CLASSIFICATION PERFORMANCE COMPARISONS OF DEEP LEARNING MODELS IN PNEUMONIA DIAGNOSIS USING CHEST X-RAY IMAGES

Abstract

In recent years, the analysis of medical images using deep learning techniques has become an area of increasing popularity. Advances in this area have been particularly evident after the discovery of deep artificial neural network models and achieving more successful performance results than other traditional models. In this study, the performance comparison of different deep learning models used to efficiently diagnose pneumonia on chest x-ray images was performed. The data set used in the study consists of a total of 5840 chest x-ray images of individuals. In order to classify these data, three different deep learning models are used: Convolutional Neural Network, Convolutional Neural Network with Data Augmentation and Transfer Learning. The images in the data set were classified into two categories as pneumonia and healthy people using these three deep learning models. The performances of these three deep learning models used in classification were compared in terms of loss and accuracy. In the comparison of three different deep learning models with two different performance values, 5216 chest x-ray images in the data set were used to train the deep learning model and the remaining 624 were used to test the model. At the end of the study, the most successful performance result was obtained by convolutional neural network model applied with data augmentation technique. According to the best results of this study, this model was able to accurately predict the class of 93.4% of the test data. 

Keywords

• Deep Learning
• Medical Diagnosis
• Data Augmentation
• Convolutional Neural Network
• Transfer Learning

References

1. Aghdam, H. H. and Heravi, E. J. (2017). Guide to Convolutional Neural Networks, NY: Springer, New York, USA
2. Chest X-Ray Images, https://www.kaggle.com/paultimothymooney/chestxray-pneumonia [Accessed 20 July 2019].
3. Convolution Operation, https://medium.com/@bdhuma/6-basic-things-to-knowabout-convolution-daef5e1bc411 [Accessed 21 July 2019].
4. Data Augmentation, https://developers.google.com/machinelearning/practica/image-classification/preventingoverfitting [Accessed 26 July 2019].
5. Dropout, https://medium.com/@amarbudhiraja/httpsmedium-com-amarbudhiraja-learning-less-to-learnbetter-dropout-in-deep-machine-learning-74334da4bfc5 [Accessed 26 July 2019].
6. Features, https://medium.com/abraia/getting-startedwith-image-recognition-and-convolutional-neuralnetworks-in-5-minutes-28c1dfdd401 [Accessed 29 July 2019].
7. First Model, http://fourier.eng.hmc.edu/e176/lectures/ch10/node8.html [Accessed 27 July 2019].
8. Flattening, https://www.kaggle.com/kanncaa1/convolutional-neuralnetwork-cnn-tutorial/notebook [Accessed 25 July 2019].

