COVID-19 Diagnosis Using Deep Learning

Year 2021, , 8 - 23, 29.05.2021

Gür Emre Güraksın , Sezin Barın , Esra Özgül , Furkan Kaya

https://doi.org/10.29130/dubited.866124

Cited By: 5

Abstract

The coronavirus, which appeared in Wuhan city of China and named COVID-19 , spread rapidly and caused the death of many people. Early diagnosis is very important to prevent or slow the spread. The first preferred method by clinicians is real-time reverse transcription-polymerase chain reaction (RT-PCR). However, expected accuracy values cannot be obtained in the diagnosis of patients in the incubation period. Therefore, common lung devastation in COVID-19 patients were considered and radiological lung images were used to diagnose. In this study, automatic COVID-19 diagnosis was made from posteroanterior (PA) chest X-Ray images by deep learning method. In the study, using two different deep learning methods, classification was made with different dataset combinations consisting of healthy, COVID, bacterial pneumonia and viral pneumonia X-ray images. The results show that the proposed deep learning-based system can be used in the clinical setting as a supplement to RT-PCR test for early diagnosis

Keywords

Deep Learning, COVID-19, GoogleNet, AlexNet, X-ray Imaging

Derin Öğrenme Yöntemleri ile COVID-19 Teşhisi

Abstract

Çin’in Wuhan şehrinde ortaya çıkan ve COVID-19 olarak adlandırılan koronovirüsü dünyanın çok büyük bir kısmını etkisi altına alarak hızla yayılmış ve birçok insanın ölümüne yol açmıştır. Yayılmanın önlenmesi veya yavaşlatılması için erken teşhis oldukça önemlidir. Klinisyenler tarafından ilk tercih edilen yöntem gerçek zamanlı ters transkripsiyon-polimeraz zincir reaksiyonu (RT-PCR) olmaktadır. Ancak kuluçka dönemindeki hastaların teşhisinde beklenen doğruluk değerleri elde edilememektedir. Bu nedenle COVID-19 hastalarında ortak olarak görülen akciğer hasarları göz önüne alınmış ve radyolojik akciğer görüntüleri teşhis koymak için kullanılmıştır. Bu çalışmada posteroanterior(PA) göğüs X-Ray görüntülerinden derin öğrenme yöntemi ile otomatik COVID-19 teşhisi yapılmıştır. Çalışmada iki farklı derin öğrenme yöntemi kullanılarak, sağlıklı,covid,bacterial pneumonia ve viral pneumonia X-ray görüntüleri bulunan sınıflardan oluşan farklı veriseti kombinasyonları ile sınıflandırma yapılmıştır. Elde edilen sonuçlar önerilen derin öğrenme tabanlı sistemin erken teşhis için RT-PCR testini destekleyici olarak klinik ortamda kullanılabileceğini göstermektedir.

