Derin Öğrenme Kullanılarak COVID-19 Vakalarının Tespiti

Abstract

2019 yılının sonlarında solunum yolu enfeksiyonu belirtileri ile ortaya çıkan COVID-19 insan hayatını ciddi şekilde etkilemekte, sağlık, eğitim, ekonomi gibi günlük sosyal aktivitelerin aksamasına sebep olmaktadır. Vakaları hızlı teşhis edebilmek salgının engellenmesi için çok önemlidir. Yapay zeka, bilgisayarların insan gibi düşünmesini sağlayarak karmaşık problemleri çözmelerini, karar vermelerini ve öğrenmelerini mümkün kılar. Derin öğrenme, yapay sinir ağları adı verilen karmaşık yapılar kullanarak, büyük miktarda verileri analiz ederek öğrenme yöntemidir. X-Ray, MRI ve BT gibi tıbbi görüntüleme yöntemlerinden sağlanan görüntüleri ve sinyal verilerini, çeşitli derin öğrenme mimarileri kullanılarak analiz edilebilmektedir. Bu çalışmada derin öğrenme modelleri kullanılarak COVID-19 vakası tespiti amaçlanmıştır. Çalışmada CNN, Xception, VGG19, Alexnet, VGG19, ResNet50 modellerinden oluşan derin öğrenme modelleri kullanılmıştır. Çalışmada 576 adet COVID-19 pozitif, 1583 adet normal, 4273 adet pnömoni teşhisi

Keywords

• COVID-19
• Yapay Zeka
• Yapay Sinir Ağları
• Evrişimli Sinir Ağları

Detection of COVID-19 Cases Using Deep Learning

Abstract

Emerging in late 2019 with respiratory infection symptoms, COVID-19 has significantly impacted human life, disrupting daily social activities such as health, education, and the economy. Rapid identification of cases is crucial for controlling the outbreak. Artificial intelligence enables computers to think like humans, allowing them to solve complex problems, make decisions, and learn. Deep learning is a method that utilizes complex structures called artificial neural networks to analyze large volumes of data and learn from them. Medical imaging techniques such as X-rays, MRIs, and CT scans can be analyzed using various deep learning architectures. This study aims to detect COVID-19 cases using deep learning models. The models employed include CNN, Xception, VGG19, AlexNet, and ResNet50. The dataset comprises 6,432 chest X-ray images, including 576 positive for COVID-19, 1,583 normal cases, and 4,273 diagnosed with pneumonia. Of this dataset, 80% was used for training and 20% for testing. The performance of the resulting deep learning models was evaluated and compared based on accuracy, precision, sensitivity, and F1 score. The results indicate that deep learning models could significantly contribute to the detection of COVID-19 and similar diseases within health systems.

Keywords

• COVID-19
• Artificial Intelligence
• Artificial Neural Networks
• Deep Learning
• Convolutional Neural Networks.

References

1. Agarap, A. F. 2018. Deep learning using rectified linear units (relu). arXiv Preprint arXiv:1803.08375, 1-8.
2. Avenash, R., Viswanath, P. 2019. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications VISIGRAPP, 413-420.
3. Caobelli, F. 2020. Artificial intelligence in medical imaging: Game over for radiologists?. European Journal of Radiology, 126, 108940
4. Chollet, F., 2017. Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition, 1251- 1258.
5. Ciresan, D. C., Meier, U., Gambardella, L. M., & Schmidhuber, J., 2011. Convolutional neural network committees for handwritten character classification. 2011 International Conference on Document Analysis and Recognition, IEEE, Beijing, China.
6. Deng, L. ve Yu, D. 2014. Deep learning: methods and applications. Foundations and Trends in Signal Processing, 7(3–4), 197-387.
7. Doğan, F., Türkoğlu, İ. (2019) Derin Öğrenme Modelleri ve Uygulama Alanlarına İlişkin Bir Derleme, 417, DÜMF Mühendislik Dergisi 10:2 (2019) : 409-445
8. Hemdan, E. E. D., Shouman, M. A. ve Karar, M. E. 2020. Covidx-net: A framework of deep learning classifiers to diagnose COVID-19 in X-ray images. arXiv Preprint arXiv:2003.11055, 1-14

