COVID-19 Diagnosis From X-ray Images With Artificial Neural Network Based Model

Öz

The number of coronavirus patients around the world is increasing day by day. Although more than one year has passed since the emergence of the disease, statistics show that the peak number of patients have not reached yet. The spread of the increase in the number of patients over time is important to prevent hospital occupancy rates from hitting dangerous levels. For this reason, people carrying the virus should be diagnosed quickly and isolated from society until the disease is over. In this study, a comprehensive artificial neural network-based model has been proposed for rapid disease diagnosis using X-ray images. Using the damage created by the coronavirus in the lung tissues, the diagnosis can be made within seconds. The model subject to study improves and augments X-ray images by pre-processing. After training is performed using DenseNet201, ResNeXt-101(32×8d), VGG-19bn and Wide-ResNet101-2 networks, Covid-19 positive or negative diagnosis is provided from the image. The best result obtained in the study is achieved by using ResNeXt-101(32×8d) network with an overall accuracy rate of 94.79%.

Anahtar Kelimeler

• Covid-19
• disease diagnosis
• X-ray
• Artificial neural network

Yapay Sinir Ağı Tabanlı Model ile X-ray Görüntülerinden Covid-19 Teşhisi

Öz

Dünyadaki koronavirüs hasta sayısı her geçen gün artmaktadır. Hastalığın ortaya çıkışının üzerinden bir seneden fazla zaman geçmesine rağmen istatistiklere göre henüz hasta sayısındaki zirve görülmemiştir. Hasta sayısındaki artışın zamana yayılması hastane doluluk oranlarının tehlikeli boyutlara ulaşmasını önlemek için önemlidir. Bu nedenle virüsü taşıyan bireylerin hızlıca teşhis edilerek hastalık geçene kadar toplumdan soyutlanmaları gerekmektedir. Bu çalışmada X-ray görüntüsü kullanılarak yapılabilecek hızlı hastalık teşhisi için kapsamlı bir yapay sinir ağı tabanlı model önerilmiştir. Koronavirüsün akciğerler dokularında yarattığı tahribattan yararlanılarak teşhis işlemi saniyeler içerisinde yapılabilmektedir. Çalışmaya konu olan model, X-ray görüntülerini ön-işlemlerden geçirerek iyileştirmekte ve çoğullamaktadır. DenseNet201, ResNeXt-101(32×8d), VGG-19bn ve Wide-ResNet101-2 ağları kullanılarak eğitim yapıldıktan sonra görüntüden Covid-19 pozitif veya negatif olarak teşhis konulmasını sağlamaktadır. Çalışmada elde edilen en iyi sonuç %94.79 genel doğruluk oranıyla ResNeXt-101(32×8d) ağı kullanılarak gerçekleştirilmiştir.

Anahtar Kelimeler

• Covid-19
• hastalık teşhisi
• X-ray
• yapay sinir ağları

Kaynakça

1. [1] Wang S., Kang B., Ma J., Zeng X., Xiao M., Guo J., ... & Xu B., “A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19)”, MedRxiv, (2020).
2. [2] Oh Y., Park S., Chul J., “Deep Learning COVID-19 Features on CXR using Limited Training Data”, IEEE Transactions on Medical Imaging, 39, 2688-2700, (2020).
3. [3] Narin A., Kaya C., Pamuk Z., “Automatic detection of coronavirus disease (covid-19) using x-ray images and deep convolutional neural Networks”, arXiv preprint arXiv:2003.10849, (2020).
4. [4] Blain M., Kassin M. T., Varble N., Wang X., Xu Z., Xu D., ... , Di Meglio L., “Determination of disease severity in COVID-19 patients using deep learning in chest X-ray images”, Diagn Interv Radiol., (2020).
5. [5] Zhang J., Xie Y., Pang G., Liao Z., Verjans J., Li W., ... & Xia Y., “Viral Pneumonia Screening on Chest X-rays Using Confidence-Aware Anomaly Detection” IEEE transactions on medical imaging.,(2020).
6. [6] Wang L., Lin Z. Q., Wong A., “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, (2020).
7. [7] Sharma A., Rani S., Gupta D., “Artificial intelligence-based classification of chest X-ray images into COVID-19 and other infectious diseases”, International journal of biomedical imaging, (2020).
8. [8] Casado-García A., Domínguez C., García-Domínguez M., Heras J., Ines A., Mata E., Pascual V., “CLoDSA: a tool for augmentation in classification, localization, detection, semantic segmentation and instance segmentation tasks”, BMC Bioinformatics, 20(1): 323, (2019).