Keywords

Derin Öğrenme, COVID-19, GoogleNet, AlexNet, X-ray Görüntüleme

References

• [1] “Q&A on coronaviruses (COVID-19).” [Online]. Available: https://www.who.int/news-room/q-a-detail/q-a-coronaviruses (accessed Apr. 09, 2020).
• [2] J. Guarner, “Three Emerging Coronaviruses in Two Decades,” Am. J. Clin. Pathol., vol. 153, no. 4, pp. 420–421, 2020, doi: 10.1093/ajcp/aqaa029.
• [3] N. N. Chathappady House, S. Palissery, and H. Sebastian, “Corona Viruses: A Review on SARS, MERS and COVID-19,” Microbiol. Insights, vol. 14, pp. 1–8, 2021, doi: 10.1177/11786361211002481.
• [4] J. Xiao, M. Fang, Q. Chen, and B. He, “SARS, MERS and COVID-19 among healthcare workers: A narrative review,” J. Infect. Public Health, 2020, doi: 10.1016/j.jiph.2020.05.019.
• [5] A. Alqudah, S. Qazan, H. Alquran, and I. Qasmieh, “Covid-2019 detection using x-ray images and artificial ıntellıgence hybrıd systems,” Biomed. Signal Image Anal. Proj. Biomed. Signal Image Anal. Mach. Learn. Lab Boca Raton, FL, USA., doi: 10.5455/jjee.204-158531224.
• [6] X. Xie, Z. Zhong, W. Zhao, C. Zheng, F. Wang, and J. Liu, “Chest CT for Typical 2019-nCoV Pneumonia: Relationship to Negative RT-PCR Testing,” Radiology, 2020, doi: 10.1148/radiol.2020200343.
• [7] C. Huang et al., “Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China,” Lancet, vol. 395, no. 10223, pp. 497–506, 2020, doi: 10.1016/S0140-6736(20)30183-5.
• [8] F. Song et al., “Emerging 2019 Novel Coronavirus (2019-nCoV) Pneumonia,” Radiology, vol. 295, no. 1, pp. 210–217, 2020, doi: 10.1148/radiol.2020200274.
• [9] A. Abbas, M. M. Abdelsamea, and M. M. Gaber, “Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network,” Appl. Intell., vol. 51, no. 2, pp. 854–864, 2021, doi: 10.1007/s10489-020-01829-7.
• [10] J. P. Cohen, P. Morrison, and L. Dao, “COVID-19 Image Data Collection,” arXiv, Mar. 2020.
• [11] S. Wang et al., “A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19),” Eur. Radiol., pp. 1–9, 2021, doi: 10.1007/s00330-021-07715-1.
• [12] “Chest X-Ray Images (Pneumonia) | Kaggle.” [Online]. Available: https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia (Accessed Apr. 12, 2020).
• [13] A. M. Alqudah and S. Qazan, “Augmented COVID-19 X-ray Images Dataset,” Mendeley Data, vol. 4, 2020, doi: 10.17632/2FXZ4PX6D8.4.
• [14] X. Xu et al., “A Deep Learning System to Screen Novel Coronavirus Disease 2019 Pneumonia,” Engineering, vol. 6, no. 10, pp. 1122–1129, 2020, doi: 10.1016/j.eng.2020.04.010.
• [15] M. E. H. Chowdhury et al., “Can AI Help in Screening Viral and COVID-19 Pneumonia?,” IEEE Access, vol. 8, pp. 132665–132676, 2020, doi: 10.1109/ACCESS.2020.3010287.
• [16] “SIRM | Italian Society of Radiology.” [Online]. Available: https://www.sirm.org/en/ (Accessed Apr. 12, 2020).
• [17] “Novel Corona Virus 2019 Dataset | Kaggle.” [Online]. Available: https://www.kaggle.com/sudalairajkumar/novel-corona-virus-2019-dataset/kernels (accessed Apr. 12, 2020).
• [18] E. E.-D. Hemdan, M. A. Shouman, and M. E. Karar, “COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images,” arXiv, 2020.
• [19] B. Ghoshal and A. Tucker, “Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection,” arXiv, 2020.
• [20] A. Narin, C. Kaya, and Z. Pamuk, “Automatic Detection of Coronavirus Disease (COVID-19) Using X-ray Images and Deep Convolutional Neural Networks,” arXiv, 2020.
• [21] B. Nigam, A. Nigam, R. Jain, S. Dodia, N. Arora, and A. B, “COVID-19: Automatic Detection from X-ray images by utilizing Deep Learning Methods,” Expert Syst. Appl., 2021, doi: 10.1016/j.eswa.2021.114883.
• [22] S. Serte and H. Demirel, “Deep Learning for Diagnosis of COVID-19 using 3D CT Scans,” Comput. Biol. Med., 2021, doi: 10.1016/j.compbiomed.2021.104306.
• [23] C. Szegedy et al., “Going Deeper with Convolutions,” in In Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1–9, doi: 10.1109/CVPR.2015.7298594.
• [24] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Adv. Neural Inf. Process. Syst., vol. 25, pp. 1097–1105, 2012, doi: 10.1145/3065386.
• [25] “Web of Science [v.5.34] - Web of Science Core Collection Results.” http://proxy.afyon.deep-knowledge.net/MuseSessionID=0210h3diw/MuseProtocol=http/MuseHost=apps.webofknowledge.com (Accessed Mar. 31, 2020).
• [26] “ImageNet.” [Online]. Available: http://www.image-net.org/ (Accessed Mar. 31, 2020).
• [27] P. Pawara, E. Okafor, O. Surinta, L. Schomaker, and M. Wiering, “Comparing Local Descriptors and Bags of Visual Words to Deep Convolutional Neural Networks for Plant Recognition,” Int. Conf. Pattern Recognit. Appl. Methods , vol. 2, pp. 479–486, 2017, doi: 10.5220/0006196204790486.
• [28] C. M. J. M. Dourado, S. P. P. da Silva, R. V. M. da Nóbrega, A. C. Antonio, P. P. R. Filho, and V. H. C. de Albuquerque, “Deep learning IoT system for online stroke detection in skull computed tomography images,” Comput. Networks, vol. 152, pp. 25–39, 2019, doi: 10.1016/j.comnet.2019.01.019.
• [29] D. N. Le, V. S. Parvathy, D. Gupta, A. Khanna, J. J. P. C. Rodrigues, and K. Shankar, “IoT enabled depthwise separable convolution neural network with deep support vector machine for COVID-19 diagnosis and classification,” Int. J. Mach. Learn. Cybern., pp. 1–14, 2021, doi: 10.1007/s13042-020-01248-7.
• [30] R. M. Sarmento, F. F. X. Vasconcelos, P. P. R. Filho, and V. H. C. de Albuquerque, “An IoT platform for the analysis of brain CT images based on Parzen analysis,” Futur. Gener. Comput. Syst., vol. 105, pp. 135–147, 2020, doi: 10.1016/j.future.2019.11.033.