摘要
U-Nets have achieved tremendous success in medical image segmentation. Nevertheless, it may have limitations in global (long-range) contextual interactions and edge-detail preservation. In contrast, the Transformer module has an excellent ability to capture long-range dependencies by leveraging the self-attention mechanism into the encoder. Although the Transformer module was born to model the long-range dependency on the extracted feature maps, it still suffers high computational and spatial complexities in processing high-resolution 3D feature maps. This motivates us to design an efficient Transformer-based UNet model and study the feasibility of Transformer-based network architectures for medical image segmentation tasks. To this end, we propose to self-distill a Transformer-based UNet for medical image segmentation, which simultaneously learns global semantic information and local spatial-detailed features. Meanwhile, a local multi-scale fusion block is first proposed to refine fine-grained details from the skipped connections in the encoder by the main CNN stem through self-distillation, only computed during training and removed at inference with minimal overhead. Extensive experiments on BraTS 2019 and CHAOS datasets show that our MISSU achieves the best performance over previous state-of-the-art methods. Code and models are available at: https://github.com/wangn123/MISSU.git
学科与关键词
- BTSwin-Unet: 3D U-shaped Symmetrical Swin Transformer-based Network for Brain Tumor Segmentation with Self-supervised Pre-trainingLiang, Junjie; Yang, Cihui*; Zhong, Jingting; Ye, XiaoliNEURAL PROCESSING LETTERS, 2023, 55(4): 3695-3713.被引 11
- 3D PSwinBTS: An efficient transformer-based Unet using 3D parallel shifted windows for brain tumor segmentationLiang, Junjie; Yang, Cihui*; Zeng, LingguoDigital Signal Processing: A Review Journal , 2022, 131: 103784.被引 7
- MSAANet: Multi-scale Axial Attention Network for medical image segmentationZeng, Hao; Shan, Xinxin; Feng, Yu; Wen, Ying*IEEE International Conference on Multimedia and Expo (ICME), Brisbane, AUSTRALIA, 2023-07-10 To 2023-07-14.
