DECOR-Net: A Covid-19 Lung Infection Segmentation Network Improved by Emphasizing Low-Level Features and Decorrelating Features

• Published in: 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI) pp. 1 - 5
• Main Authors: Hu, Jiesi, Yang, Yanwu, Guo, Xutao, Peng, Bo, Huang, Hua, Ma, Ting
• Format: Conference Proceeding
• Language: English
• Published: IEEE 18.04.2023
• Subjects: Biological system modeling; CNN; Computed tomography; COVID-19; Decorrelation; Image segmentation; Infection segmentation; Low-level feature; Lung; Redundancy
• ISSN: 1945-8452
• DOI: 10.1109/ISBI53787.2023.10230325

Since 2019, coronavirus Disease 2019 (COVID-19) has been widely spread and seriously threatened public health. Chest Computed Tomography (CT) holds great potential for screening and diagnosis of this disease. The segmentation of COVID-19 CT imaging can achieve a quantitative evaluation of infections and track disease progression. COVID-19 infections are characterized by high heterogeneity and unclear boundaries, so capturing low-level features such as texture and intensity is critical for segmentation. However, most existing segmentation models potentially overlook this feature. In this work, we propose a DECOR-Net capable of perceiving more diverse low-level features. The channel re-weighting strategy is applied to balance high-level and low-level features and the dependencies between channels are reduced by proposed decorrelation loss. Experiments show that DECOR-Net outperforms other cutting-edge methods and surpasses the baseline by 4.8% and 4.7% in terms of Dice coefficient and intersection over union. Moreover, the proposed decorrelation loss can constantly improve performance under different settings. The Code is available at https://github.com/jiesihu/DECOR-Net.git.