STM-UNet: An Efficient U-shaped Architecture Based on Swin Transformer and Multi-scale MLP for Medical Image Segmentation

TL;DR

This paper introduces STM-UNet, a novel U-shaped architecture combining Swin Transformer and multi-scale MLP, which improves global feature modeling and segmentation accuracy in medical images while maintaining low complexity.

Contribution

The paper proposes a new U-shaped architecture integrating Swin Transformer and a novel PCAS-MLP for enhanced multi-scale feature extraction and segmentation performance.

Findings

Outperforms state-of-the-art methods in IoU and Dice scores.

Demonstrates effective global feature modeling with Swin Transformer.

Achieves a good balance between accuracy and model complexity.

Abstract

Automated medical image segmentation can assist doctors to diagnose faster and more accurate. Deep learning based models for medical image segmentation have made great progress in recent years. However, the existing models fail to effectively leverage Transformer and MLP for improving U-shaped architecture efficiently. In addition, the multi-scale features of the MLP have not been fully extracted in the bottleneck of U-shaped architecture. In this paper, we propose an efficient U-shaped architecture based on Swin Transformer and multi-scale MLP, namely STM-UNet. Specifically, the Swin Transformer block is added to skip connection of STM-UNet in form of residual connection, which can enhance the modeling ability of global features and long-range dependency. Meanwhile, a novel PCAS-MLP with parallel convolution module is designed and placed into the bottleneck of our architecture to contribute to the improvement of segmentation performance. The experimental results on ISIC 2016 and ISIC 2018 demonstrate the effectiveness of our proposed method. Our method also outperforms several state-of-the-art methods in terms of IoU and Dice. Our method has achieved a better trade-off between high segmentation accuracy and low model complexity.