9. Hossin, M. and Sulaiman, M.N. (2015) A review on evaluation metrics for data classification evaluations, International Journal of Data Mining & Knowledge Management Process, 5(2), 1-11. doi: 10.5121/ijdkp.2015.5201
10. Ismael, A. M. ve Şengür, A. 2021. Deep learning approaches for COVID-19 detection based on chest X-ray images. Expert Systems With Applications, 164, 6.
11. Jarrett, K., Kavukcuoglu, K., & LeCun, Y. (2009). What is the best multi-stage architecture for object recognition?. In Computer Vision, 2009 IEEE 12th International Conference on(pp. 2146-2153).
12. Kızrak, A., (2018). Konu: Derine Daha Derine: Evrişimli Sinir Ağları, Bilgisayarlı görü neden gerekli?. Erişim Adresi: https://medium.com/deep-learning-turkiye/deri%CC%87nedaha-deri%CC%87ne-evri%C5%9Fimli-sinir-a%C4%9Flar%C4%B1-2813a2c8b2a
13. Lin, M., Chen, Q. and Yan, S., 2013. Network in network. arXiv preprint arXiv:1312.4400.
14. Ouchicha, C., Ammor, O. ve Meknassi, M. 2020. CVDNet: A novel deep learning architecture for detection of coronavirus (Covid-19) from chest X-ray images. Chaos, Solitons and Fractals, 140
15. Ozturk, T., Talo, M., Yildirim, E. A., Baloglu, U. B., Yildirim, O. ve Acharya, U. R. 2020. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in Biology and Medicine, 121.
16. Pandit, M. K., Banday, S. A., Naaz, R. and Chishti, M. A., 2020. Automatic detection of COVID-19 from chest radiographs using deep learning. Radiography
17. Panwar, H., Gupta, P. K., Siddiqui, M. K., Morales-Menendez, R. and Singh, V., 2020b. Application of deep learning for fast detection of COVID-19 in X-Rays using nCOVnet. Chaos, Solitons and Fractals, 138, 109944.
18. Patel, P., 2020, Chest X-ray (Covid-19 & Pneumonia) https://www.kaggle.com/datasets/prashant268/chest-xray-covid19-pneumonia
19. Scherer, D., Müller, A., and Behnke, S. (2010) Evaluation of pooling operations in convolutional architectures for object recognition, In International conference on artificial neural networks, Springer, Berlin, Heidelberg, 92-101. doi: 10.1007/978-3-642-15825-4_10 Tabian I., Fu H., and Khodaei Z., 2019, A convolutional neural network for impact detection and characterization of complex composite structures, Sensors, 19, 4933.
20. Talo, M. 2019. Convolutional neural networks for multi-class histopathology image classification. arXiv Preprint arXiv:1903.10035, 1-16.
21. Ucar, F. and Korkmaz, D., 2020. COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images. Medical Hypotheses, 140, 109761.
22. Zheng, Y., Yang, C. and Merkulov, A. (2018) Breast cancer screening using convolutional neural network and follow-up digital mammography, in Proc. SPIE San Francisco 10669, Computational Imaging III, doi: 10.1117/12.2304564
23. Medium, Convolutional Neural Network from Scratch,acces link https://medium.com/latinxinai/convolutional-neural-network-from-scratch-6b1c856e1c07, accessed on 28 July 2025.
24. Medium, Convolutional Neural Network from Scratch, acces link https://ayyucekizrak.medium.com/deri%CC%87ne-daha-deri%CC%87ne-evri%C5%9Fimli-sinir-a%C4%9Flar%C4%B1-2813a2c8b2a9, accessed on 28 July 2025.
25. Pashine, S., Mandiya, S., Gupta, P., & Sheikh, R. (2021). Deep fake detection: Survey of facial manipulation detection solutions. arXiv preprint arXiv:2106.12605. https://doi.org/10.48550/arXiv.2106.12605
26. Eryilmaz, F., & Karacan, H. (2021). Comparison Of Lightweight And Traditional Convolutional Neural Network Architectures In The Detection Of Covid-19 From Lung X-Ray Images. Düzce University Journal Of Science And Technology, 9, 26-39. Https://Doi.Org/10.29130/Dubited.1011829.