RE-XswinUnet: Rotary Positional Encoding and Inter-Slice Contextual Connections for Multi-Organ Segmentation
Big Data and Cognitive Computing · 31.10.2025 · 9 (11) · 274
DOI: 10.3390/bdcc9110274 ↗Kurz gefasst
Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 31.10.2025. Verfasst von Hang Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation for Theoretical Physics special fund “cooperation program”, Shaanxi Provincial Natural Science Research Funding Project, Shaanxi Institute of Scientific Research Plan projects.
Abstract (Originalsprache)
Medical image segmentation has been a central research focus in deep learning, but methods based on convolutions have limitations in modeling the long-range validity of images. To overcome this issue, hybrid CNN-Transformer architectures have been explored, with SwinUNet being a classic approach. However, SwinUNet still faces challenges such as insufficient modeling of relative position information, limited feature fusion capabilities in skip connections, and the loss of translational invariance caused by Patch Merging. To overcome these limitations, the architecture RE-XswinUnet is presented as a novel solution for medical image segmentation. In our design, relative position biases are replaced with rotary position embedding to enhance the model’s ability to extract detailed information. During the decoding stage, XskipNet is designed to improve cross-scale feature fusion and learning capabilities. Additionally, an SCAR Block downsampling module is incorporated to preserve translational invariance more effectively. The experimental results demonstrate that RE-XswinUnet achieves improvements of 2.65% and 0.95% in Dice coefficients on the Synapse multi-organ and ACDC datasets, respectively, validating its superiority in medical image segmentation tasks.
Förderung
- National Natural Science Foundation for Theoretical Physics special fund “cooperation program”
- Shaanxi Provincial Natural Science Research Funding Project
- Shaanxi Institute of Scientific Research Plan projects
Zitieren
APA
Yang, H., Yang, C., Yang, D., Hang, X., & Liu, W. (2025). RE-XswinUnet: Rotary Positional Encoding and Inter-Slice Contextual Connections for Multi-Organ Segmentation. Big Data and Cognitive Computing, 9(11), 274. https://doi.org/10.3390/bdcc9110274
Vancouver
Yang H, Yang C, Yang D, Hang X, Liu W. RE-XswinUnet: Rotary Positional Encoding and Inter-Slice Contextual Connections for Multi-Organ Segmentation. Big Data and Cognitive Computing. 2025;9(11):274. doi:10.3390/bdcc9110274
BibTeX
@article{Yang2025,
author = {Yang, Hang and Yang, Chuanghua and Yang, Dan and Hang, Xiaojing and Liu, Wu},
title = {RE-XswinUnet: Rotary Positional Encoding and Inter-Slice Contextual Connections for Multi-Organ Segmentation},
journal = {Big Data and Cognitive Computing},
year = {2025},
volume = {9},
number = {11},
pages = {274},
doi = {10.3390/bdcc9110274}
}
EUVIMED