Derin Öğrenme Tekniklerini Kullanarak Akciğer X-Ray Görüntülerinden COVID-19 Tespiti

Abstract

COVID-19 salgını tüm dünyada hızla yayılarak küresel bir pandemi haline gelmiştir. Bu salgın, günlük yaşamda hem halk sağlığı hem de küresel ekonomi üzerinde yıkıcı bir etkiye sahip olmuştur. Bu salgının daha fazla yayılmasını önlemek ve etkilenen hastaları hızla tedavi etmek için pozitif vakaları olabildiğince erken tespit etmek çok önemlidir. COVID-19 enfeksiyonunun hızlı bir şekilde ve yüksek doğrulukta teşhisini sağlayan herhangi bir yardımcı araç uzmanlar için faydalıdır. Bu anlamda, X-Ray tomografik görüntüleme COVID-19 teşhisinde kolay erişilebilir alternatif bir araçtır. Radyoloji görüntüleme teknikleri kullanılarak elde edilen son bulgular, bu tür görüntülerin COVID-19 virüsü hakkında çarpıcı bilgiler içerdiğini göstermektedir. Radyolojik görüntülemeyle birlikte gelişmiş yapay zekâ ve makine öğrenmesi tekniklerinin uygulanması, bu hastalığın doğru tespiti için yardımcı olabilir. X-ray görüntüleri şüpheli vakaların erken tespitine yardımcı olabilse de, çeşitli viral ve bakteriyel pnömoni (zatürre) görüntüleri COVID-19 ile benzerdir ve benzer özellikler içermektedir. Dolayısıyla radyologların viral ve bakteriyel pnömoni gibi benzer akciğer hastalıklarını COVID-19’dan ayırt etmesi zordur. Bu bağlamda, COVID-19 semptomlarının viral pnömoniye benzer olması, yanlış tanılara yol açabilmektedir. Bu çalışmada, kurulan farklı modeller ile akciğer X-Ray görüntülerini COVID-19, normal ve viral pnömoni (zatürre) hastalar olarak sınıflandırabilen derin öğrenme tekniklerinin bir karşılaştırması yapılmıştır. Bu çalışmada, 11 farklı derin öğrenme tekniği üzerinde çalışılmıştır. Günümüzde popüler olan evrişimli sinir ağları tabanlı farklı tekniklerin aynı veri kümesi üzerinde deneysel çalışmaları yapılarak her bir tekniğin performans değerlendirmesi yapılmış ve en iyi tahminleme yöntemi belirlenmiştir. Yapılan deneysel çalışmalarda, en yüksek doğruluk değeri %97.17 ile DenseNet121 modeli ile elde edilmiştir.

Keywords

• Derin öğrenme
• Evrişimli sinir ağları
• Sınıflandırma
• Akciğer X-Ray görüntüleri
• COVID-19

COVID-19 Detection from Chest X-Ray Images Using Deep Learning Techniques

Abstract

COVID-19 has spread rapidly all over the world and has become a global pandemic. This epidemic has a devastating impact on both public health and the global economy in everyday life. Detecting positive cases as early as possible is crucial to prevent the further spread of this epidemic and to treat affected patients quickly. Any tool that provides a fast and highly accurate diagnosis of COVID-19 infection is useful to experts. In this context, X-Ray tomographic imaging is an easily accessible alternative tool in the diagnosis of COVID-19. Recent developments using radiology imaging techniques show that such images contain interesting information about the COVID-19. The application of advanced artificial intelligence and machine learning techniques combined with radiological imaging can assist to accurate detection of this disease. Although X-Ray images can help to diagnose suspected cases early, various viral and bacterial pneumonia images are similar to COVID-19 and include similar features. Therefore, it is difficult for radiologists to distinguish similar lung diseases like viral and bacterial pneumonia from COVID-19. In this context, the similarity of COVID-19 symptoms to viral pneumonia can lead to misdiagnosis. In this study, deep learning techniques that can classify chest X-Ray images as COVID-19, normal and viral pneumonia are compared. In this study, 11 different deep learning techniques have been studied. Experimental studies of different techniques based on convolutional neural networks, which are popular today, have been studied on the same dataset to evaluate the performance of each technique and the best prediction method has been determined. In experimental studies, the highest accuracy value is obtained with the DenseNet121 model with 97.17%.

