","volume":"11","author":"M Hong","year":"2021","unstructured":"Hong, M. et al. Multi-class classification of lung diseases using CNN models. Appl. Sci. 11, 915 (2021).","journal-title":"Appl. Sci."},{"key":"28079_CR16","doi-asserted-by":"publisher","first-page":"915","DOI":"10.3390\/diagnostics12040915","volume":"12","author":"S Kim","year":"2022","unstructured":"Kim, S. et al. Deep learning in multi-class lung diseases\u2019 classification on chest X-ray images. Diagnostics 12, 915 (2022).","journal-title":"Diagnostics"},{"key":"28079_CR17","doi-asserted-by":"publisher","unstructured":"X. Wang et al. ChestX-Ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3462\u20133471. https:\/\/doi.org\/10.1109\/CVPR.2017.369 (2017).","DOI":"10.1109\/CVPR.2017.369"},{"key":"28079_CR18","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1109\/JBHI.2019.2928369","volume":"24","author":"H Wang","year":"2020","unstructured":"Wang, H., Jia, H., Lu, L. & Xia, Y. Thorax-Net: An attention regularized deep neural network for classification of thoracic diseases on chest radiography. IEEE J. Biomed. Health Inform. 24, 475\u2013485 (2020).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"28079_CR19","doi-asserted-by":"crossref","unstructured":"G\u00fcndel, S. et al. Learning to recognize abnormalities in chest X-rays with location-aware dense networks. in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications (eds. Vera-Rodriguez, R., Fierrez, J. & Morales, A.). 757\u2013765 (Springer, 2019).","DOI":"10.1007\/978-3-030-13469-3_88"},{"key":"28079_CR20","unstructured":"Yao, L. et al. Learning to Diagnose from Scratch by Exploiting Dependencies Among Labels. arXiv preprint: arXiv:171010501 (2017)."},{"key":"28079_CR21","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.495","volume":"7","author":"S Albahli","year":"2021","unstructured":"Albahli, S., Rauf, H. T., Algosaibi, A. & Balas, V. E. AI-driven deep CNN approach for multi-label pathology classification using chest X-rays. PeerJ Comput. Sci. 7, e495 (2021).","journal-title":"PeerJ Comput. Sci."},{"key":"28079_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z. et al. Thoracic Disease Identification and Localization with Limited Supervision. 8290\u20138299 (2018).","DOI":"10.1109\/CVPR.2018.00865"},{"key":"28079_CR23","doi-asserted-by":"crossref","unstructured":"Shin, H.-C. et al. Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation. 2497\u20132506 (2016).","DOI":"10.1109\/CVPR.2016.274"},{"key":"28079_CR24","unstructured":"World Health Organization. Definitions and Reporting Framework for Tuberculosis\u20142013 Revision: Updated December 2014 and January 2020. (2013)."},{"key":"28079_CR25","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.5588\/ijtld.10.0734","volume":"15","author":"M Wang","year":"2011","unstructured":"Wang, M. et al. Is the delay in diagnosis of pulmonary tuberculosis related to exposure to fluoroquinolones or any antibiotic?. Int. J. Tuberc. Lung Dis. 15, 1062\u20131068 (2011).","journal-title":"Int. J. Tuberc. Lung Dis."},{"key":"28079_CR26","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.ijid.2013.09.013","volume":"18","author":"RF Grossman","year":"2014","unstructured":"Grossman, R. F., Hsueh, P.-R., Gillespie, S. H. & Blasi, F. Community-acquired pneumonia and tuberculosis: Differential diagnosis and the use of fluoroquinolones. Int. J. Infect. Dis. 18, 14\u201321 (2014).","journal-title":"Int. J. Infect. Dis."},{"key":"28079_CR27","unstructured":"Selvaraju, R. R. et al. Grad-CAM: Why Did You Say That? arXiv:1611.07450 (2016)."