9. [9] Gao T., “Chest X-ray image analysis and classification for COVID-19 pneumonia detection using Deep CNN”, medRxiv., (2020).
10. [10] Abbas A., Abdelsamea M. M., Gaber M. M., “Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network”, arXiv preprint arXiv:2003.13815, (2020).
11. [11] Pereira R. M., Bertolini D., Teixeira L. O., Silla Jr C. N., Costa Y. M., “COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios”, Computer Methods and Programs in Biomedicine, 105532, (2020).
12. [12] Jain R., Gupta M., Taneja S., Hemanth D. J., “Deep learning based detection and analysis of COVID-19 on chest X-ray images”, Applied Intelligence, 1-11, (2020).
13. [13] Minaee S., Kafieh R., Sonka M., Yazdani S., Soufi G. J., “Deep-covid: Predicting covid-19 from chest x-ray images using deep transfer learning”, arXiv preprint arXiv:2004.09363, (2020).
14. [14] Hemdan E. E. D., Shouman M. A., Karar M. E., “Covidx-net: A framework of deep learning classifiers to diagnose covid-19 in x-ray images”, arXiv preprint arXiv:2003.11055., (2020).
15. [15] Luz E. J. D. S., Silva P. L., Silva R., Silva L., Moreira G., Menotti D., “Towards an Effective and Efficient Deep Learning Model for COVID-19 Patterns Detection in X-ray Images”, CoRR., (2020).
16. [16] Kaya A., Ataş K., Myderrizi I., “Implementation of CNN based COVID-19 classification model from CT images”, IEEE 19th World Symposium on Applied Machine Intelligence and Informatics, Slovakia, 201-206, (2021).
17. [17] Civit-Masot J., Luna-Perejón F., Domínguez Morales M., Civit, A., “Deep learning system for COVID-19 diagnosis aid using X-ray pulmonary images”, Applied Sciences, 10(13), 4640., (2020).
18. [18] Ismael A. M., Şengür A., “Deep learning approaches for COVID-19 detection based on chest X-ray images”, Expert Systems with Applications, 164, 114054., (2020).
19. [19] Afshar P., Heidarian S., Naderkhani F., Oikonomou A., Plataniotis K. N., Mohammadi A., “Covid-caps: A capsule network-based framework for identification of covid-19 cases from x-ray images”, arXiv preprint arXiv:2004.02696., (2020).
20. [20] Cohen, J. P., Morrison, P., Dao, L., Roth, K., Duong, T. Q., & Ghassemi, M. Covid-19 image data collection: Prospective predictions are the future. arXiv preprint arXiv:2006.11988. (2020). [21] C. Shorten, T. M. Khoshgoftaar, “A Survey on Image Data Augmentation for Deep Learning,” Journal of Big Data 6, 60, (2019).
21. [22] Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, 248-255, (2009).
22. [23] Simonyan, K., & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. (2014).
23. [24] Zagoruyko, S., & Komodakis, N. Wide residual networks. arXiv preprint arXiv:1605.07146. (2016).
24. [25] Xie, S., Girshick, R., Dollár, P., Tu, Z., & He, K. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition ,1492-1500, (2017).
25. [26] Krizhevsky, A., Sutskever, I., & Hinton, G. E. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90. (2017).
26. [27] Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition , 4700-4708, (2017).
27. [28] Bishop, C. M. "Pattern recognition and machine learning; 2nd printing." Springer, ISBN 10: 0387310738 New York, (2010).
28. [29] Powers, D.M., “Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation.”. arXiv preprint arXiv:2010.16061. (2020).