Cov-TransNet: Dual branch fusion network with transformer for COVID-19 infection segmentation. (February 2023)

• Record Type: Journal Article
• Authors: Peng, Yanjun; Zhang, Tong; Guo, Yanfei
• Is Part Of: Biomedical signal processing and control. Volume 80:Part 2(2023)
• Publication Date: 2023-02
• Subjects: COVID-19 -- Deep learning -- Transformer -- Semantic segmentation -- Attention mechanism -- CT images; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104366
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: Segmentation of COVID-19 infection is a challenging task due to the blurred boundaries and low contrast between the infected and the non-infected areas in COVID-19 CT images, especially for small infection regions. COV-TransNet is presented to achieve high-precision segmentation of COVID-19 infection regions in this paper. The proposed segmentation network is composed of the auxiliary branch and the backbone branch. The auxiliary branch network adopts transformer to provide global information, helping the convolution layers in backbone branch to learn specific local features better. A multi-scale feature attention module is introduced to capture contextual information and adaptively enhance feature representations. Specially, a high internal resolution is maintained during the attention calculation process. Moreover, feature activation module can effectively reduce the loss of valid information during sampling. The proposed network can take full advantage of different depth and multi-scale features to achieve high sensitivity for identifying lesions of varied sizes and locations. We experiment on several datasets of the COVID-19 lesion segmentation task, including COVID-19-CT-Seg, UESTC-COVID-19, MosMedData and COVID-19-MedSeg. Comprehensive results demonstrate that COV-TransNet outperforms the existing state-of-the-art segmentation methods and achieves better segmentation performance for multi-scale lesions. Highlights: A network with a transformer branch for COVID-19 infection region segmentation. The FAM module can enhance relevant features while suppressing irrelevant features. The MsA mechanism is designed to capture the various scales of features. Four datasets are used to validate the generalization ability of the proposed model. Outperforms the existing binary segmentation methods of COVID-19 infection region.