Covid-19 Detection from Chest X-Ray Images and Hybrid Model Recommendation with Convolutional Neural Networks

Abstract

The COVID-19 pandemic, which emerged at the end of 2019, continues to be effective. Although various vaccines have been developed, uncertainties remain over vaccine sharing, supply, storage and effect. The tendency of some countries to keep the developed vaccines only for their own citizens and using them as a political leverage shows that the pandemic will not end in the near future. In addition, discussions continue about the effectiveness of the proposed vaccine and drugs. For these reasons, the most effective method in the fight against COVID-19 is still considered to be using mask, social distance and 14-day isolation after disease detection. In most countries around the world, difficulties in diagnosing COVID-19 remain. Within the scope of the related study, the detection of COVID-19 from cost-effective and easily accessible lung X-Ray images was studied. The detection of COVID-19, which can be confused with other lung diseases from X-Ray images, can only be made by expert radiologists. In this context, a hybrid approach with high accuracy classification based on convolutional neural network has been proposed for the detection of COVID-19 pneumonia. In the proposed architecture, binary and multiple classification was made using MobileNetV2, DenseNet121, Inception ResNet V2 and Xception networks. Then, these networks were combined with stacking ensemble learning to create a hybrid model.

Keywords

• COVID-19
• CHEST X-RAY
• ENSEMBLE DEEP LEARNING
• CNN
• MACHINE LEARNING
• ANN
• Viral Pneumonia
• Binary Classification
• Multiple Classification

References

1. Allam, Z. (2020). The First 50 days of COVID-19: A Detailed Chronological Timeline and Extensive Review of Literature Documenting the Pandemic. Surveying the Covid-19 Pandemic and Its Implications, 1–7. doi: 10.1016/b978-0-12-824313-8.00001-2
2. Allam, Z. (2020). The First 50 days of COVID-19: A Detailed Chronological Timeline and Extensive Review of Literature Documenting the Pandemic. Surveying the Covid-19 Pandemic and Its Implications, 1–7. doi: 10.1016/b978-0-12-824313-8.00001-2
3. Qu, J., Cao, B., & Chen, R. (2021). Respiratory virus and COVID-19. Covid-19, 1-6. doi:10.1016/b978-0-12-824003-8.00001-2
4. Qu, J., Cao, B., & Chen, R. (2021). Respiratory virus and COVID-19. Covid-19, 1-6. doi:10.1016/b978-0-12-824003-8.00001-2
5. WHO Coronavirus (COVID-19) Dashboard. (n.d.). Retrieved from https://covid19.who.int/
6. WHO Coronavirus (COVID-19) Dashboard. (n.d.). Retrieved from https://covid19.who.int/
7. Huang, P., Liu, T., Huang, L., Liu, H., Lei, M., Xu, W., . . . Liu, B. (2020). Use of Chest CT in Combination with Negative RT-PCR Assay for the 2019 Novel Coronavirus but High Clinical Suspicion. Radiology, 295(1), 22-23. doi:10.1148/radiol.2020200330
8. Huang, P., Liu, T., Huang, L., Liu, H., Lei, M., Xu, W., . . . Liu, B. (2020). Use of Chest CT in Combination with Negative RT-PCR Assay for the 2019 Novel Coronavirus but High Clinical Suspicion. Radiology, 295(1), 22-23. doi:10.1148/radiol.2020200330

9. Wang, L., Lin, Z. Q., & Wong, A. (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). doi:10.1038/s41598-020-76550-z
10. Wang, L., Lin, Z. Q., & Wong, A. (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). doi:10.1038/s41598-020-76550-z
11. Ozturk, T., Talo, M., Yildirim, E. A., Baloglu, U. B., Yildirim, O., & Acharya, U. R. (2020). Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in Biology and Medicine, 121, 103792. doi:10.1016/j.compbiomed.2020.103792
