Residual Swin Transformer Unet with Consistency Regularization for Automatic Breast Ultrasound Tumor Segmentation

Xianwei Zhuang, Xiner Zhu, Haoji Hu, Jincao Yao, Wei Li, Chen Yang, Liping Wang, Na Feng, Dong Xu

Abstract

Automatic Breast Ultrasound (ABUS) image segmentation is of great significance for breast cancer diagnosis and treatment. However, similar to most medical datasets, ABUS image datasets are often small-scale and seriously imbalanced, which makes ABUS image segmentation become a challenge. To solve this problem, we propose the Residual Swin Transformer Unet with Consistency Regularization (RSTUnet-CR) which can make full use of non-lesion and unlabeled images for high-precision tumor segmentation on ABUS images. We design a consistency-regularization decoder to reconstruct the input image, which can learn well from non-lesion and unlabeled data. The reconstruction task makes the model more suitable for the imbalanced medical image datasets. In addition, observing that the ABUS images have global semantic correlation, we establish long-distance dependence of images by the residual Swin Transformer block to improve segmentation performance. We evaluate our method on the ABUS dataset collected from 256 subjects and demonstrate the superiority of the proposed method over other state-of-the-art methods in this imbalanced dataset.
BibTeX
@inproceedings{zhuang2022residual,
  author = {Xianwei Zhuang and Xiner Zhu and Haoji Hu and Jincao Yao and Wei Li and Chen Yang and Liping Wang and Na Feng and Dong Xu},
  title = {{Residual Swin Transformer Unet with Consistency Regularization for Automatic Breast Ultrasound Tumor Segmentation}},
  booktitle = {ICIP},
  year = {2022},
  doi = {10.1109/icip46576.2022.9897941},
}

Loading related content...

Figure