Decor-Net: A Covid-19 Lung Infection Segmentation Network Improved By Emphasizing Low-Level Features And Decorrelating Features

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.