12. Ozturk, T., Talo, M., Yildirim, E. A., Baloglu, U. B., Yildirim, O., & Acharya, U. R. (2020). Automated detection of COVID-19 cases using deep neural networks with X-ray images. Computers in Biology and Medicine, 121, 103792. doi:10.1016/j.compbiomed.2020.103792
13. Wang, D., Hu, B., Hu, C., Zhu, F., Liu, X., Zhang, J., . . . Peng, Z. (2020). Clinical Characteristics of 138 Hospitalized Patients With 2019 Novel Coronavirus–Infected Pneumonia in Wuhan, China. Jama, 323(11), 1061. doi:10.1001/jama.2020.1585
14. Wang, D., Hu, B., Hu, C., Zhu, F., Liu, X., Zhang, J., . . . Peng, Z. (2020). Clinical Characteristics of 138 Hospitalized Patients With 2019 Novel Coronavirus–Infected Pneumonia in Wuhan, China. Jama, 323(11), 1061. doi:10.1001/jama.2020.1585
15. Wang, Z., Xiao, Y., Li, Y., Zhang, J., Lu, F., Hou, M., & Liu, X. (2021). Automatically discriminating and localizing COVID-19 from community-acquired pneumonia on chest X-rays. Pattern Recognition, 110, 107613. doi:10.1016/j.patcog.2020.107613
16. Wang, Z., Xiao, Y., Li, Y., Zhang, J., Lu, F., Hou, M., & Liu, X. (2021). Automatically discriminating and localizing COVID-19 from community-acquired pneumonia on chest X-rays. Pattern Recognition, 110, 107613. doi:10.1016/j.patcog.2020.107613
17. Oh, Y., Park, S., & Ye, J. C. (2020). Deep Learning COVID-19 Features on CXR Using Limited Training Data Sets. IEEE Transactions on Medical Imaging, 39(8), 2688-2700. doi:10.1109/tmi.2020.2993291
18. Oh, Y., Park, S., & Ye, J. C. (2020). Deep Learning COVID-19 Features on CXR Using Limited Training Data Sets. IEEE Transactions on Medical Imaging, 39(8), 2688-2700. doi:10.1109/tmi.2020.2993291
19. Narin, A., Kaya, C., & Pamuk, Z. (2021). Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. Pattern Analysis and Applications. doi:10.1007/s10044-021-00984-y
20. Narin, A., Kaya, C., & Pamuk, Z. (2021). Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks. Pattern Analysis and Applications. doi:10.1007/s10044-021-00984-y
21. Hemdan, E. E., Shouman, A. M., Karar, M. E. (2020). COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images. arXiv:2003.11055
22. Hemdan, E. E., Shouman, A. M., Karar, M. E. (2020). COVIDX-Net: A Framework of Deep Learning Classifiers to Diagnose COVID-19 in X-Ray Images. arXiv:2003.11055
23. Rubin, G. D., Ryerson, C. J., Haramati, L. B., Sverzellati, N., Kanne, J. P., Raoof, S., . . . Leung, A. N. (2020). The Role of Chest Imaging in Patient Management during the COVID-19 Pandemic: A Multinational Consensus Statement from the Fleischner Society. Radiology, 296(1), 172-180. doi:10.1148/radiol.2020201365
24. Rubin, G. D., Ryerson, C. J., Haramati, L. B., Sverzellati, N., Kanne, J. P., Raoof, S., . . . Leung, A. N. (2020). The Role of Chest Imaging in Patient Management during the COVID-19 Pandemic: A Multinational Consensus Statement from the Fleischner Society. Radiology, 296(1), 172-180. doi:10.1148/radiol.2020201365
25. Abbas, A., Abdelsamea, M. M., & Gaber, M. M. (2020). Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network. doi:10.1101/2020.03.30.20047456
26. Abbas, A., Abdelsamea, M. M., & Gaber, M. M. (2020). Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network. doi:10.1101/2020.03.30.20047456
27. Rahman, T. (2021, March 06). COVID-19 Radiography Database. Retrieved from https://www.kaggle.com/tawsifurrahman/covid19-radiography-databas
28. Rahman, T. (2021, March 06). COVID-19 Radiography Database. Retrieved from https://www.kaggle.com/tawsifurrahman/covid19-radiography-databas
29. Rahimzadeh, M., & Attar, A. (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, 100360. doi:10.1016/j.imu.2020.100360