Keywords

• Deep learning
• Convolutional neural network
• Classification
• Chest X-ray images
• COVID-19

References

1. Abd Almisreb, A., Jamil, N., & Din, N. M. (2018). Utilizing AlexNet deep transfer learning for ear recognition. In 2018 Fourth International Conference on Information Retrieval and Knowledge Management (CAMP) (pp. 1-5). IEEE.
2. Asnaoui, K. E., Chawki, Y., & Idri, A. (2020). Automated methods for detection and classification pneumonia based on x-ray images using deep learning. arXiv preprint arXiv:2003.14363.
3. Bhandary, A., Prabhu, G. A., Rajinikanth, V., Thanaraj, K. P., Satapathy, S. C., Robbins, D. E., ... & Raja, N. S. M. (2020). Deep-learning framework to detect lung abnormality–A study with chest X-Ray and lung CT scan images. Pattern Recognition Letters, 129, 271-278.
4. Bozkurt, F., Altay, Ş. Y., Yaganoğlu, M., (2015). Yapay Sinir Ağları İle Ankara İlinde Hava Kalitesi Sağlık İndeksi Tahmini, 2.Ulusal Yönetim Bilişim Sistemleri Kongresi, Erzurum.
5. Bozkurt, F., Köse, C., & Sarı, A. (2020). A texture-based 3D region growing approach for segmentation of ICA through the skull base in CTA. Multimedia Tools and Applications, 79(43), 33253-33278.
6. Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1251-1258).
7. Chouhan, V., Singh, S. K., Khamparia, A., Gupta, D., Tiwari, P., Moreira, C., ... & De Albuquerque, V. H. C. (2020). A novel transfer learning based approach for pneumonia detection in chest X-ray images. Applied Sciences, 10(2), 559.
8. Chowdhury, M. E., Rahman, T., Khandakar, A., Mazhar, R., Kadir, M. A., Mahbub, Z. B., ... & Islam, M. T. (2020). “Can AI help in screening viral and COVID-19 pneumonia?”, IEEE Access, 8, 132665-132676.

