Transfer Öğrenme Kullanarak Göğüs Röntgeni Görüntülerinden COVID-19 Tahmini

Abstract

COVID-19 salgını, sadece ülkelerdeki sağlık sistemlerini değil, dünya çapında tüm toplumları birçok şekilde etkilemektedir. Bu süreçte, pandeminin üstesinden gelmek için önemli sayıda çalışma yapılmış ve birçok tıbbi teknik denenmiştir. Bu çalışmada, gerçek görüntülerden yararlanarak, bir hastada COVID-19 virüsünün olup olmadığını tahmin etmek için Evrişimsel Sinir Ağlarını göğüs röntgeni görüntülerine uyguladık. Başlangıçta, görüntü işleme alanındaki başarıları nedeniyle çok iyi bilinen mimariler olan bir dizi önceden eğitilmiş ResNet, VGG, ve Xception modellerini elimizdeki probleme uygun olarak yeniden eğitmek üzere Transfer Öğrenme kullandık. Bu modellerle ulaşılan performans tatmin edici olsa da daha isabetli ve güvenilir sonuçlar elde etmek amacıyla üç ayrı modeli bir araya getiren bir topluluk modeli oluşturduk. Son olarak, topluluk modelimiz %97'lik bir F-Skoru ile diğer tüm modellerden daha iyi performans gösterdi.

Keywords

• Göğüs Röntgeni
• COVID-19
• Viral Pnömoni
• Derin Öğrenme
• Transfer Öğrenme
• Topluluk Öğrenmesi

COVID-19 Prediction from Chest X-Ray Images using Transfer Learning

Abstract

The COVID-19 pandemic has been affecting our lives in many ways, not only the healthcare systems in the countries but the whole societies worldwide. Meantime, a considerable number of studies have been conducted and lots of medical techniques have been tried to overcome the pandemic. In this work, making use of real-world images, we applied Convolutional Neural Networks to chest X-ray images to predict whether a patient has the COVID-19 virus or not. Initially, we used transfer learning to fine tune a number of pre-trained ResNet, VGG, and Xception models, which are very well-known architectures due to their success in image processing tasks. While the achieved performance with these models was encouraging, we ensembled three models to obtain more accurate and reliable results. Finally, our ensemble model outperformed all other models with an F-Score of 97%.

Keywords

• Chest X-Ray
• COVID-19
• Viral Pneumonia
• Deep Learning
• Transfer Learning
• Ensemble Learning

References

1. [1] Worldometers.info. (2021, Feb. 10). Coronavirus Update (Live) from COVID-19 Virus Pandemic [Online]. Available: https://www.worldometers.info/coronavirus/.
2. [2] K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778.
3. [3] G. Huang, Z. Liu, L. V. D. Maaten, and K. Q. Weinberger, "Densely Connected Convolutional Networks," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2261-2269.
4. [4] S. Minaee, R. Kafieh, M. Sonka, S. Yazdani, and G. Jamalipour Soufi, "Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning," Medical Image Analysis, vol. 65, p. 101794, 2020.
5. [5] F. Chollet, "Xception: Deep Learning with Depthwise Separable Convolutions," in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1800-1807.
6. [6] A. I. Khan, J. L. Shah, and M. M. Bhat, "CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images," Computer Methods and Programs in Biomedicine, vol. 196, p. 105581, 2020.
7. [7] J. Deng, W. Dong, R. Socher, L. Li, L. Kai, and F.-F. Li, "ImageNet: A large-scale hierarchical image database," in 2009 IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 248-255.
8. [8] A. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications," ArXiv, vol. abs/1704.04861, 2017.

9. [9] K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," CoRR, vol. abs/1409.1556, 2015.
10. [10] I. D. Apostolopoulos and T. A. Mpesiana, "Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks," Physical and Engineering Sciences in Medicine, vol. 43, pp. 635-640, 2020.
11. [11] T. Ozturk, M. Talo, E. A. Yildirim, U. B. Baloglu, O. Yildirim, and U. Rajendra Acharya, "Automated detection of COVID-19 cases using deep neural networks with X-ray images," Computers in Biology and Medicine, vol. 121, p. 103792, 2020.
12. [12] M. E. H. Chowdhury, T. Rahman, A. Khandakar, R. Mazhar, M. A. Kadir, Z. B. Mahbub, K. R. Islam, M. S. Khan, A. Iqbal, N. A. Emadi, M. B. I. Reaz, and M. T. Islam, "Can AI Help in Screening Viral and COVID-19 Pneumonia?," IEEE Access, vol. 8, pp. 132665-132676, 2020.
13. [13] G. Bradski, "The OpenCV library," Dr Dobb's J. Software Tools, vol. 25, pp. 120-125, 2000 2000.
14. [14] S. v. d. Walt, J. L. Schönberger, J. Nunez-Iglesias, F. Boulogne, J. D. Warner, N. Yager, E. Gouillart, T. Yu, and t. s.-i. contributors, "scikit-image: image processing in Python," PeerJ, vol. 2, p. e453, 2014.
15. [15] S. W. Yusuf, J. B. Durand, D. J. Lenihan, and J. Swafford, "Dextrocardia: an incidental finding," Texas Heart Institute journal, vol. 36, pp. 358-359, 2009.
16. [16] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge: The MIT Press, 2016.
17. [17] M. Z. Alom, T. M. Taha, C. Yakopcic, S. Westberg, P. Sidike, M. S. Nasrin, M. Hasan, B. C. Van Essen, A. A. S. Awwal, and V. K. Asari, "A State-of-the-Art Survey on Deep Learning Theory and Architectures," Electronics, vol. 8, p. 292, 2019.
18. [18] F. Huang, G. Xie, and R. Xiao, "Research on Ensemble Learning," in 2009 International Conference on Artificial Intelligence and Computational Intelligence, 2009, pp. 249-252.
19. [19] E. Alpaydin, Introduction to Machine Learning, 2nd ed. London, England: The MIT Press, 2010.
20. [20] L. Breiman, "Bagging Predictors," Machine Learning, vol. 24, pp. 123-140, 1996.
21. [21] R. E. Schapire, "Theoretical Views of Boosting and Applications," in 10th International Conference on Algorithmic Learning Theory AL'99, 1999, pp. 13-25.
22. [22] R. E. Schapire, "A Brief Introduction to Boosting," in 16th International Joint Conference on Artificial Intelligence IJCAI'99, 1999, pp. 1401-1406.
23. [23] M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean, M. Devin, S. Ghemawat, G. Irving, M. Isard, M. Kudlur, J. Levenberg, R. Monga, S. Moore, D. G. Murray, B. Steiner, P. Tucker, V. Vasudevan, P. Warden, M. Wicke, Y. Yu, and X. Zheng, "TensorFlow: a system for large-scale machine learning," in Proceedings of the 12th USENIX conference on Operating Systems Design and Implementation, Savannah, GA, USA, 2016, pp. 265–283.
24. [24] F. Chollet. (2021, Dec. 12). Keras [Online]. Available: https://keras.io.
25. [25] N. Keskar and R. Socher, "Improving Generalization Performance by Switching from Adam to SGD," ArXiv, vol. abs/1712.07628, 2017.
26. [26] L. N. Smith, "Cyclical Learning Rates for Training Neural Networks," in 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), 2017, pp. 464-472.
27. [27] R. Caruana, S. Lawrence, and L. Giles, "Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping," in Proceedings of the 13th International Conference on Neural Information Processing Systems, Denver, CO, 2000, pp. 381–387.
28. [28] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and É. Duchesnay, "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825-2830, 2011.