Dynamic feature learning for COVID-19 segmentation and classification

Citations of this article
Mendeley users who have this article in their library.

Your institution provides access to this article.


Since December 2019, coronavirus SARS-CoV-2 (COVID-19) has rapidly developed into a global epidemic, with millions of patients affected worldwide. As part of the diagnostic pathway, computed tomography (CT) scans are used to help patient management. However, parenchymal imaging findings in COVID-19 are non-specific and can be seen in other diseases. In this work, we propose to first segment lesions from CT images, and further, classify COVID-19 patients from healthy persons and common pneumonia patients. In detail, a novel Dynamic Fusion Segmentation Network (DFSN) that automatically segments infection-related pixels is first proposed. Within this network, low-level features are aggregated to high-level ones to effectively capture context characteristics of infection regions, and high-level features are dynamically fused to model multi-scale semantic information of lesions. Based on DFSN, Dynamic Transfer-learning Classification Network (DTCN) is proposed to distinguish COVID-19 patients. Within DTCN, a pre-trained DFSN is transferred and used as the backbone to extract pixel-level information. Then the pixel-level information is dynamically selected and used to make a diagnosis. In this way, the pre-trained DFSN is utilized through transfer learning, and clinical significance of segmentation results is comprehensively considered. Thus DTCN becomes more sensitive to typical signs of COVID-19. Extensive experiments are conducted to demonstrate effectiveness of the proposed DFSN and DTCN frameworks. The corresponding results indicate that these two models achieve state-of-the-art performance in terms of segmentation and classification.




Zhang, X., Jiang, R., Huang, P., Wang, T., Hu, M., Scarsbrook, A. F., & Frangi, A. F. (2022). Dynamic feature learning for COVID-19 segmentation and classification. Computers in Biology and Medicine, 150. https://doi.org/10.1016/j.compbiomed.2022.106136

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free