MS-DCANet: A Novel Segmentation Network For Multi-Modality COVID-19 Medical Images

TL;DR

MS-DCANet is a new segmentation network designed for COVID-19 medical images that balances accuracy, complexity, and speed by integrating novel attention mechanisms and multi-scale features.

Contribution

The paper introduces MS-DCANet with a Tokenized MLP block and dual channel modules for improved lesion boundary detection and small target recognition.

Findings

Achieved state-of-the-art performance on COVID-19 segmentation tasks

Demonstrated strong generalization on ISIC 2018 and BAA datasets

Balanced accuracy with computational efficiency

Abstract

The Coronavirus Disease 2019 (COVID-19) pandemic has increased the public health burden and brought profound disaster to humans. For the particularity of the COVID-19 medical images with blurred boundaries, low contrast and different infection sites, some researchers have improved the accuracy by adding more complexity. Also, they overlook the complexity of lesions, which hinder their ability to capture the relationship between segmentation sites and the background, as well as the edge contours and global context. However, increasing the computational complexity, parameters and inference speed is unfavorable for model transfer from laboratory to clinic. A perfect segmentation network needs to balance the above three factors completely. To solve the above issues, this paper propose a symmetric automatic segmentation framework named MS-DCANet. We introduce Tokenized MLP block, a novel attention scheme that use a shift-window mechanism to conditionally fuse local and global features to get more continuous boundaries and spatial positioning capabilities. It has greater understanding of irregular lesions contours. MS-DCANet also uses several Dual Channel blocks and a Res-ASPP block to improve the ability to recognize small targets. On multi-modality COVID-19 tasks, MS-DCANet achieved state-of-the-art performance compared with other baselines. It can well trade off the accuracy and complexity. To prove the strong generalization ability of our proposed model, we apply it to other tasks (ISIC 2018 and BAA) and achieve satisfactory results.