30. Rahimzadeh, M., & Attar, A. (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, 100360. doi:10.1016/j.imu.2020.100360
31. Ardakani, A. A., Kanafi, A. R., Acharya, U. R., Khadem, N., & Mohammadi, A. (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, 103795. doi:10.1016/j.compbiomed.2020.103795
32. Ardakani, A. A., Kanafi, A. R., Acharya, U. R., Khadem, N., & Mohammadi, A. (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, 103795. doi:10.1016/j.compbiomed.2020.103795
33. Hassantabar, S., Ahmadi, M., & Sharifi, A. (2020). Diagnosis and detection of infected tissue of COVID-19 patients based on lung x-ray image using convolutional neural network approaches. Chaos, Solitons & Fractals, 140, 110170. doi:10.1016/j.chaos.2020.110170
34. Hassantabar, S., Ahmadi, M., & Sharifi, A. (2020). Diagnosis and detection of infected tissue of COVID-19 patients based on lung x-ray image using convolutional neural network approaches. Chaos, Solitons & Fractals, 140, 110170. doi:10.1016/j.chaos.2020.110170
35. Jain, R., Gupta, M., Taneja, S., & Hemanth, D. J. (2020). Deep learning based detection and analysis of COVID-19 on chest X-ray images. Applied Intelligence, 51(3), 1690-1700. doi:10.1007/s10489-020-01902-1
36. Jain, R., Gupta, M., Taneja, S., & Hemanth, D. J. (2020). Deep learning based detection and analysis of COVID-19 on chest X-ray images. Applied Intelligence, 51(3), 1690-1700. doi:10.1007/s10489-020-01902-1
37. Pereira, R. M., Bertolini, D., Teixeira, L. O., Silla, C. N., & Costa, Y. M. (2020). COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios. Computer Methods and Programs in Biomedicine, 194, 105532. doi:10.1016/j.cmpb.2020.105532
38. Pereira, R. M., Bertolini, D., Teixeira, L. O., Silla, C. N., & Costa, Y. M. (2020). COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios. Computer Methods and Programs in Biomedicine, 194, 105532. doi:10.1016/j.cmpb.2020.105532
39. Feki, I., Ammar, S., Kessentini, Y., & Muhammad, K. (2021). Federated learning for COVID-19 screening from Chest X-ray images. Applied Soft Computing, 106, 107330. doi:10.1016/j.asoc.2021.107330
40. Feki, I., Ammar, S., Kessentini, Y., & Muhammad, K. (2021). Federated learning for COVID-19 screening from Chest X-ray images. Applied Soft Computing, 106, 107330. doi:10.1016/j.asoc.2021.107330
41. Benmalek, E., Elmhamdi, J., & Jilbab, A. (2021). Comparing CT scan and chest X-ray imaging for COVID-19 diagnosis. Biomedical Engineering Advances, 1, 100003. doi:10.1016/j.bea.2021.100003
42. Benmalek, E., Elmhamdi, J., & Jilbab, A. (2021). Comparing CT scan and chest X-ray imaging for COVID-19 diagnosis. Biomedical Engineering Advances, 1, 100003. doi:10.1016/j.bea.2021.100003
43. Ouchicha, C., Ammor, O., & Meknassi, M. (2020). CVDNet: A novel deep learning architecture for detection of coronavirus (Covid-19) from chest x-ray images. Chaos, Solitons & Fractals, 140, 110245. doi:10.1016/j.chaos.2020.110245
44. Ouchicha, C., Ammor, O., & Meknassi, M. (2020). CVDNet: A novel deep learning architecture for detection of coronavirus (Covid-19) from chest x-ray images. Chaos, Solitons & Fractals, 140, 110245. doi:10.1016/j.chaos.2020.110245
45. Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., & Liu, C. (2018). A Survey on Deep Transfer Learning. ICANN.
46. Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., & Liu, C. (2018). A Survey on Deep Transfer Learning. ICANN.
47. Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2021). A Comprehensive Survey on Transfer Learning. Proceedings of the IEEE, 109, 43-76.
48. Zhuang, F., Qi, Z., Duan, K., Xi, D., Zhu, Y., Zhu, H., Xiong, H., & He, Q. (2021). A Comprehensive Survey on Transfer Learning. Proceedings of the IEEE, 109, 43-76.
