DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation
Frontiers in Bioengineering and Biotechnology · 16.05.2024 · 12
DOI: 10.3389/fbioe.2024.1398237 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Bioengineering and Biotechnology, online erschienen am 16.05.2024. Verfasst von Guanqun Sun und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Hangzhou Medical College, Hangzhou, China. Die Arbeit wurde bisher 352-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional U-Net architectures and their transformer-integrated variants excel in automated segmentation tasks. Existing models also struggle with parameter efficiency and computational complexity, often due to the extensive use of Transformers. However, they lack the ability to harness the image’s intrinsic position and channel features. Research employing Dual Attention mechanisms of position and channel have not been specifically optimized for the high-detail demands of medical images. To address these issues, this study proposes a novel deep medical image segmentation framework, called DA-TransUNet, aiming to integrate the Transformer and dual attention block (DA-Block) into the traditional U-shaped architecture. Also, DA-TransUNet tailored for the high-detail requirements of medical images, optimizes the intermittent channels of Dual Attention (DA) and employs DA in each skip-connection to effectively filter out irrelevant information. This integration significantly enhances the model’s capability to extract features, thereby improving the performance of medical image segmentation. DA-TransUNet is validated in medical image segmentation tasks, consistently outperforming state-of-the-art techniques across 5 datasets. In summary, DA-TransUNet has made significant strides in medical image segmentation, offering new insights into existing techniques. It strengthens model performance from the perspective of image features, thereby advancing the development of high-precision automated medical image diagnosis. The codes and parameters of our model will be publicly available at https://github.com/SUN-1024/DA-TransUnet .
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Hangzhou Medical College, Hangzhou, China.
- School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Japan.
- Department of Electronic Engineering, Tsinghua University, Beijing, China.
- Department of Systems Immunology, Immunology Frontier Research Institute (IFReC), Osaka University, Suita, Japan.
- Faculty of Computer and Information Sciences, Hosei University, Tokyo, Japan.
- Zhejiang Engineering Research Center for Brain Cognition and Brain Diseases Digital Medical Instruments, Hangzhou Medical College, Hangzhou, China.
Zitieren
APA
Sun, G., Pan, Y., Kong, W., Xu, Z., Ma, J., Racharak, T., Nguyen, L. M., & Xin, J. (2024). DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation. Frontiers in Bioengineering and Biotechnology, 12. https://doi.org/10.3389/fbioe.2024.1398237
Vancouver
Sun G, Pan Y, Kong W, Xu Z, Ma J, Racharak T, et al. DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation. Frontiers in Bioengineering and Biotechnology. 2024;12. doi:10.3389/fbioe.2024.1398237
BibTeX
@article{Sun2024,
author = {Sun, Guanqun and Pan, Yizhi and Kong, Weikun and Xu, Zichang and Ma, Jianhua and Racharak, Teeradaj and Nguyen, Le-Minh and Xin, Junyi},
title = {DA-TransUNet: integrating spatial and channel dual attention with transformer U-net for medical image segmentation},
journal = {Frontiers in Bioengineering and Biotechnology},
year = {2024},
volume = {12},
doi = {10.3389/fbioe.2024.1398237}
}
EUVIMED