9. Fully Connected Layer, http://cs231n.github.io/convolutional-networks/ [Accessed 22 July 2019].
10. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning, MIT press, Massachusetts, USA. Image Pixels, https://ai.stanford.edu/~syyeung/cvweb/tutorial1.html [Accessed 20 July 2019].
11. Indraswari, R., Kurita, T., Arifin, A. Z., Suciati, N. and Astuti, E. R. (2019). “Multi-projection deep learning network for segmentation of 3D medical images.” Pattern Recognition Letters, Vol. 125, pp. 791-797.
12. Kermany, D. K., & Goldbaum, M. (2018). Labeled optical coherence tomography (OCT) and Chest X-Ray images for classification. Mendeley Data, 2.
13. Krizhevsky, A., Sutskever, I. and Hinton, G. E. (2012). “Imagenet classification with deep convolutional neural networks.” Neural Information Processing Systems 2012, NIPS, Lake Tahoe, Nevada, USA, pp. 1097-1105.
14. Li, Y., Zhang, H., Bermudez, C., Chen, Y., Landman, B. A. and Vorobeychik, Y. (2019). “Anatomical context protects deep learning from adversarial perturbations in medical imaging.” Neurocomputing.
15. Lundervold, A. S. and Lundervold, A. (2019). “An overview of deep learning in medical imaging focusing on MRI.” Zeitschrift für Medizinische Physik, Vol. 29, No. 2, pp. 102-127.
16. Max Pooling, http://adventuresinmachinelearning.com/convolutionalneural-networks-tutorial-tensorflow/[Accessed 22 July 2019].
17. Relu Activation Function, https://www.kaggle.com/kanncaa1/convolutional-neuralnetwork-cnn-tutorial/notebook [Accessed 25 July 2019].
18. Roth, H. R., Lu, L., Liu, J., Yao, J., Seff, A., Cherry, K., Kim, L. And Summers, R. M. (2015). “Improving computer-aided detection using convolutional neural networks and random view aggregation.” IEEE Transactions on Medical Imaging, Vol. 35, No. 5, pp. 1170-1181.
19. Same Padding, https://medium.com/@ayeshmanthaperera/what-ispadding-in-cnns-71b21fb0dd7 [Accessed 21 July 2019].
20. Second Model, http://fourier.eng.hmc.edu/e176/lectures/ch10/node8.html [Accessed 27 July 2019].
21. Setio, A. A. A., Ciompi, F., Litjens, G., Gerke, P., Jacobs, C., Van Riel, S. J., Wille, M. M. W., Naqibullah, M.,Sanchez, C. I. and van Ginneken, B. (2016). “Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks.” IEEE Transactions on Medical Imaging, Vol. 35, No. 5, pp. 1160-1169.
22. Shin, H. C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I. and Summers, R. M. (2016). “Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning.” IEEE transactions on medical imaging, Vol. 35, No. 5, pp. 1285-1298.
23. Sigmoid Function, http://buyukveri.firat.edu.tr/2018/04/16/derin-ogrenmeyapay-sinir-aglari-3/ [Accessed 26 July 2019].
24. Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I. and Salakhutdinov, R. (2014). “Dropout: a simple way to prevent neural networks from overfitting.” The journal of machine learning research, Vol. 15, No 1, pp. 1929-1958.
25. Şengür, A., Akılotu, B. N., Tuncer, S. A., Kadiroğlu, Z., Yavuzkılıç, S., Budak, Ü. and Deniz, E. (2018). “Optic disc determination in retinal images with deep features.” Proc., 2018 26th Signal Processing and Communications Applications Conference (SIU), Izmir, Turkey, pp. 1-4.
26. Toraman, S., Tuncer, S. A. and Balgetir, F. (2019). “Is it possible to detect cerebral dominance via EEG signals by using deep learning?” Medical hypotheses, Vol. 131,109315.
27. Transfer Learning, https://mlconf.com/blog/use-transferlearning-for-efficient-deep-learning-training/ [Accessed 28 July 2019].
28. Tuncer, S. A., Akılotu, B. and Toraman, S. (2019). “A deep learning-based decision support system for diagnosis of OSAS using PTT signals.” Medical hypotheses, Vol. 127, pp. 15-22.
29. Van Ginneken, B., Setio, A. A., Jacobs, C. and Ciompi, F. (2015). “Off-the-shelf convolutional neural network features for pulmonary nodule detection in computed tomography scans.” Proc., 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), New York, USA, pp. 286-289.
30. VGG16 Model, https://neurohive.io/en/popularnetworks/vgg16/ [Accessed 28 July 2019].
31. Wang, C., Shi, J., Zhang, Q. and Ying, S. (2017). “Histopathological image classification with bilinear convolutional neural networks.” Proc., 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Seogwipo, South Korea, pp. 4050-4053.
32. Wong, S. C., Gatt, A., Stamatescu, V., and McDonnell, M. D. (2016). “Understanding data augmentation for classification: when to warp?.” Proc., 2016 international conference on digital image computing: techniques and applications (DICTA), IEEE, Canberra, Australia, pp.1-6.
33. Zhang, J., Xie, Y., Wu, Q. and Xia, Y. (2019). “Medical image classification using synergic deep learning.” Medical Image Analysis, Vol. 54, pp. 10-19.
34. Zhu, R., Zhang, R. and Xue, D. (2015). “Lesion detection of endoscopy images based on convolutional neural network features.” Proc., 2015 8th International Congress on Image and Signal Processing (CISP), Shenyang, China, pp. 372-376.