Computer-Aided Tuberculosis Detection from Chest X-Ray Images with Convolutional Neural Networks

• Lucas Gabriel Coimbra Evalgelista UEA
• Elloá B. Guedes UEA

DOI: https://doi.org/10.5753/eniac.2018.4444

Resumo

Diagnosing Tuberculosis is crucial for proper treatment since it is one of the top 10 causes of deaths worldwide. Considering a computer-aided approach based on intelligent pattern recognition on chest X-ray with Convolutional Neural Networks, this work presents the proposition, training and test results of 9 different architectures to address this task as well as two ensembles. The highest performance verified reaches accuracy of 88.76%, surpassing human experts on similar data as previously reported by literature. The experimental data used comes from public medical datasets and comprise real-world examples from patients with different ages and physical characteristics, what favours reproducibility and application in practical scenarios.

Referências

Agah, A. (2013). Medical Applications of Artificial Intelligence. CRC Press, United States.

Brazilian Ministry of Health (2016a). Brasil Livre da Tuberculose. Available at http://portalarquivos.saude.gov.br/images/pdf/2017/ fevereiro/24/Plano-Nacional-Tuberculose.pdf.

Brazilian Ministry of Health (2016b). Panorama da Tuberculose no Brasil. Available at http://bvsms.saude.gov.br/bvs/publicacoes/panorama%20tuberculose%20brasil_2014.pdf.

Brink, H., Richards, J. W., and Fetherolf, M. (2017). Real-World Machine Learning. Manning Publications, United States.

Chollet, F. (2017). Deep Learning with Python. Manning Publications, Shelter Island, New York, 1 edition.

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. Imianvan, A. A. and Obi, J. (2011). Fuzzy cluster means expert system for the diagnosis of tuberculosis. Global Journal of Computer Science & Technology, 11(6):41–48.

Jaeger, S., Candemir, S., Antani, S., Yi-Xiang, Wang, J., Lu, P.-X., , and Thoma, G. (2014a). Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. Quantitative Imaging in Medicine and Surgery, 6(4):475–477.

Jaeger, S., Karargyris, A., Candemir, S., Folio, L., Siegelman, J., Callaghan, F., Xue, Z., Palaniappan, K., Singh, R. K., and Antani, S. (2014b). Automatic tuberculosis screening using chest radiographs. IEEE Transactions on Medical Imaging, 33(2):233–245.

Jaeger, S., Karargyris, A., Candemir, S., Siegelman, J., Folio, L., Antani, S., and Thoma, G. (2013). Automatic screening for tuberculosis in chest radiographs: a survey. Quantitative Imaging in Medicine and Surgery, 3(2):89–99.

Jamison, D. T., Breman, J. G., Measham, A. R., Alleyne, G., Claeson, M., Evans, D. B., Jha, P., Mills, A., and Musgrove, P. (2006). Disease Control Priorities in Developing Countries. World Bank Publications, 2th edition.

Keras (2018). Keras: The python deep learning library. Available at http://keras.io/. Accessed in August 14, 2018.

Khan, S., Rahmani, H., Shah, S. A. A., and Bennamoun, M. (2018). A Guide to Convolutional Neural Networks for Computer Vision. Morgan and Claypool.

Kubat, M. (2015). An Introduction to Machine Learning. Springer, United States.

Lakhani, P. and Sundaram, B. (2017). Deep learning at chest radiography: Automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology, 284(2):1–9.

Liao, S.-H. (2005). Expert system methodologies and applications — a decade review from 1995 to 2004. Expert systems with applications, 28(1):93–103.

McBee, M. P., Awan, O. A., Colucci, A. T., Ghobadi, C. W., Kadom, N., Kansagra, A. P., Tridandapani, S., and Auffermann,W. F. (2018). Deep learning in radiology. Academic Radiology, March 30rd, 2018:1–9. In Press.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.

Python (2018). Python programming language. Available at http://www.python.org. Accessed in August 14, 2018.

Ravì, D., Wong, C., Deligianni, F., Berthelot, M., Andreu-Perez, J., Lo, B., and Yang, G. Z. (2017). Deep learning for health informatics. IEEE Journal of Biomedical and Health Informatics, 21(1):4–21.

Shiraishi, J., Katsuragawa, S., Ikezoe, J., Matsumoto, T., Kobayashi, T., Komatsu, K.,

Matsui, M., Fujita, H., Kodera, Y., and Doi, K. (2000). Development of a digital image database for chest radiographs with and without a lung nodule: Receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. American Journal of Roentgenology, (174):71–74.

United Nations (2015). Sustainable development goals. Available at https://www.un.org/sustainabledevelopment/sustainable-development-goals/.

WHO (2016). Global Tuberculosis Report 2016. Available at http://www.who.int/tb/publications/global_report/en/.

Yasaka, K., Akai, H., Kunimatsu, A., Kiryu, S., and Abe, O. (2018). Deep learning withconvolutional neural network in radiology. Japanese Journal of Radiology, 26(257):1–16.

Zhou, Z.-H. (2012). Ensemble Methods – Foundations and Algorithms. CRC Press, United States.