← 返回

SDA-SwinNet: Swin-UNet with Dense Skip and Shift-ASPP for Retinal Vessel Segmentation.

SDA-SwinNet: Swin-UNet with Dense Skip and Shift-ASPP for Retinal Vessel Segmentation.

期刊: Sensors (Basel, Switzerland) 日期: 2026-08-03 PMID: 42590673 DOI: 10.3390/s26154899 浏览: 8
作者: Xiao J, Zhao M, Yang R, Wang Z, Luo T, Wu W
J, X., M, Z., R, Y., Z, W., T, L., & W, W. (2026). SDA-SwinNet: Swin-UNet with Dense Skip and Shift-ASPP for Retinal Vessel Segmentation.. Sensors (Basel, Switzerland). https://doi.org/10.3390/s26154899
J X, M Z, R Y, Z W, T L, W W. SDA-SwinNet: Swin-UNet with Dense Skip and Shift-ASPP for Retinal Vessel Segmentation.. Sensors (Basel, Switzerland). 2026; doi: 10.3390/s26154899
J X, M Z, R Y, et al. SDA-SwinNet: Swin-UNet with Dense Skip and Shift-ASPP for Retinal Vessel Segmentation.[J]. Sensors (Basel, Switzerland). 2026. DOI: 10.3390/s26154899.
@article{j2026,
  author = {Xiao J and Zhao M and Yang R and Wang Z and Luo T and Wu W},
  title = {SDA-SwinNet: Swin-UNet with Dense Skip and Shift-ASPP for Retinal Vessel Segmentation.},
  journal = {Sensors (Basel, Switzerland)},
  year = {2026},
  doi = {10.3390/s26154899},
  note = {PMID: 42590673},
}
TY  - JOUR
AU  - Xiao J
AU  - Zhao M
AU  - Yang R
AU  - Wang Z
AU  - Luo T
AU  - Wu W
TI  - SDA-SwinNet: Swin-UNet with Dense Skip and Shift-ASPP for Retinal Vessel Segmentation.
T2  - Sensors (Basel, Switzerland)
PY  - 2026
DO  - 10.3390/s26154899
AN  - PMID:42590673
ER  - 

摘要

Retinal artery/vein segmentation is a prerequisite for many ophthalmic diagnostic tools. Yet, the task remains difficult: vessels form complex trees, vary widely in caliber, and often appear low-contrast at terminal branches. We propose SDA-SwinNet to handle these challenges. The network adopts Swin-UNet as its backbone and adds three modifications: a Shift-ASPP module for multi-scale context, an HF-Bridge for cross-level feature fusion, and a fractal-constrained loss with a differentiable topology surrogate. Experimental results on the DRIVE-AV and LES-AV datasets show that the proposed model achieves an overall F1-score of 73.13% on DRIVE-AV and 67.85% on LES-AV, with additional class-wise evaluations for arteries and veins. The results demonstrate that SDA-SwinNet achieves a competitive trade-off between segmentation accuracy and computational efficiency.

AI 智能解读

相关文献

返回分类: 心血管 查看原文 (DOI)
已选择 0 篇文献