},{"key":"28079_CR28","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1001\/jama.293.22.2740","volume":"293","author":"E Geng","year":"2005","unstructured":"Geng, E., Kreiswirth, B., Burzynski, J. & Schluger, N. W. Clinical and radiographic correlates of primary and reactivation tuberculosis: A molecular epidemiology study. JAMA 293, 2740\u20132745 (2005).","journal-title":"JAMA"},{"key":"28079_CR29","doi-asserted-by":"publisher","first-page":"753","DOI":"10.2214\/ajr.160.4.8456658","volume":"160","author":"KS Lee","year":"1993","unstructured":"Lee, K. S. et al. Adult-onset pulmonary tuberculosis: Findings on chest radiographs and CT scans. AJR Am. J. Roentgenol. 160, 753\u2013758 (1993).","journal-title":"AJR Am. J. Roentgenol."},{"key":"28079_CR30","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1038\/s41598-019-56589-3","volume":"10","author":"M Nash","year":"2020","unstructured":"Nash, M. et al. Deep learning, computer-aided radiography reading for tuberculosis: A diagnostic accuracy study from a tertiary hospital in India. Sci. Rep. 10, 210 (2020).","journal-title":"Sci. Rep."},{"key":"28079_CR31","doi-asserted-by":"publisher","first-page":"328","DOI":"10.5588\/ijtld.17.0520","volume":"22","author":"A Becker","year":"2018","unstructured":"Becker, A. et al. Detection of tuberculosis patterns in digital photographs of chest X-ray images using deep learning: Feasibility study. Int. J. Tuberc. Lung Dis. 22, 328\u2013335 (2018).","journal-title":"Int. J. Tuberc. Lung Dis."},{"key":"28079_CR32","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.583427","volume":"3","author":"R Guo","year":"2020","unstructured":"Guo, R., Passi, K. & Jain, C. K. Tuberculosis diagnostics and localization in chest X-rays via deep learning models. Front. Artif. Intell. 3, 583427 (2020).","journal-title":"Front. Artif. Intell."},{"issue":"6","key":"28079_CR33","first-page":"455","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. Imaging Med. Surg. 4(6), 455\u2013457 (2014).","journal-title":"Quant. Imaging Med. Surg."},{"key":"28079_CR34","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","volume":"33","author":"JR Landis","year":"1977","unstructured":"Landis, J. R. & Koch, G. G. The measurement of observer agreement for categorical data. Biometrics 33, 159\u2013174 (1977).","journal-title":"Biometrics"},{"key":"28079_CR35","unstructured":"Tan, M. & Le, Q. Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks. 6105\u20136114 (PMLR, 2019)."},{"key":"28079_CR36","doi-asserted-by":"publisher","unstructured":"Reddy, A. S. B. & Juliet, D. S. Transfer learning with ResNet-50 for malaria cell-image classification. in 2019 International Conference on Communication and Signal Processing (ICCSP). 0945\u20130949. https:\/\/doi.org\/10.1109\/ICCSP.2019.8697909 (2019).","DOI":"10.1109\/ICCSP.2019.8697909"},{"key":"28079_CR37","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1148\/radiology.148.3.6878708","volume":"148","author":"JA Hanley","year":"1983","unstructured":"Hanley, J. A. & McNeil, B. J. A method of comparing the areas under receiver operating characteristic curves derived from the same cases. Radiology 148, 839\u2013843 (1983).","journal-title":"Radiology"},{"key":"28079_CR38","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1080\/01621459.1927.10502953","volume":"22","author":"EB Wilson","year":"1927","unstructured":"Wilson, E. B. Probable inference, the law of succession, and statistical inference. J. Am. Stat. Assoc. 22, 209\u2013212 (1927).","journal-title":"J. Am. Stat. Assoc."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-28079-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-28079-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-28079-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,20]],"date-time":"2023-01-20T23:24:07Z","timestamp":1674257047000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-28079-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,17]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["28079"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-28079-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,17]]},"assertion":[{"value":"27 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"887"}}