An Application on Chest X-Ray Images for the Detection of Tuberculosis Disease by Employing Deep Convolutional Neural Networks

Abstract

Tuberculosis is the second infectious disease causing death after COVID-19. Diagnosing it is an easy and cheap via chest radiographs. However, some countries lack medical personnel and equipment for tuberculosis detection on chest radiographs. Computer-aided diagnosis and computer-aided detection systems utilizing deep learning can be employed to identify tuberculosis on medical images. Although there are some studies, they are insufficient for unbiased systems because these systems require the datasets having different features. The aim of this study is to evaluate the performance of pretrained networks for a classification application on chest X-ray images by utilizing the dataset from the Hospital in Turkey and Montgomery Count Dataset. The predictive models were implemented with the pre-trained DCNNs such as ResNet-50, Xception, and GoogLeNet. An Xception model provides the best performance.

Keywords

• tuberculosis
• deep convolutional neural networks
• transfer learning
• classification

References

1. [1] World Health Organization, «Global tuberculosis report,» World Health Organization, Geneva, 2020.
2. [2] World Health Organization, «Global tuberculosis report,» World Health Organization, Geneva, 2022.
3. [3] T.C. Sağlık Bakanlığı, «Ulusal tüberküloz kontrol programı,» T.C. Sağlık Bakanlığı Yayın No: 1129, Ankara, 2022.
4. [4] T.C. Sağlık Bakanlığı Halk Sağlığı Genel Müdürlüğü, «Tüberküloz tanı ve tedavi rehberi,» T.C. Sağlık Bakanlığı Halk Sağlığı Genel Müdürlüğü, Ankara, 2019.
5. [5] E. J. Hwang, S. Park, K.-N. Jin, J. I. Kim, S. Y. Choi, J. H. Lee, J. M. Go, J. Aum, J.-J. Yim, J.-J. Yim ve C. M. Park, «Development and validation of a deep learning–based automatic detection algorithm for active pulmonary tuberculosis on chest radiographs,» Clinical Infectious Diseases, cilt 65, no. 5, pp. 739-747, 2019.
6. [6] World Health Organization, «Chest Radiography in Tuberculosis Detection: Summary of current WHO recommendations and guidance on programmatic approaches,» World Health Organization, Geneva, 2016.
7. [7] R. A. Castellino, «Computer aided detection (CAD): an overview,» Cancer Imaging, pp. 17-19, 23 August 2005.
8. [8] K. Suzuki, «Computer-aided detection of lung cancer,» Image-based computer-assisted radiation theraphy, Singapore, Springer, 2017, pp. 9-40.

