The novel coronavirus disease 2019 (COVID-19) has emerged as an enormous challenge facing China today. Preventive Medicine physicians and Artificial Intelligence (AI) researchers try to improve the ability to early automatic warning of coronavirus infections, promote epidemic prevention, and reduce medical costs using deep learning methods. In this work, we build an extensive database of chest computed tomography (CT) scans with image data from domestic and international open-source medical datasets. Swin Transformer is chosen as the backbone network to establish a model (STCovidNet) for the prediction of COVID-19. We then compare the performance of our technique against that of Vision Transformer (ViT) and Convolutional Neural Network (CNN). Next, to visualize our model's high-dimensional outputs in 2-dimensional space, we apply t-distributed stochastic neighbor embedding (t-SNE) as the dimension-reduction strategy. Finally, we employ gradient-weighted class activation mapping (Grad-CAM) to present a class activation map. The results indicate that STCovidNet’s performance surpasses ViT and CNN with a 0.9811 AUC and 0.9858 accuracy score. Our network outperforms previous techniques to reduce intra-class variability and generate well-separated feature embedding. The CAM figure illustrates that the decision region corresponds to radiologists' detecting spots. The suggested method can be an effective way of catching COVID-19 instances.
The rapid evolution of coronaviruses in respiratory diseases, including severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), poses a significant challenge for deep learning models to accurately detect and adapt to new strains. To address this challenge, we propose a novel Continuous Learning approach, CoroTrans-CL, for the diagnosis and prevention of various coronavirus infections that cause severe respiratory diseases using chest radiography images. Our approach is based on the Swin Transformer architecture and uses a combination of the Elastic Weight Consolidation (EWC) and Herding Selection Replay (HSR) methods to mitigate the problem of catastrophic forgetting. We constructed an informative benchmark dataset containing multiple strains of coronaviruses and present the proposed approach in five successive learning stages representing the epidemic timeline of different coronaviruses (SARS, MERS, wild-type SARS-CoV-2, and the Omicron and Delta variants of SARS-CoV-2) in the real world. Our experiments showed that the proposed CoroTrans-CL model achieved a joint training accuracy of 95.34%, an F1 score of 92%, and an average accuracy of 83.40% while maintaining a balance between plasticity and stability. Our study demonstrates that CoroTrans-CL can accurately diagnose and detect the changes caused by new mutant viral strains in the lungs without forgetting existing strains, and it provides an effective solution for the ongoing diagnosis of mutant SARS-CoV-2 virus infections.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.