Diagnosis of the Stage of COVID-19 Disease from CT Scan Images of the Lung by Using a Swin Transformer
Subject Areas : International Journal of Smart Electrical EngineeringAmir Mohammad Hamedani 1 , Mahsa Akhbari 2 * , Parisa Gifani 3
1 - Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 - Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
3 - MRC London Institute of Medical Sciences, Imperial College London, London, England
Keywords: COVID-19, Lung CT scan, Swin transform, Stages of disease, Diagnosis,
Abstract :
COVID-19 is an infectious disease that emerged in China in 2019 and became a global pandemic. To contain the virus, governments adopted the strategy of testing, tracing, and isolating the infected people. This strategy required two steps: first, to detect the COVID-19 cases, and second, to assess the disease severity (which was vital for treatment). Various diagnostic methods were applied, but the most reliable one was analyzing the lung computed tomography (CT) images of the suspected cases. However, some radiologists lacked the experience with the new patterns and the high volume of patients increased the error rate. Therefore, an automated diagnosis system was needed. In this paper, we propose a system that uses the Swin transformer, a vision transformer model, to identify the disease severity of COVID-19. The system can distinguish between normal and abnormal lungs and categorize the disease severity to assist the doctor in treating the patient. We fine-tuned the pre-trained Swin Transformer network on our private dataset. We achieved 97% accuracy on our test dataset. Our dataset consisted of five classes (lung CT scan), including one normal class and four classes with different levels of involvement: (1) early stage, (2) progressive stage, (3) peak stage, and (4) absorption stage.
References
1. Ciotti, M., et al., The COVID-19 pandemic. Critical reviews in clinical laboratory sciences, 2020. 57(6): p. 365-388.
2. Alimohamadi, Y., et al., Determine the most common clinical symptoms in COVID-19 patients: a systematic review and meta-analysis. Journal of preventive medicine and hygiene, 2020. 61(3): p. E304.
3. Elibol, E., Otolaryngological symptoms in COVID-19. European Archives of Oto-Rhino-Laryngology, 2021. 278(4): p. 1233-1236.
4. Czubak, J., et al., Comparison of the clinical differences between COVID-19, SARS, influenza, and the common cold: A systematic literature review. Advances in Clinical and Experimental Medicine, 2021. 30(1): p. 109-114.
5. Mortazavi, H., et al., SARS-CoV-2 droplet deposition path and its effects on the human upper airway in the oral inhalation. Computer Methods and Programs in Biomedicine, 2021. 200: p. 105843.
6. Birman, D., Investigation of the Effects of Covid-19 on Different Organs of the Body. Eurasian Journal of Chemical, Medicinal and Petroleum Research, 2023. 2(1): p. 24-36.
7. Kollias, D., et al. Mia-cov19d: Covid-19 detection through 3-d chest ct image analysis. in Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021.
8. Khehrah, N., et al., Lung nodule detection in CT images using statistical and shape-based features. Journal of Imaging, 2020. 6(2): p. 6.
9. LeCun, Y., Y. Bengio, and G. Hinton, Deep learning. nature, 2015. 521(7553): p. 436-444.
10. Vaswani, A., et al., Attention is all you need. Advances in neural information processing systems 30 (NIPS 2017), 2017.
11. Dosovitskiy, A., et al., An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
12. Liu, Z., et al. Swin transformer: Hierarchical vision transformer using shifted windows. in Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021.
13. Dümen, S., et al., Performance of vision transformer and swin transformer models for lemon quality classification in fruit juice factories. European Food Research and Technology, 2024: p. 1-12.
14. Zhang, L. and Y. Wen. A transformer-based framework for automatic COVID19 diagnosis in chest CTs. in Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021.
15. Jiang, J. and S. Lin, Covid-19 detection in chest x-ray images using swin-transformer and transformer in transformer. arXiv preprint arXiv:2110.08427, 2021.
16. Chen, G.-L., C.-C. Hsu, and M.-H. Wu. Adaptive distribution learning with statistical hypothesis testing for COVID-19 CT scan classification. in Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021.
17. Jamali, A. and M. Mahdianpari, Swin Transformer and Deep Convolutional Neural Networks for Coastal Wetland Classification Using Sentinel-1, Sentinel-2, and LiDAR Data. Remote Sensing, 2022. 14(2): p. 359.
18. Tummala, S., J. Kim, and S. Kadry, BreaST-Net: Multi-Class Classification of Breast Cancer from Histopathological Images Using Ensemble of Swin Transformers. Mathematics, 2022. 10(21): p. 4109.
19. Remy-Jardin, M., et al., Computed tomography assessment of ground-glass opacity: semiology and significance. Journal of thoracic imaging, 1993. 8(4): p. 249-264.
20. Kunal, S., et al., “Crazy-paving” pattern: a characteristic presentation of pulmonary alveolar proteinosis and a review of the literature from India. Lung India: Official Organ of Indian Chest Society, 2016. 33(3): p. 335.
21. Lee, K.S., et al., Consolidation. Radiology Illustrated: Chest Radiology, 2014: p. 33-47.
22. Gifani, P., et al., Automatic diagnosis of stage of COVID-19 patients using an ensemble of transfer learning with convolutional neural networks based on computed tomography images. Journal of Medical Signals & Sensors, 2023. 13(2): p. 101-109.
23. Xu, Z., et al., Efficient transformer for remote sensing image segmentation. Remote Sensing, 2021. 13(18): p. 3585.
24. Shaw, P., J. Uszkoreit, and A. Vaswani, Self-attention with relative position representations. arXiv preprint arXiv:1803.02155, 2018.
25. Peng, L., et al., Analysis of CT scan images for COVID-19 pneumonia based on a deep ensemble framework with DenseNet, Swin transformer, and RegNet. Frontiers in microbiology, 2022. 13: p. 995323.
26. Grandini, M., E. Bagli, and G. Visani, Metrics for multi-class classification: an overview. arXiv preprint arXiv:2008.05756, 2020.
27. Shaha, M. and M. Pawar. Transfer learning for image classification. in 2018 second international conference on electronics, communication and aerospace technology (ICECA). 2018. IEEE.