TRANSFORMER BASED COVID-19 DETECTION USING CHEST X-RAYS
Affiliation:
1. KAHRAMANMARAŞ SÜTÇÜ İMAM ÜNİVERSİTESİ, MÜHENDİSLİK-MİMARLIK FAKÜLTESİ
Abstract
Covid-19 has affected millions globally, leading to substantial illness and mortality. Chest X-rays serve as a rapid and effective means of tracking the progression of Covid-19. However, diagnosing Covid-19 from a chest X-ray can be complex, and even skilled radiologists may not always provide a conclusive diagnosis. In our research, we utilized a dataset comprising X-ray images of Covid-19, lung opacity, viral pneumonia, and healthy patients to assess the efficacy of various vision transformer-based models. A modified version of the Swin Transformer achieved an accuracy of 98.9% and a precision of 99.2% on Covid-19 images in a four-way classification task. Our findings are competitive with cutting-edge techniques for diagnosing Covid-19. This method could aid healthcare professionals in screening patients for Covid-19, thereby enabling quicker treatment and improved health outcomes for those affected by the virus.
Publisher
Kahramanmaras Sutcu Imam University Journal of Engineering Sciences
Reference19 articles.
1. Apostolopoulos, I. D. & Mpesiana, T. A. (2020). COVID-19: Automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. Physical and Engineering Sciences in Medicine, 43(2), 635-640. 2. Chetoui, M., & Akhlouf, M. A. (2022). Explainable vision transformers and radiomics for covid-19 detection in chest x-rays. J. Clin. Med. 11, 3013. 3. Chowdhury, M.E., Rahman, T., Khandakar, A., Mazhar, R., Kadir, M.A., Mahbub, Z.B., Islam, K.R., Khan, M.S., Iqbal, A., Emadi, N.A., et al. (2020). Can AI help in screening viral and covid-19 pneumonia? https://arxiv.org/abs/2003.13145. 4. Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. https://arxiv.org/abs/2010.11929. 5. Gorbalenya, A. E., Baker, S. C., Baric, R. S., De Groot, R. J., Drosten, C., Gulyaeva, A. A & Ziebuhr, J. (2020). The species severe acute respiratory syndrome-related coronavirus: Classifying 2019-nCoV and naming it SARS-CoV-2. Nat Microbiol; 5, 536–44.
|
|