English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automated medical image segmentation can assist doctors to diagnose fasterand more accurate. Deep learning based models for medical image segmentationhave made great progress in recent years. However, the existing models fail toeffectively leverage Transformer and MLP for improving U-shaped architectureefficiently. In addition, the multi-scale features of the MLP have not beenfully extracted in the bottleneck of U-shaped architecture. In this paper, wepropose an efficient U-shaped architecture based on Swin Transformer andmulti-scale MLP, namely STM-UNet. Specifically, the Swin Transformer block isadded to skip connection of STM-UNet in form of residual connection, which canenhance the modeling ability of global features and long-range dependency.Meanwhile, a novel PCAS-MLP with parallel convolution module is designed andplaced into the bottleneck of our architecture to contribute to the improvementof segmentation performance. The experimental results on ISIC 2016 and ISIC2018 demonstrate the effectiveness of our proposed method. Our method alsooutperforms several state-of-the-art methods in terms of IoU and Dice. Ourmethod has achieved a better trade-off between high segmentation accuracy andlow model complexity.

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