Machine Learning Based Lung Disease Prediction Using X-Ray Images

This paper described a system that identifies lung diseases in chest X-rays by combining preprocessing and augmentation with two groups of classifiers: SVM and Random Forest on handcrafted features, and fine-tuned VGG16, ResNet50 and DenseNet121 networks. The deep models were clearly better than the classical ones, with [DenseNet121] giving the best results in [accuracy, recall and AUC]. Grad-CAM heatmaps showed that the network concentrated on meaningful lung regions, which makes its output easier to trust. As a decision- support tool, the system can speed up diagnosis and bring screening closer to remote communities. In future work, we intend to test the model on data collected from several hospitals to measure how well it generalises. Other planned directions are multi-label prediction for patients with more than one condition, adding clinical information such as symptoms and history, comparison with Vision Transformers and ensemble methods, and a real-time web or mobile version for clinical use.

[1]   P. Rajpurkar et al., “CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning,” arXiv preprint arXiv:1711.05225, 2017. [2]   X. Wang, Y. Peng, L. Lu, Z. Lu, M. Bagheri, and R. M. Summers, “ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly supervised classification and localization of common thorax diseases,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2097–2106. [3] L. Wang, Z. Q. Lin, and A. Wong, “COVID-Net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images,” Scientific Reports, vol. 10, no. 1, p. 19549, 2020. [4] E. E.-D. Hemdan, M. A. Shouman, and M. E. Karar, “COVIDX-Net: A framework of deep learning classifiers to diagnose COVID-19 in X-ray images,” arXiv preprint arXiv:2003.11055, 2020. [5]   P. Rajpurkar et al., “Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists,” PLOS Medicine, vol. 15, no. 11, p. e1002686, 2018. [6] National Institutes of Health Clinical Center, “NIH Chest X-ray Dataset (ChestX-ray14),” 2017. [Online]. Available: https://nihcc.app.box.com/v/ChestXray-NIHCC [7]   K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Proc. Int. Conf. Learning Representations (ICLR), 2015. [8] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. [9]  G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4700–4708. [10]  R. R. Selvaraju et al., “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” in Proc. IEEE Int. Conf. Computer Vision (ICCV), 2017, pp. 618–626.