# DECOR-NET: A COVID-19 Lung Infection Segmentation Network Improved by Emphasizing Low-level Features and Decorrelating Features

## TL;DR

DECOR-Net is a novel segmentation network that emphasizes low-level features and reduces feature correlation, leading to improved COVID-19 lung infection segmentation accuracy in CT images.

## Contribution

The paper introduces DECOR-Net, which captures decorrelated low-level features and applies a decorrelation loss, enhancing segmentation performance over existing methods.

## Key findings

- DECOR-Net outperforms state-of-the-art methods in Dice coefficient and IoU.
- Decorrelating features improves segmentation accuracy.
- The decorrelation loss consistently enhances performance across different settings.

## Abstract

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.