Classification of COVID-19 in Chest X-Ray Images using Deep Transfer Learning

Roaa Abdalrhman; Murtada Elbashir; Gais Alhadi Babikir

Roaa Abdalrhman Department of Computer Science, University of Gezira, Wad Madani, Sudan
Murtada Elbashir Department of Computer Science, University of Gezira, Wad Madani, Sudan
Gais Alhadi Babikir Department of Computer Science, University of Gezira, Wad Madani, Sudan

Abstract

In December 2019, the novel coronavirus appeared in Wuhan, China, and became a critical public health problem worldwide. The transmission of this virus via small droplets produced by coughing, sneezing, and talking led to the rapid spread of the virus. Noteworthy, the coronavirus caused a devastating effect on daily lives, public health, the global economy and still threatening the lives of billions of people. Therefore, a fast and accurate method of diagnosing COVID-19 infection is vital to prevent the spread of the disease and to quickly treat affected patients. In this paper, we proposed a deep learning model for classifying covid-19 chest X-ray images into six classes. However, the main challenges are there is no large enough covid-19 dataset in the public domain compared to other classes. Hence, it is not easy to distinguish the similarities between categories and detailed features. Therefore, to counteract the problem of insufficient annotated images of covid-19 compatible with other classes, transfer learning is used which is also an effective deep feature extractor to extract similarity features between these classes. In fact, we trained three pre-training models [RestNet50, MobileNet, ResNet101] to classify covid-19 X-ray images into six classes. The experimental results showed the validity and efficiency of our proposed model which exceeds all proposed models in the literature.

References

1]. A.A. Ardakani, A.R. Kanafi, U.R. Acharya, N. Khadem, and A. Mohammad, 2020. Application of deep learning technique to manage COVID-19 in routine clinical practice using CT images: Results of 10 convolutional neural networks. Computers in biology and medicine, 121, p.103795.
2]. A. Narin, C. Kaya, and Z. Pamuk, 2021. Automatic detection of coronavirus disease (covid-19) using x-ray images and deep convolutional neural networks. Pattern Analysis and Applications, pp.1-14.
3]. X. He, S. Wang, S. Shi, X. Chu, J. Tang, X. Liu, C. Yan, J. Zhang, and G. Ding, 2020. Benchmarking deep learning models and automated model design for covid-19 detection with chest ct scans. medRxiv, 2020 Jan 1.
4]. Coronavirus. (2021, june 17). Retrieved from worldometer: https://www.worldometers.info/coronavirus/
5]. D. Singh, V. Kumar, and M. Kaur, 2020. Classification of COVID-19 patients from chest CT images using multi-objective differential evolution–based convolutional neural networks. European Journal of Clinical Microbiology & Infectious Diseases, 39(7), pp.1379-1389.
6]. S. Vaid, R. Kalantar, and M. Bhandari, 2020. Deep learning COVID-19 detection bias: accuracy through artificial intelligence. International Orthopaedics, 44, pp.1539-1542.
7]. I. Allaouzi, and M.B. Ahmed, 2019. A novel approach for multi-label chest X-ray classification of common thorax diseases. IEEE Access, 7, pp.64279-64288.
8]. A. Abbas, M.M. Abdelsamea, and M.M. Gaber, 2021. Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network. Applied Intelligence, 51(2), pp.854-864.
9]. A.U. Ibrahim, M. Ozsoz, S. Serte, F. Al-Turjman, and P.S. Yakoi, 2021. Pneumonia classification using deep learning from chest X-ray images during COVID-19. Cognitive Computation, pp.1-13.
10]. C.S.R. Annavarapu, 2021. Deep learning-based improved snapshot ensemble technique for COVID-19 chest X-ray classification. Applied Intelligence, 51(5), pp.3104-3120.
11]. T. Ozturk, M. Talo, E.A. Yildirim, U.B. Baloglu, O. Yildirim, and U.R. Acharya, 2020. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in biology and medicine, 121, p.103792.
12]. I.D. Apostolopoulos, and T.A. Mpesiana, 2020. Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Physical and Engineering Sciences in Medicine, 43(2), pp.635-640.
13]. L. Wang, Z.Q. Lin, and A. Wong, 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), pp.1-12.
14]. M. Rahimzadeh, and A. Attar, 2020. A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2. Informatics in Medicine Unlocked, 19, p.100360.
15]. J. P. Cohe, (2020). covid-chestxray-dataset. Retrieved from ieee8023: https://github.com/ieee8023/covid-chestxray-dataset
16]. R. Summers, (2017). NIHCC. Retrieved from ChestXray-NIHCC: https://nihcc.app.box.com/v/ChestXray-NIHCC
17]. E. Rezende, G. Ruppert, T. Carvalho, F. Ramos, and P. De Geus, 2017. Malicious software classification using transfer learning of resnet-50 deep neural network. In 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 1011-1014). IEEE.
18]. L. Yan, H.T. Zhang, J. Goncalves, Y. Xiao, M. Wang, Y. Guo, C. Sun, X. Tang, L. Jing, M. Zhang, and X. Huang, 2020. An interpretable mortality prediction model for COVID-19 patients. Nature machine intelligence, 2(5), pp.283-288.