SA-UNetv2: Rethinking Spatial Attention U-Net for Retinal Vessel Segmentation

2025-09-15 · Changlu Guo, Anders Nymark Christensen, Anders Bjorholm Dahl, Yugen Yi, Morten Rieger Hannemose arxiv

Retinal vessel segmentation is essential for early diagnosis of diseases such as diabetic retinopathy, hypertension, and neurodegenerative disorders. Although SA-UNet introduces spatial attention in the bottleneck, it underuses attention in skip connections and does not address the severe foreground-background imbalance. We propose SA-UNetv2, a lightweight model that injects cross-scale spatial attention into all skip connections to strengthen multi-scale feature fusion and adopts a weighted Binary Cross-Entropy (BCE) plus Matthews Correlation Coefficient (MCC) loss to improve robustness to class imbalance. On the public DRIVE and STARE datasets, SA-UNetv2 achieves state-of-the-art performance with only 1.2MB memory and 0.26M parameters (less than 50% of SA-UNet), and 1 second CPU inference on 592 x 592 x 3 images, demonstrating strong efficiency and deployability in resource-constrained, CPU-only settings.

📄 PDF Abstract BibTeX arXiv:2509.11774

Code (0)

등록된 구현이 없습니다.

Tasks

Retinal Vessel Segmentation

Residual Spatial Attention Network for Retinal Vessel Segmentation

2020-09-18 · Changlu Guo, Márton Szemenyei, Yugen Yi, Wei Zhou 외

Reliable segmentation of retinal vessels can be employed as a way of monitoring and diagnosing certain diseases, such as diabetes and hypertension, as they affect the retinal vascular structure. In this work, we propose …

Retinal Vessel Segmentation Segmentation

Rethinking the Extraction and Interaction of Multi-Scale Features for Vessel Segmentation

2020-10-09 · Yicheng Wu, Chengwei Pan, Shuqi Wang, Ming Zhang 외

Analyzing the morphological attributes of blood vessels plays a critical role in the computer-aided diagnosis of many cardiovascular and ophthalmologic diseases. Although being extensively studied, segmentation of blood …

Decoder

VFGS-Net: Frequency-Guided State-Space Learning for Topology-Preserving Retinal Vessel Segmentation

2026-02-11 · Ruiqi Song, Lei Liu, Ya-Nan Zhang, Chao Wang 외 arxiv

Accurate retinal vessel segmentation is a critical prerequisite for quantitative analysis of retinal images and computer-aided diagnosis of vascular diseases such as diabetic retinopathy. However, the elongated morpholog…

Retinal Vessel Segmentation Representation Learning

SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation

2020-04-07 · Changlu Guo, Márton Szemenyei, Yugen Yi, Wenle Wang 외

The precise segmentation of retinal blood vessels is of great significance for early diagnosis of eye-related diseases such as diabetes and hypertension. In this work, we propose a lightweight network named Spatial Atten…

Data Augmentation Retinal Vessel Segmentation

Polygon-mamba: Retinal vessel segmentation using polygon scanning mamba and space-frequency collaborative attention

2026-05-11 · Yuanyuan Peng, Wen Li arxiv

Retinal vessel segmentation is crucial for diagnosis and assessment of ocular diseases. Notably, segmentation of small retinal vessels has been consistently recognized as a challenging and complex task. To tackle this ch…