Region Aware Transformer for Automatic Breast Ultrasound Tumor Segmentation

Xiner Zhu, Haoji Hu, Hualiang Wang, Jincao Yao, Wei Li, Di Ou, Dong Xu
Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, PMLR 172:1523-1537, 2022.

Abstract

Although Automatic Breast Ultrasound (ABUS) has become an important tool to detect breast cancer, computer-aided diagnosis requires accurate segmentation of tumors on ABUS. In this paper, we propose the Region Aware Transformer Network (RAT-Net) for tumor segmentation on ABUS images. RAT-Net incorporates region prior information of tumors into network design. The specially designed Region Aware Self-Attention Block (RASAB) and Region Aware Transformer Block (RATB) fuse the tumor region information into multi-scale features to obtain accurate segmentation. To the best of our knowledge, it is the first time that tumor region distributions are incorporated into network architectures for ABUS image segmentation. Experimental results on a dataset of 256 subjects (330 ABUS images each) show that RAT-Net outperforms other state-of-the-art methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v172-zhu22b, title = {Region Aware Transformer for Automatic Breast Ultrasound Tumor Segmentation}, author = {Zhu, Xiner and Hu, Haoji and Wang, Hualiang and Yao, Jincao and Li, Wei and Ou, Di and Xu, Dong}, booktitle = {Proceedings of The 5th International Conference on Medical Imaging with Deep Learning}, pages = {1523--1537}, year = {2022}, editor = {Konukoglu, Ender and Menze, Bjoern and Venkataraman, Archana and Baumgartner, Christian and Dou, Qi and Albarqouni, Shadi}, volume = {172}, series = {Proceedings of Machine Learning Research}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v172/zhu22b/zhu22b.pdf}, url = {https://proceedings.mlr.press/v172/zhu22b.html}, abstract = {Although Automatic Breast Ultrasound (ABUS) has become an important tool to detect breast cancer, computer-aided diagnosis requires accurate segmentation of tumors on ABUS. In this paper, we propose the Region Aware Transformer Network (RAT-Net) for tumor segmentation on ABUS images. RAT-Net incorporates region prior information of tumors into network design. The specially designed Region Aware Self-Attention Block (RASAB) and Region Aware Transformer Block (RATB) fuse the tumor region information into multi-scale features to obtain accurate segmentation. To the best of our knowledge, it is the first time that tumor region distributions are incorporated into network architectures for ABUS image segmentation. Experimental results on a dataset of 256 subjects (330 ABUS images each) show that RAT-Net outperforms other state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Region Aware Transformer for Automatic Breast Ultrasound Tumor Segmentation %A Xiner Zhu %A Haoji Hu %A Hualiang Wang %A Jincao Yao %A Wei Li %A Di Ou %A Dong Xu %B Proceedings of The 5th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2022 %E Ender Konukoglu %E Bjoern Menze %E Archana Venkataraman %E Christian Baumgartner %E Qi Dou %E Shadi Albarqouni %F pmlr-v172-zhu22b %I PMLR %P 1523--1537 %U https://proceedings.mlr.press/v172/zhu22b.html %V 172 %X Although Automatic Breast Ultrasound (ABUS) has become an important tool to detect breast cancer, computer-aided diagnosis requires accurate segmentation of tumors on ABUS. In this paper, we propose the Region Aware Transformer Network (RAT-Net) for tumor segmentation on ABUS images. RAT-Net incorporates region prior information of tumors into network design. The specially designed Region Aware Self-Attention Block (RASAB) and Region Aware Transformer Block (RATB) fuse the tumor region information into multi-scale features to obtain accurate segmentation. To the best of our knowledge, it is the first time that tumor region distributions are incorporated into network architectures for ABUS image segmentation. Experimental results on a dataset of 256 subjects (330 ABUS images each) show that RAT-Net outperforms other state-of-the-art methods.
APA
Zhu, X., Hu, H., Wang, H., Yao, J., Li, W., Ou, D. & Xu, D.. (2022). Region Aware Transformer for Automatic Breast Ultrasound Tumor Segmentation. Proceedings of The 5th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 172:1523-1537 Available from https://proceedings.mlr.press/v172/zhu22b.html.

Related Material