CSSWin-UNet: A Transformer UNet Combined with Patch-Based and Cross-Shaped Windows for Medical Image Segmentation
Open Access
- 17 October 2025
- journal article
- Published by Angus Academic Press in Advances in Computer and Materials Scienc Research
- Vol. 4 (1) , 61-68
Abstract
In medical image segmentation, both Convolutional Neural Networks (CNNs) and self-attention mechanisms have shown success but also have limitations. CNNs excel at capturing local features but struggle with long-range dependencies, while self-attention effectively models global context but is computationally intensive and may lose fine local details. To address these challenges, we propose CSSWin-UNet, a novel U-shaped architecture that integrates two complementary self-attention mechanisms(Swin and CSWin Transformer) to achieve a balanced representation of both local features and global dependencies, while substantially reducing computational overhead. Experimental results on multiple public benchmark datasets demonstrate that CSSWin-UNet delivers superior segmentation performance with significantly lower model complexity, highlighting its potential for practical deployment in medical imaging tasks.Keywords
This publication has 13 references indexed in Scilit:
- CSWin-UNet: Transformer UNet with cross-shaped windows for medical image segmentationInformation Fusion, 2024
- TransDeepLab: Convolution-Free Transformer-Based DeepLab v3+ for Medical Image Segmentation2022
- Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images2022
- TransFuse: Fusing Transformers and CNNs for Medical Image Segmentation2021
- nnU-Net: a self-configuring method for deep learning-based biomedical image segmentationNature Methods, 2020
- Domain Adaptive Relational Reasoning for 3D Multi-organ Segmentation2020
- ResUNet-a: A deep learning framework for semantic segmentation of remotely sensed dataISPRS Journal of Photogrammetry and Remote Sensing, 2020
- Skin lesion classification using ensembles of multi-resolution EfficientNets with meta dataMethodsX, 2020
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015