49. Ankile, L.H., Heggland, M.F., Krange, K. (2020). Deep Convolutional Neural Networks: A survey of the foundations, selected improvements, and some current applications. arXiv:2011.12960
50. Ankile, L.H., Heggland, M.F., Krange, K. (2020). Deep Convolutional Neural Networks: A survey of the foundations, selected improvements, and some current applications. arXiv:2011.12960
51. Arora, D., Garg, M., & Gupta, M. (2020). Diving deep in Deep Convolutional Neural Network. 2020 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN). doi:10.1109/icacccn51052.2020.9362907
52. Arora, D., Garg, M., & Gupta, M. (2020). Diving deep in Deep Convolutional Neural Network. 2020 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN). doi:10.1109/icacccn51052.2020.9362907
53. Aloysius, N., & Geetha, M. (2017). A review on deep convolutional neural networks. 2017 International Conference on Communication and Signal Processing (ICCSP), 0588-0592.
54. Aloysius, N., & Geetha, M. (2017). A review on deep convolutional neural networks. 2017 International Conference on Communication and Signal Processing (ICCSP), 0588-0592.
55. Gulcu, A., & Kus, Z. (2020). Hyper-Parameter Selection in Convolutional Neural Networks Using Microcanonical Optimization Algorithm. IEEE Access, 8, 52528-52540. doi:10.1109/access.2020.2981141
56. Gulcu, A., & Kus, Z. (2020). Hyper-Parameter Selection in Convolutional Neural Networks Using Microcanonical Optimization Algorithm. IEEE Access, 8, 52528-52540. doi:10.1109/access.2020.2981141
57. BIMCV. (n.d.). Retrieved from https://bimcv.cipf.es/bimcv-projects/bimcv-covid19/#1590858128006-9e640421-6711
58. BIMCV. (n.d.). Retrieved from https://bimcv.cipf.es/bimcv-projects/bimcv-covid19/#1590858128006-9e640421-6711
59. Ml-Workgroup. (n.d.). Ml-workgroup/covid-19-image-repository. Retrieved from https://github.com/ml-workgroup/covid-19-image-repository/tree/master/png
60. Ml-Workgroup. (n.d.). Ml-workgroup/covid-19-image-repository. Retrieved from https://github.com/ml-workgroup/covid-19-image-repository/tree/master/png
61. Redazione. (2021, May 20). COVID-19 DATABASE. Retrieved from https://www.sirm.org/category/senza-categoria/covid-19/
62. Redazione. (2021, May 20). COVID-19 DATABASE. Retrieved from https://www.sirm.org/category/senza-categoria/covid-19/
63. Eurorad.org. (n.d.). Retrieved from https://www.eurorad.org/advanced-search?filter[0]=section:40
64. Eurorad.org. (n.d.). Retrieved from https://www.eurorad.org/advanced-search?filter[0]=section:40
65. Ieee8023. (n.d.). Ieee8023/covid-chestxray-dataset. Retrieved from https://github.com/ieee8023/covid-chestxray-dataset
66. Ieee8023. (n.d.). Ieee8023/covid-chestxray-dataset. Retrieved from https://github.com/ieee8023/covid-chestxray-dataset
67. Haghanifar, A., Majdabadi, M. M., & Ko, S. (2021, May 20). COVID-19 Chest X-Ray Image Repository. Retrieved from https://figshare.com/articles/dataset/COVID-19_Chest_X-Ray_Image_Repository/12580328
68. Haghanifar, A., Majdabadi, M. M., & Ko, S. (2021, May 20). COVID-19 Chest X-Ray Image Repository. Retrieved from https://figshare.com/articles/dataset/COVID-19_Chest_X-Ray_Image_Repository/12580328
69. Armiro. (n.d.). Armiro/COVID-CXNet. Retrieved from https://github.com/armiro/COVID-CXNet
70. Armiro. (n.d.). Armiro/COVID-CXNet. Retrieved from https://github.com/armiro/COVID-CXNet
71. RSNA Pneumonia Detection Challenge. (n.d.). Retrieved from https://www.kaggle.com/c/rsna-pneumonia-detection-challenge/data
72. RSNA Pneumonia Detection Challenge. (n.d.). Retrieved from https://www.kaggle.com/c/rsna-pneumonia-detection-challenge/data
73. Mooney, P. (2018, March 24). Chest X-Ray Images (Pneumonia). Retrieved from https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
74. Mooney, P. (2018, March 24). Chest X-Ray Images (Pneumonia). Retrieved from https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia
