DS-TransUNet: Dual Swin Transformer U-Net for Medical Image Segmentation

Lin, Ailiang; Chen, Bingzhi; Xu, Jiayu; Zhang, Zheng; Lu, Guangming; Zhang, David

doi:10.1109/tim.2022.3178991

articleIEEE Transactions on Instrumentation and MeasurementJan 1, 2022Closed access

DS-TransUNet: Dual Swin Transformer U-Net for Medical Image Segmentation

ALAiliang Lin BCBingzhi Chen JXJiayu Xu ZZZheng Zhang GLGuangming Lu

Shenzhen Institute of Information Technology · Harbin Institute of Technology · +1 more institution

Indexed incrossref

Abstract

Automatic medical image segmentation has made great progress owing to the powerful deep representation learning. Inspired by the success of self-attention mechanism in Transformer, considerable efforts are devoted to designing the robust variants of encoder-decoder architecture with Transformer. However, the patch division used in the existing Transformer-based models usually ignores the pixel-level intrinsic structural features inside each patch. In this paper, we propose a novel deep medical image segmentation framework called Dual Swin Transformer U-Net (DS-TransUNet), which aims to incorporate the hierarchical Swin Transformer into both encoder and decoder of the standard U-shaped architecture. Our…

Citation impact

822

total citations

FWCI: 79.90
Percentile: 100%
References: 77

Citations per year

Authors

6

Topics & keywords

Topics

Keywords

Encoder
Computer science
Transformer
Artificial intelligence
Segmentation
Image segmentation
Computer vision
Pattern recognition (psychology)

No related works found for this paper.