DECOR-NET: A COVID-19 Lung Infection Segmentation Network Improved by Emphasizing Low-level Features and Decorrelating Features
This work addresses the need for accurate segmentation of COVID-19 infections in medical imaging to aid diagnosis and tracking, but it is incremental as it builds on existing segmentation networks with specific enhancements.
The authors tackled the problem of segmenting COVID-19 lung infections in CT scans, which is challenging due to high heterogeneity and unclear boundaries, and their DECOR-NET method achieved improvements of 5.1% in Dice coefficient and 4.9% in intersection over union over the baseline.
Since 2019, coronavirus Disease 2019 (COVID-19) has been widely spread and posed a serious threat to public health. Chest Computed Tomography (CT) holds great potential for screening and diagnosis of this disease. The segmentation of COVID-19 CT imaging can achieves quantitative evaluation of infections and tracks 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, segmentation networks that emphasize low-level features are still lacking. In this work, we propose a DECOR-Net capable of capturing more decorrelated low-level features. The channel re-weighting strategy is applied to obtain plenty of 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 5.1% and 4.9% in terms of Dice coefficient and intersection over union. Moreover, the proposed decorrelation loss can improve the performance constantly under different settings. The Code is available at https://github.com/jiesihu/DECOR-Net.git.