Abstract
Pneumonia is one of the most chronic diseases, and therefore, its timely diagnosis is of utmost importance. Traditionally, clinical decisions have been considered as a gold standard for diagnosis, but it is not a practical option in all scenarios. Therefore, several methods have been explored to make the process of diagnosis faster, efficient and as accurate as clinical decisions. In this paper, we have described and proposed a Convolutional Neural Network (CNN) based deep learning technique for the classification of chest X-ray images for the diagnosis of Pneumonia. The proposed model is trained on 4099 images and tested on 1757 images resulting in an accuracy of 96.18%. The evaluation and training are conducted on ‘Labeled Optical Coherence Tomography (OCT) and Chest X-Ray Images for Classification’ dataset which is one of the largest labeled datasets which is publicly available. Also, a comparison of the proposed model with various other popular models is discussed. The results indicate that our model despite having simpler architecture and without any pre-training outperforms many of the popular models on several different performance parameters.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ruuskanen, O., Lahti, E., Jennings, L.C., Murdoch, D.R.: Viral pneumonia. Lancet (2011)
Islam, S.R., Maity, S.P., Ray, A.K., Mandal, M.: Automatic detection of pneumonia on compressed sensing images using deep learning. In: IEEE Canadian Conference of Electrical and Computer Engineering (CCECE) (2019)
Kaiming, H., Xiangyu, Z., Shaoqing, R., Jian, S.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Esteva, A., Kuprel, B., Roberto, A.N., Ko, J., Susan, M.S., Helen, M.B., Thrun, S.: Dermatologist-level classification of skin cancer. Nature (2017)
El-Solh, A.A., Hsiao, C.B., Goodnough, S., Serghani, J., Grant, B.J.: Predicting active pulmonary tuberculosis using an artificial neural network (1999)
Er, O., Yumusak, N., Temurtas, F.: Chest diseases diagnosis using artificial neural networks. Expert System with Application 37(12), 7648–7655 (2010)
Rajpurkar, P., et al.: CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning, arXiv (2017)
Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: IEEE - Computer Vision and Pattern Recognition (2017)
Xia, Y., Wang, H.: ChestNet: a deep neural network for classification of thoracic diseases on chest radiography. ArXiv (2018)
Kermany, D.S., et al.: Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 72(5), 1122–1131 (2018)
Stephen, O., Sain, M., Maduh, U.J., Jeong, D.-U.: An efficient deep learning approach to Pneumonia classification in healthcare. J. Healthcare Eng. 2019 (2019). Article ID 4180949
Saraiva, A.A., et al.: Classification of images of childhood pneumonia using convolutional neural networks. In: 6th International Conference on Bioimaging (2019)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning (2015)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Kermany, D., Zhang, K., Goldbaum, M.: Labeled Optical Coherence Tomography (OCT) and chest X-Ray images for classification. Mendeley Data (2018)
Zhang, Z., Sabuncu, M.R.: Generalized cross entropy loss for training deep neural networks with noisy labels. In: NIPS 2018 Proceedings of the 32nd International Conference on Neural Information Processing Systems (2018)
Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)
Zhu, W., Zeng, N., Wang, N.: Sensitivity, specificity, accuracy, associated confidence interval and ROC analysis with practical SAS implementations. Health Care and Life Science 19, 67 (2010)
Saito, T., Rehmsmeier, M.: The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE 10(3), e0118432 (2015)
Brzezinski, D., Stefanowski, J.: Prequential AUC: properties of the area under the ROC curve for data streams with concept drift. Knowledge and Information Systems, 52(2), 531–562 (2017)
Junge, M.R.J., Dettori, J.R.: ROC Solid: Receiver Operator Characteristic (ROC) curves as a foundation for better diagnostic tests. Global Spine J. 8(4), 424–429 (2018)
Acknowledgment
The research work was supported by the Electronics Engineering Department, S. V. National Institute of Technology, Surat, India. We appreciate the effort kept to collect and share the labeled Chest X-ray image dataset [15]. We would also like to appreciate Apurva Randeria’s (SVNIT, Surat) effort for developing an interpretable graphical model for the proposed CNN based classifier.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Bhatt, R., Yadav, S., Sarvaiya, J.N. (2020). Convolutional Neural Network Based Chest X-Ray Image Classification for Pneumonia Diagnosis. In: Gupta, S., Sarvaiya, J. (eds) Emerging Technology Trends in Electronics, Communication and Networking. ET2ECN 2020. Communications in Computer and Information Science, vol 1214. Springer, Singapore. https://doi.org/10.1007/978-981-15-7219-7_22
Download citation
DOI: https://doi.org/10.1007/978-981-15-7219-7_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-7218-0
Online ISBN: 978-981-15-7219-7
eBook Packages: Computer ScienceComputer Science (R0)