75. Huang, G., Liu, Z., Maaten, L. V., & Weinberger, K. Q. (2017). Densely Connected Convolutional Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr.2017.243
76. Huang, G., Liu, Z., Maaten, L. V., & Weinberger, K. Q. (2017). Densely Connected Convolutional Networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr.2017.243
77. Wang, S., & Zhang, Y. (2020). DenseNet-201-Based Deep Neural Network with Composite Learning Factor and Precomputation for Multiple Sclerosis Classification. ACM Transactions on Multimedia Computing, Communications, and Applications, 16(2s), 1-19. doi:10.1145/3341095
78. Wang, S., & Zhang, Y. (2020). DenseNet-201-Based Deep Neural Network with Composite Learning Factor and Precomputation for Multiple Sclerosis Classification. ACM Transactions on Multimedia Computing, Communications, and Applications, 16(2s), 1-19. doi:10.1145/3341095
79. Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr.2017.195
80. Chollet, F. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). doi:10.1109/cvpr.2017.195
81. Rismiyati, Endah, S. N., Khadijah, & Shiddiq, I. N. (2020). Xception Architecture Transfer Learning for Garbage Classification. 2020 4th International Conference on Informatics and Computational Sciences (ICICoS). doi:10.1109/icicos51170.2020.9299017
82. Rismiyati, Endah, S. N., Khadijah, & Shiddiq, I. N. (2020). Xception Architecture Transfer Learning for Garbage Classification. 2020 4th International Conference on Informatics and Computational Sciences (ICICoS). doi:10.1109/icicos51170.2020.9299017
83. Wu, X., Liu, R., Yang, H., & Chen, Z. (2020). An Xception Based Convolutional Neural Network for Scene Image Classification with Transfer Learning. 2020 2nd International Conference on Information Technology and Computer Application (ITCA). doi:10.1109/itca52113.2020.00063
84. Wu, X., Liu, R., Yang, H., & Chen, Z. (2020). An Xception Based Convolutional Neural Network for Scene Image Classification with Transfer Learning. 2020 2nd International Conference on Information Technology and Computer Application (ITCA). doi:10.1109/itca52113.2020.00063
85. Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11231
86. Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017). Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11231
87. Konig, J., Jenkins, M. D., Barrie, P., Mannion, M., & Morison, G. (2019). A Convolutional Neural Network for Pavement Surface Crack Segmentation Using Residual Connections and Attention Gating. 2019 IEEE International Conference on Image Processing (ICIP). doi:10.1109/icip.2019.8803060
88. Konig, J., Jenkins, M. D., Barrie, P., Mannion, M., & Morison, G. (2019). A Convolutional Neural Network for Pavement Surface Crack Segmentation Using Residual Connections and Attention Gating. 2019 IEEE International Conference on Image Processing (ICIP). doi:10.1109/icip.2019.8803060
89. Goodfellow, I., Bengio, Y., & Courville, A. (2017). Deep learning. Cambridge, MA: The MIT Pr
90. Goodfellow, I., Bengio, Y., & Courville, A. (2017). Deep learning. Cambridge, MA: The MIT Pr
91. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. doi:10.1109/cvpr.2018.0047
92. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. doi:10.1109/cvpr.2018.0047
93. Ganaie, m. A., Hu, M., Tanveer, M., Suganthan, P. N., (2021). Ensemble deep learning: A review. https://arxiv.org/abs/2104.02395
94. Ganaie, m. A., Hu, M., Tanveer, M., Suganthan, P. N., (2021). Ensemble deep learning: A review. https://arxiv.org/abs/2104.02395
95. Yang, Y., Lv, H., Chen, N., Wu, Y., Zheng, J., & Zheng, Z. (2021). Local minima found in the subparameter space can be effective for ensembles of deep convolutional neural networks. Pattern Recognition, 109, 107582. doi:10.1016/j.patcog.2020.107582
96. Yang, Y., Lv, H., Chen, N., Wu, Y., Zheng, J., & Zheng, Z. (2021). Local minima found in the subparameter space can be effective for ensembles of deep convolutional neural networks. Pattern Recognition, 109, 107582. doi:10.1016/j.patcog.2020.107582