CGS‐Net: A classification‐guided framework for automated infection segmentation of COVID‐19 from CT images

Abstract

Automated segmentation of lung lesions in CT images of COVID‐19 based on deep learning holds great potential for comprehending the advancement of the disease and establishing suitable treatment approaches. However, the complex background, indistinct boundaries, varying sizes and distributions of infected regions, and high similarity to other lung diseases pose substantial challenges. To address these issues, we propose a joint deep learning‐based framework, named Classification‐Guided Segmentation Network (CGS‐Net), for COVID‐19 segmentation. The framework comprises a classification and a segmentation sub‐network, which are trained sequentially. Initially, the classification sub‐network learns the feature information of COVID‐19 and other pneumonia classifications. Subsequently, the trained classification sub‐network assists in the training of the segmentation sub‐network. In addition, several key modules are employed to construct the network, including the Multi‐scale Feature Mapping Module (MSFM), the Context Information Module (Context), and the Axial Attention Fusion Module (AAFM). The MSFM employs dilated convolutions to extract multi‐scale features with an emphasis on spatial and channel information. The Context combines strip pooling and average pooling to aggregate contextual and global information. Finally, the AAFM is employed to incorporate contextual information through an axial attention mechanism. Extensive experimental results demonstrate that our proposed method outperforms competing approaches in the segmentation task.