DRA U-Net: An Attention based U-Net Framework for 2D Medical Image Segmentation

Summary:

This work proposes an attention-based U-Net architecture for 2D medical image segmentation. By combining attention mechanisms with residual feature extraction, the model is designed to better capture ambiguous boundaries and anatomical variation, improving segmentation performance in challenging medical images.

Bibtex:

@inproceedings{zhang2021draunet,
  title={DRA U-Net: An Attention based U-Net Framework for 2D Medical Image Segmentation},
  author={Xian Zhang and Ziyuan Feng and Tianchi Zhong and Sicheng Shen and Ruolin Zhang and Lijie Zhou and Bo Zhang and Wendong Wang},
  booktitle={2021 IEEE International Conference on Big Data (Big Data)},
  pages={3936--3942},
  year={2021},
  doi={10.1109/BigData52589.2021.9672031},
  url={https://doi.org/10.1109/BigData52589.2021.9672031}
}

Recommended citation: Zhang, X., Feng, Z., Zhong, T., Shen, S., Zhang, R., Zhou, L., Zhang, B., & Wang, W. (2021). DRA U-Net: An Attention based U-Net Framework for 2D Medical Image Segmentation.
Download Paper