Medical image segmentation method based on self-attention and multi-view attention.
10.7507/1001-5515.202408007
- Author:
Dan PAN
1
;
Jin LYU
1
;
An ZENG
2
Author Information
1. School of Electronics and Information Engineering, Guangdong University of Technology and Education, Guangzhou 510450, P. R. China.
2. School of Computers, Guangdong University of Technology, Guangzhou 510006, P. R. China.
- Publication Type:Journal Article
- Keywords:
Convolutional neural network;
Medical image segmentation;
Multi-view attention;
Self-attention;
Transformer
- MeSH:
Humans;
Image Processing, Computer-Assisted/methods*;
Neural Networks, Computer;
Algorithms;
Attention;
Coronary Vessels/diagnostic imaging*;
Diagnostic Imaging/methods*
- From:
Journal of Biomedical Engineering
2025;42(5):919-927
- CountryChina
- Language:Chinese
-
Abstract:
Most current medical image segmentation models are primarily built upon the U-shaped network (U-Net) architecture, which has certain limitations in capturing both global contextual information and fine-grained details. To address this issue, this paper proposes a novel U-shaped network model, termed the Multi-View U-Net (MUNet), which integrates self-attention and multi-view attention mechanisms. Specifically, a newly designed multi-view attention module is introduced to aggregate semantic features from different perspectives, thereby enhancing the representation of fine details in images. Additionally, the MUNet model leverages a self-attention encoding block to extract global image features, and by fusing global and local features, it improves segmentation performance. Experimental results demonstrate that the proposed model achieves superior segmentation performance in coronary artery image segmentation tasks, significantly outperforming existing models. By incorporating self-attention and multi-view attention mechanisms, this study provides a novel and efficient modeling approach for medical image segmentation, contributing to the advancement of intelligent medical image analysis.
