Symmetrical Supervision with Transformer for Few-shot Medical Image Segmentation

Yao Niu, Zhiming Luo, Sheng Lian, Lei Li, Shaozi Li, Haixin Song

Abstract

Few-shot learning can potentially learn the target knowledge in extremely few data regimes. Existing few-shot medical image segmentation methods fail to consider the global anatomy correlation between the support and query sets. They generally adopt a weak one-way information transmission that can not fully explore the knowledge to segment query data. To address this problem, we propose a novel Symmetrical Supervision network based on traditional two-branch methods. We raise two main contributions: (1) The Symmetrical Supervision Mechanism is leveraged to strengthen the supervision of network training; (2) A transformer-based Global Feature Alignment module is introduced to increase the global consistency between the two branches. Experimental results on two challenging datasets (abdominal segmentation dataset CHAOS and cardiac segmentation dataset MS-CMRSeg) show a remarkable performance compared to other comparing methods.
BibTeX
@inproceedings{niu2022symmetrical,
  author = {Yao Niu and Zhiming Luo and Sheng Lian and Lei Li and Shaozi Li and Haixin Song},
  title = {{Symmetrical Supervision with Transformer for Few-shot Medical Image Segmentation}},
  booktitle = {BIBM},
  year = {2022},
  doi = {10.1109/bibm55620.2022.9995238},
}

Loading related content...

Figure