Email this article Resource-Efficient Tuberculosis Screening Via Deep Cnns And Machine Learning
Abstract
The low-resource settings is one of the areas where tuberculosis is one of the most critical public health issues, it tends to cause more issues when there is a lack of diagnosis. The current project demonstrates the use of a hybrid model integrating deep convolutional neural networks (CNNs) and additional Machine Learning algorithms to detect Tuberculosis from radiographs. Along with InceptionResNetV2, Xception, and DenseNet201, we perform ensemble learning on three pretrained CNNs to classificate ML models like SVM, KNN, and Bagging classifiers, on the extracted and feature volunteered images. For accurate and low-relouse prognosis, our proposed system is trained on COVID and TB chest X-ray datasets, allowing it to differentiate between TB, COVID-19, and normal cases. This new testing methodology was able to achieve a whooping 98% in accuracy which goes to show how useful it could be for diagnosing TB in areas where medical professionals are not available. The new system demonstrates it’s potential for quick and reliable TB screening.
Keywords
References
(2020). Global Tuberculosis Report 2020. Accessed: May 10, 2021. [Online]. Available: http://apps.who.int/bookorders
L. M. Parsons, Á. Somoskövi, C. Gutierrez, E. Lee, C. N. Paramasivan, A. L. Abimiku, S. Spector, G. Roscigno, and J. Nkengasong, ‘‘Diagnostic standards and classification of tuberculosis in adults and children,’’ Amer. J. Respiratory Crit. Care Med., vol. 161, no. 4, pp. 1376–1395, 2000, doi: 10.1164/ajrccm.161.4.16141.
Country Profiles for 30 high tb burden countries 20 High TB Burden Countries Based on Absolute Number of Incident Cases 10 High TB Burden Countries Based on Severity of Disease Burden (Incidence per Capita). Accessed: May 10, 2021. [Online]. Available: https://www.who.int/tb/data
L. M. Parsons, Á. Somoskövi, C. Gutierrez, E. Lee, C. N. Paramasivan, A. Abimiku, S. Spector, G. Roscigno, and J. Nkengasong, ‘‘Laboratory diagnosis of tuberculosis in resource-poor countries: Challenges and opportunities,’’ Clin. Microbiol. Rev., vol. 24, no. 2, pp. 314–350, 2011, doi: 10.1128/Cmr.00059-10.
M. Roy and S. Ellis, ‘‘Radiological diagnosis and follow-up of pulmonary tuberculosis,’’ Postgraduate Med. J., vol. 86, no. 1021, pp. 663–674, Nov. 2010, doi: 10.1136/pgmj.2009.084418.
A. H. van’t Hoog, H. K. Meme, H. van Deutekom, A. M. Mithika, C. Olunga, F. Onyino, M. W. Borgdorff, ‘‘High sensitivity of chest radiograph reading by clinical officers in a tuberculosis prevalence survey,’’ Int. J. Tuberculosis Lung Disease, vol. 15, no. 10, pp. 1308–1314, 2011, doi: 10.5588/ijtld.11.0004.
R. Hooda, A. Mittal, and S. Sofat, ‘‘Tuberculosis detection from chest radiographs: A comprehensive survey on computer-aided diagnosis techniques,’’ Current Med. Imag., vol. 14, no. 4, pp. 506–520, 2017, doi: 10.2174/1573405613666171115154119.
Coronavirus Disease (COVID-19): Tuberculosis. Accessed: May 10, 2021. [Online]. Available: https://www.who.int/news-room/q-adetail/coronavirus-disease-covid-19-tuberculosis.
P. Glaziou, ‘‘Predicted impact of the COVID-19 pandemic on global tuberculosis deaths in 2020,’’ MedRxiv, Oct. 2021, doi: 10.1101/2020.04.28.20079582.
Dashboard: Nikshay Reports. Accessed: May 12, 2021. [Online]. Available: https://reports.nikshay.in/Reports/TBNotification
A. S. Becker and C. Blüthgen, ‘‘Detection of tuberculosis patterns in digital photographs of chest X-ray images using deep learning: Feasibility study,’’ Int. J. Tuberculosis Lung Disease, vol. 22, no. 3, pp. 328–335, 2018.
P. Lakhani and B. Sundaram, ‘‘Deep learning at chest radiography: Automated classification of pulmonary tuberculosis by using convolutional neural networks,’’ Radiology, vol. 284, no. 2, pp. 574–582, 2017. [Online]. Available: https://doi.org/10.1148/radiol.2017162326
Y. Cao, C. Liu, B. Liu, M. J. Brunette, N. Zhang, T. Sun, P. Zhang, J. Peinado, E. S. Garavito, L. L. Garcia, and W. H. Curioso, ‘‘Improving tuberculosis diagnostics using deep learning and mobile health technologies among resource-poor and marginalized communities,’’ in Proc. IEEE 1st Int. Conf. Connected Health, Appl., Syst. Eng. Technol. (CHASE). Washington, DC, USA: IEEE, Jun. 2016, pp. 274–281, doi: 10.1109/CHASE.2016.18.
R. Singh, M. K. Kalra, C. Nitiwarangkul, J. A. Patti, F. Homayounieh, A. Padole, P. Rao, P. Putha, V. V. Muse, A. Sharma, and S. R. Digumarthy, ‘‘Deep learning in chest radiography: Detection of findings and presence of change,’’ PLoS ONE, vol. 13, no. 10, Oct. 2018, Art. no. e0204155, doi: 10.1371/journal.pone.0204155.
O. Yadav, K. Passi, and C. K. Jain, ‘‘Using deep learning to classify X-ray images of potential tuberculosis patients,’’ in Proc. IEEE Int. Conf. Bioinf. Biomed. (BIBM), Dec. 2018, pp. 2368–2375.
C. Liu, Y. Cao, M. Alcantara, B. Liu, M. Brunette, J. Peinado, and W. Curioso, ‘‘TX-CNN: Detecting tuberculosis in chest X-ray images using convolutional neural network,’’ in Proc. IEEE Int. Conf. Image Process. (ICIP), Sep. 2017, pp. 2314–2318.
T. Karnkawinpong and Y. Limpiyakorn, ‘‘Chest X-ray analysis of tuberculosis by convolutional neural networks with affine transforms,’’ in Proc. 2nd Int. Conf. Comput. Sci. Artif. Intell., 2018, pp. 90–93.
S. Sathitratanacheewin, P. Sunanta, and K. Pongpirul, ‘‘Deep learning for automated classification of tuberculosis-related chest X-ray: Dataset distribution shift limits diagnostic performance generalizability,’’ Heliyon, vol. 6, no. 8, Aug. 2020, Art. no. e04614.
S. Hwang, H. E. Kim, J. Jeong, S. Hwang, and H.-J. Kim, ‘‘A novel approach for tuberculosis screening based on deep convolutional neural networks,’’ Proc. SPIE, vol. 9785, Mar. 2016, Art. no. 97852W, doi: 10.1117/12.2216198.
R. Mehrotra, M. A. Ansari, R. Agrawal, and R. S. Anand, ‘‘A transfer learning approach for AI-based classification of brain tumors,’’ Mach. Learn. Appl., vol. 2, Dec. 2020, Art. no. 100003, doi: 10.1016/j.mlwa.2020.100003.
Refbacks
- There are currently no refbacks.
Copyright © 2013, All rights reserved.| ijseat.com
International Journal of Science Engineering and Advance Technology is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJSEat , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.
Â