A Hybrid Deep Transfer Learning-based Approach for COVID-19 Classification in Chest X-ray Images

Document Type : Research Article

Authors

1 Department of Biomedical Engineering, Meybod University, Meybod, Iran

2 Department of Biomedical Engineering, Faculty of Electrical and Computer Engineering, Tabriz University, Tabriz, Iran

3 Department of Electrical Engineering, Faculty of Engineering, Vali-e-Asr University of Rafsanjan, Rafsanjan, Iran

Abstract

The COVID-19 pandemic is a severe public health hazard. Hence, proper and early diagnosis is necessary to control the infection progression. We can diagnose this disease by employing a chest X-ray (CXR) screening, which is ordinarily cheaper and less harmful than a Computed Tomography scan (CT scan) and is continuously accessible in small or rustic hospitals. Since the COVID-19 dataset is inadequate and cannot be strictly distinguished from CXR, Deep Transfer Learning (DTL) models can be used to diagnose coronavirus even with access to a small number of images. In this paper, we presented an approach to diagnosis COVID-19 using CXR images based on the concatenated features vector of the three DTL structures and soft-voting feature selection procedure, including Receiver of Curve (ROC), Entropy, and signal-to-noise ratio (SNR) techniques. Our hybrid model reduces the feature vector size and classifies it in optimize manner to improve the decision-making process. A collection of 2,863 CXR images comprising normal, bacterial, viral, and COVID-19 cases were prepared in JPEG format from the Medical Imaging Center of Vasei Hospital, Sabzevar, Iran. The proposed approach obtained an Accuracy of 99.34%, Sensitivity of 99.48%, Specificity of 99.27% while having a far fewer number of trainable parameters in contrast to its counterparts. Compared to the latest similar methods, the diagnosis accuracy has increased from 1.5 to 2.2%. The comparative experiment reveals the advantage of the suggested COVID-19 classification pattern based on DTL over other competing schemes.