9. Dai, W. C., Zhang, H. W., Yu, J., Xu, H. J., Chen, H., Luo, S. P., ... & Lin, F. (2020). CT imaging and differential diagnosis of COVID-19. Canadian Association of Radiologists Journal, 71(2), 195-200.
10. Erdem, E., & Bozkurt, F. (2021). A comparison of various supervised machine learning techniques for prostate cancer prediction. Avrupa Bilim ve Teknoloji Dergisi, (21), 610-620.
11. Gopalakrishnan, K., Khaitan, S.K., Choudhary, A., Agrawal, A. (2017). Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection, Constr. Build. Mater. 157, 322–330.
12. Han, X., Zhong, Y., Cao, L., & Zhang, L. (2017). Pre-trained alexnet architecture with pyramid pooling and supervision for high spatial resolution remote sensing image scene classification. Remote Sensing, 9(8), 848.
13. Hassaballah, M., & Awad, A. I. (Eds.). (2020). Deep learning in computer vision: principles and applications. CRC Press.
14. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition,pp. 770-778.
15. Ho, T. K. K., & Gwak, J. (2019). Multiple feature integration for classification of thoracic disease in chest radiography. Applied Sciences, 9(19), 4130.
16. Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4700-4708.
17. Ismael, A. M., & Şengür, A. (2021). Deep learning approaches for COVID-19 detection based on chest X-ray images. Expert Systems with Applications, 164, 114054.
18. Kesim, E., Dokur, Z., & Olmez, T. (2019). X-ray chest image classification by a small-sized convolutional neural network. In 2019 scientific meeting on electrical-electronics & biomedical engineering and computer science (EBBT) (pp. 1-5). IEEE.
19. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 1097-1105.
20. Kumar, S., Mishra, S., & Singh, S. K. (2020). Deep Transfer Learning-based COVID-19 prediction using Chest X-rays. medRxiv.
21. Li, L., Qin, L., Xu, Z., Yin, Y., Wang, X., Kong, B., ... & Xia, J. (2020). Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT. Radiology.
22. Narin, A., Kaya, C., & Pamuk, Z. (2020). Automatic detection of coronavirus disease (covid-19) using x-ray images and deep convolutional neural networks. arXiv preprint arXiv:2003.10849.
23. Oğuz Ç. & Yağanoğlu, M. (2021). Determination of Covid-19 Possible Cases by Using Deep Learning Techniques, Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 25(1), 7-17.
24. Otter, D. W., Medina, J. R., & Kalita, J. K. (2020). A survey of the usages of deep learning for natural language processing. IEEE Transactions on Neural Networks and Learning Systems.
25. Ouchicha, C., Ammor, O., & Meknassi, M. (2020). CVDNet: A novel deep learning architecture for detection of coronavirus (Covid-19) from chest x-ray images. Chaos, Solitons & Fractals, 140, 110245.
26. Özbilgin, F., & Cengiz, T. E. P. E. (2020). Robotik Uygulamalar İçin Derin Öğrenme Tabanlı Nesne Tespiti ve Sınıflandırması. Karadeniz Fen Bilimleri Dergisi, 10(1), 205-213.
27. Pathak, Y., Shukla, P. K., Tiwari, A., Stalin, S., & Singh, S. (2020). Deep transfer learning based classification model for COVID-19 disease. Irbm.
28. Rawat, W., & Wang, Z. (2017). Deep convolutional neural networks for image classification: A comprehensive review. Neural computation, 29(9), 2352-2449.
29. Sarker, L., Islam, M. M., Hannan, T., & Ahmed, Z. (2021). Covid-densenet: A deep learning architecture to detect covid-19 from chest radiology images.
30. Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
31. Singh, K. K., Siddhartha, M., & Singh, A. (2020). Diagnosis of Coronavirus Disease (COVID-19) from Chest X-ray images using modified XceptionNet. Romanian Journal of Information Science and Technology, 23(657), 91-115.
32. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-9.
33. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2818-2826.
34. Theckedath, D., & Sedamkar, R. R. (2020). Detecting Affect States Using VGG16, ResNet50 and SE-ResNet50 Networks. SN Computer Science, 1(2), 1-7.
35. Toraman, S., & Bihter, D. A. Ş. (2020). Evrişimsel sinir ağları kullanılarak normal ve göğüs kanseri hücreleri içeren genomların sınıflandırılması. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 11(1), 81-90.
36. Wang, L., Lin, Z. Q., & Wong, A. (2020). Covid-net: A tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Scientific Reports, 10(1), 1-12.
37. WHO. (2020). Coronavirus disease (COVID-19) Pandemic. Erişim: 15 Şubat 2021. https://www.who.int/emergencies/diseases/novel-coronavirus-2019.
38. Xu, X., Jiang, X., Ma, C., Du, P., Li, X., Lv, S., ... & Li, L. (2020). A deep learning system to screen novel coronavirus disease 2019 pneumonia. Engineering, 6(10), 1122-1129.
39. Yağanoğlu, M., & Irmak, E. (2021). Separation of Incoming E-Mails Through Artificial Intelligence Techniques. Avrupa Bilim ve Teknoloji Dergisi, (21), 690-696.
40. Zhao, J., Zhang, Y., He, X., & Xie, P. (2020). Covid-ct-dataset: a ct scan dataset about covid-19. arXiv preprint arXiv:2003.13865.
41. Zheng, Y., Yang, C., & Merkulov, A. (2018). Breast cancer screening using convolutional neural network and follow-up digital mammography. In Computational Imaging III, Vol. 10669, p.1066905, International Society for Optics and Photonics.