9. [9] J. Zhang, X. Yutong, Q. Wu ve Y. Xia, «Medical image classification using synergic deep learning,» Medical image analysis, cilt 54, pp. 10-19, 2019.
10. [10] D. W. v. S. T. I. M. E. Matheny, «Artificial intelligence in health care a report from the national academy of medicine,» JAMA,, cilt 323, no. 6, pp. 509-510, 2020.
11. [11] M. A. Musen, B. Middleton ve R. A. Greenes, «Clinical decision support system,» Biomedical informatics, Cham,, Springer, 2021, pp. 795-840.
12. [12] K. C. Laudon ve J. P. Laudon, Management information systems: managing the digital firm, London: Pearson, 2020.
13. [13] R. Sharda, D. Dursun ve E. Turban, Analytics, data science, & artificial intelligence: systems for decision support, Hoboken: Pearson, 2020.
14. [14] E. Alpaydın, «Introduction,» Introduction to machine learning, Cambrige, MIT Press, 2010, pp. 1-19.
15. [15] A. M. Antoniadi, Y. Du, Y. Guendouz, L. Wei, C. Mazo, B. A. Becker ve C. Mooney, «Current challenges and future opportunities for XAI in machine learning-based clinical decision support systems: a systemeatic review,» Applied Sciences, cilt 11, no. 11, 2021.
16. [16] A. K. Jain, J. Mao ve K. M. Mohiuddin, «Artificial neural networks: a tutorial,» Computer, cilt 29, no. 3, pp. 31-44, 1996.
17. [17] R. Yamashita, M. Nishio, R. K. G. Do ve K. Togashi, «Convolutional neural networks: an overview and application in radiology,» Insights into imaging, cilt 9, no. 4, pp. 611-629, 2018.
18. [18] S. Kulkarni ve S. Jha, «Artificial intelligence, radiology, and tuberculosis: a review,» Academic radiology, cilt 27, no. 1, pp. 71-75, 2020.
19. [19] R. H. Abiyev ve M. K. S. Ma'aitah, «Deep convolutional neural networks for chest diseases detection,» Journal of healthcare engineering, 2018.
20. [20] M. Mamalakis, A. J. Swift, B. Vorselaars, S. Ray, S. Weeks, W. Ding, R. H. Clayton, L. Mackenzie ve A. Banerjee, «DenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and tuberculosis from X-rays,» Computerized Medical Imaging and Graphics, no. 102008, p. 94, 2021.
21. [21] E. Ölmez, O. Er ve A. Hızıroğlu, «Deep learning in biomedical applications: detection of lung disease with convolutional neural networks,» Deep learning in biomedical and health informatics, Boca Raton, CRC Press, 2021, pp. 97-115.
22. [22] P. Lakhani ve B. Sundaram, «Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks,» Radiology, cilt 284, no. 2, pp. 574-582, 2017.
23. [23] B. K. Karaca, S. Güney, B. Dengiz ve M. Ağıldere, «Comparative Study for Tuberculosis Detection by Using Deep Learning,» 2021 44th International Conference on Telecommunications and Signal Processing (TSP), Brno, 2021.
24. [24] B. Oltu, S. Güney, B. Dengiz ve M. Ağıldere, «Automated tuberculosis detection using pre-trained and SVM,» 2021 44th International Conference on Telecommunications and Signal Processing (TSP), Brno, 2021.
25. [25] Y. Cao, C. Liu, M. J. Brunette, N. Zhang, T. Sun, P. Zhang, J. Peinado, E. S. Garavito, L. L. Garcia ve W. H. Curioso, «Improving tuberculosis diagnostics using deep learning and mobile health technologies among resource-poor and marginalized communities,» 2016 IEEE first international conference on connected health: applications, systems and engineering technologies (CHASE), Washington, 2016.
26. [26] S. Stirenko, Y. Kochura, O. Alienin, O. Rokovyi, Y. Gordienko, P. Gang ve W. Zeng, «Chest X-ray analysis of tuberculosis by deep learning with segmentation and augmentation,» 2018 IEEE 38th International Conference on Electronics and Nanotechnology (ELNANO), Kyiv, 2019.
27. [27] T. Rahman, A. Khandakar, M. Abdulkadir, K. R. Islam ve K. F. Islam, «Reliable tuberculosis detection using chest X-ray with deep learning, segmentation and visualization,» IEEE Access, cilt 8, pp. 191586-191601, 2020.
28. [28] S.-J. Heo, Y. Kim, S. Yun, S.-S. Lim, J. Kim, C.-M. Nam, E.-C. Park, I. Jung ve J.-H. Yoon, «Deep learning algorithms with demographic information help to detect tuberculosis in chest radiographs in annual workers’ health examination data,» International journal of environmental research and public health, cilt 16, no. 2, p. 250, 2019.
29. [29] T. M. Navamani, «Efficient deep learning approaches for health informatics,» Deep learning and parallel computing environment for bioengineering systems, St. Louis, Academic Press, 2019, pp. 123-137.
30. [30] M. J. Willemink, W. A. Koszek, C. Hardell, J. Wu, D. Fleischmann, H. Harvey, L. R. Folio, R. M. Summers, D. L. Rubin ve M. P. Lungren, «Preparing medical imaging data for machine learning,» Radiology, cilt 295, no. 1, pp. 4-15, 2020.