Keywords

Main Subjects

References

[1] F. Wu, S. Zhao, B. Yu, Y. M. Chen, W. Wang, Z. G. Song, Y. Hu, Z. W. Tao, J. H.  Tian, Y. Y. Pei, M. L. Yuan, A new coronavirus associated with human respiratory disease in China, Nature, 579 (7798) (2020) 265-269.
[2] C. Huang, W. Yeming L. Xingwang R. Lili, Z. Jianping, H. Yi, Z. Li, and et al., Clinical features of patients infected with 2019 novel coronavirus in Wuhan, China, The lancet,  39 (10223) (2020) 497-506.
[3] World Health Organization, WHO coronavirus disease (COVID- 19) dashboard, (2020). https://covid19.who.int/. Accessed 10 august 2020.
[4] S. Stoecklin, et al., First cases of coronavirus disease 2019 (COVID-19) in France: surveillance, investigations and control measures, January 2020, Eurosurveillance, 25 (6) (2020) 2000094.
[5] A. Jaiswal, N. Gianchandani, D. Singh, V. Kumar, and M. Kaur, Classification of the covid-19 infected patients using densenet201 based deep transfer learning, Journal of Biomolecular Structure and Dynamics, (2020) 1–8.
[6] S. Rakshit, I. Saha, M. Wlasnowolski, U. Maulik and D. Plewczynski, Deep Learning for Detection and Localization of Thoracic Diseases Using Chest X-Ray Imagery, International Conference on Artificial Intelligence and Soft Computing, (2019).
[7] M. Kaur and D. Singh, Fusion of medical images using deep belief networks, Cluster Computing, 23 (2020) 1439–1453.
[8] N. N. Das, N. Kumar, M. Kaur, V. Kumar, and D. Singh, Automated deep transfer learning-based approach for detection of covid-19 infection in chest x-rays, IRBM, 2020.
[9] A. Narin, C. Kaya and Z. Pamuk, Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks, arXiv:2003.10849, (2020), [online] Available: http://arxiv.org/abs/2003.10849.
[10] A. S. Lundervold and A. Lundervold, An overview of deep learning in medical imaging focusing on MRI, Zeitschrift für Medizinische Physik, 29 (2) (2019) 102-127, 2019.
[11] A. Maier, C. Syben, T. Lasser and C. Riess, A gentle introduction to deep learning in medical image processing, Zeitschrift für Medizinische Physik, 29 (2) (2019) 86-101.
[12] A. Krizhevsky, I. Sutskever and G. Hinton, Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6) (2017) 84-90.
[13] S. Liu and W. Deng, Very deep convolutional neural network based image classification using small training sample size, Pattern Recognition (ACPR) 2015 3rd IAPR Asian Conference on, (2015) 730-734.
[14] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, et al., Going deeper with convolutions, arXiv:1409.4842, (2014).
[15] K. He, X. Zhang, S. Ren and J. Sun,  Deep residual learning for image recognition, In Proceedings of the IEEE conference on computer vision and pattern recognition (2016) 770-778.
[16] F. Chollet, Xception: Deep learning with depthwise separable convolutions, In Proceedings of the IEEE conference on computer vision and pattern recognition (2017) 1251-1258.
[17] G. Huang, Z. Liu, L. Van Der Maaten, K. Q. Weinberger, Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, (2017) 4700-4708.
[18] M. Loey, F. Smarandache, N. E. Khalifa, Within the Lack of Chest COVID-19 X-ray Dataset: A Novel Detection Model Based on GAN and Deep Transfer Learning,” Symmetry, 12 (4) (2020) 651.
[19] L. Wang and A. Wong, COVID-net: A tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images, arXiv:2003.09871, (2020), [online] Available: http://arxiv.org/abs/2003.09871.
[20] I. D. Apostolopoulos and T. A. Mpesiana, Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks, Physical and Engineering Sciences in Medicine (2020) 1.
[21] A. Abbas, M. M. Abdelsamea and M. M. Gaber, Classification of covid-19 in chest x-ray images using detrac deep convolutional neural network, In: arXiv preprint arXiv:2003.13815, (2020).
[22] E. El-Din Hemdan, M. A. Shouman and M. Esmail Karar, COVIDX-net: A framework of deep learning classifiers to diagnose COVID-19 in X-ray images, arXiv:2003.11055, (2020), [online] Available: http://arxiv.org/abs/2003.11055.
[23] J. Zhang et al., Covid-19 screening on chest x-ray images using deep learning based anomaly detection, In: arXiv preprint arXiv:2003.12338, (2020).
[24] T. Ai, Z. Yang, H. Hou, C. Zhan, C. Chen, W. Lv, et al., Correlation of chest CT and RT-PCR testing in coronavirus disease 2019 (COVID-19) in China: A report of 1014 cases, Radiology, 26 (2020).
[25] F. Shan, Y. Gao, J. Wang, W. Shi, N. Shi, M. Han, et al., Lung infection quantification of COVID-19 in CT images with deep learning, arXiv:2003.04655, (2020), [online] Available:  http://arxiv.org/abs/2003.04655.
[26] O. Gozes, M. Frid-Adar, H. Greenspan, P. D. Browning, H. Zhang, W. Ji, et al., Rapid AI development cycle for the coronavirus (COVID-19) pandemic: Initial results for automated detection &; Patient monitoring using deep learning CT image analysis, arXiv:2003.05037, (2020), [online] Available: http://arxiv.org/abs/2003.05037.
[27] S. Wang, B. Kang, J. Ma, X. Zeng, M. Xiao, J. Guo, et al., A deep learning algorithm using CT images to screen for corona virus disease (COVID-19), in MedRxiv, (2020), [online] Available: https://doi.org/10.1101/2020.02.14.20023028.
[28] X. Xu, X. Jiang, C. Ma, P. Du, X. Li, S. Lv, et al., Deep learning system to screen coronavirus disease 2019 pneumonia, arXiv:2002.09334, (2020), [online] Available: http://arxiv.org/abs/2002.09334.
[29] J. Chen et al., Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography: A prospective study, MedRxiv, (2020).
[30] D. Das, K. C. Santosh, U. Pal, Truncated inception net: COVID-19 outbreak screening using chest X-rays, Physical and engineering sciences in medicine 43 (3) (2020) 915-925.
[31] C. Zheng, X. Deng, Q. Fu, Q. Zhou, J. Feng, H. Ma, et al., Deep Learning-based Detection for COVID-19 from Chest CT using Weak Label, Medrxiv, (2020).
[32] S. Minaee, R. Kafieh, M. Sonka, S. Yazdani, G.J. Soufi, Deep-covid: Predicting covid-19 from chest x-ray images using deep transfer learning, arXiv preprint arXiv:2004. 09363 (2020).
[33] T. D. Pham, Classification of COVID-19 chest X-rays with deep learning: new models or fine tuning?, Health Information Science and Systems, 9(1) (2021) 1-11.
[34] M. Loey, G. Manogaran, M. H. Taha, N. E. Khalifa. A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic. Measurement. 167 (2021), 108288.
[35] M. F. Aslan, M. F. Muhammed, K. Sabanci, A. Durdu, CNN-based transfer learning–BiLSTM network: A novel approach for COVID-19 infection detection, Applied Soft Computing 98 (2021): 106912.
[36] K. Rezaee, A. Badiei, S. Meshgini, A hybrid deep transfer learning based approach for COVID-19 classification in chest X-ray images. In 2020 27th National and 5th International Iranian Conference on Biomedical Engineering (ICBME) (2020) 234-241.
[37] K. Chatfield, K. Simonyan, A. Vedaldi and A. Zisserman, Return of the devil in the details: Delving deep into convolutional nets, arXiv preprint arXiv:1405.3531 (2014).
[38] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, et al., Caffe: Convolutional architecture for fast feature embedding, In Proceedings of the 22nd ACM international conference on Multimedia, (2014) 675-678.
[39] O. Russakovsky et al., ImageNet large scale visual recognition challenge,International journal of computer vision 115 (3) (2015) 211-252.
[40] K. Rezaee, F. Ghaderi, H. Taheri Gorji, J. Hadadnia, Hand gesture and movement recognition based on electromyogram signals using novel soft ensembling feature selection and optimized classifier, Journal of Biomedical Engineering, 14 (3) (2020) 221-230 (In persian).  https://doi.org/10.22041/ijbme.2020.123570.1580.
[41] X. W. Chen, M. Wasikowski, Fast: a roc-based feature selection metric for small samples and imbalanced data classification problems. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, (2008) 124-132.
[42] S. Cateni, V. Colla , M.Vannucci, A hybrid feature selection method for classification purposes. In 2014 European Modelling Symposium (2014), 39-44.
[43] T. Nguyen, A. Khosravi, D. Creighton, S. Nahavandi,  Hidden Markov models for cancer classification using gene expression profiles, Information Sciences, 316 (2015) 293-307.
[44] J. P. Vert, K. Tsuda, B. Schölkopf, A primer on kernel methods. Kernel methods in computational biology, 47(2004) 35-70.
[45] K. Rezaee, J. Haddadnia, Intelligent and Online Evaluation of Diabetes using Wireless Sensor Networks and Support Vector Machines Algorithm, Iranian Journal of Diabetes and Obesity, 6 (2) (2014) 56-66.
AUT Journal of Electrical Engineering
Volume 53, Issue 2
December 2021
Pages 223-232

Files

Share

How to cite

Statistics