U-PEN Mamba improves retinal vessel segmentation with efficient global context
U-PEN Mamba: Progressive Expansion with Selective State-Space Modeling for Efficient Retinal Vessel Segmentation
Computer Vision and Pattern Recognition
Summary
Identifying the tiny blood vessels in eye images is important for eye health analysis but is difficult due to faint signals and image complexity. The authors created U-PEN Mamba, a computer program that improves this by expanding how it looks at local details step-by-step and including a special block to understand wider patterns efficiently. This helps the system better outline thin vessels and handle difficult parts of the image. Tests show it outperforms other methods on standard retina image datasets with reasonable model size. This approach can help build better tools for automatic eye disease diagnosis.
What this means in practice
- •For ophthalmic image analysis teams: Integrate U-PEN Mamba to improve automated detection of retinal vessels in fundus images for better disease diagnosis assistance.
- •For medical device software developers: Enhance retinal imaging tools with U-PEN Mamba’s efficient model to offer more accurate vessel segmentation without large computational resource needs.$Commercial implications: Enables commercial development of refined retinal analysis products with improved segmentation accuracy and efficiency.
Authors
Abel A. Reyes-Angulo, Sidike Paheding, Vijayan K. Asari, Mohammad Alam, Jeevan Devagiri
Abstract
Accurate retinal vessel segmentation is important for computer-aided ophthalmic analysis, yet thin vessels, low contrast, and severe foreground-background imbalance remain challenging for encoder-decoder networks. This paper presents U-PEN Mamba, a U-shaped retinal vessel segmentation architecture that couples progressive nonlinear feature expansion with selective state-space modeling. The proposed network enriches local vessel responses with progressive expansion, models long-range spatial dependencies through a Mamba Global Context (MGC) block with linear sequence complexity, and uses attention-based decoder fusion to recover fine vascular boundaries. We evaluate U-PEN Mamba on CHASE DB1 and DRIVE using a consistent patch-based preprocessing pipeline and compare it with convolutional, attention-based, transformer-based, and Mamba-based segmentation baselines. U-PEN Mamba obtains the best mean intersection over union among the compared methods, achieving 0.8394 on CHASE DB1 and 0.8221 on DRIVE, with Dice scores of 0.8187 and 0.8078, respectively, using 21.6M trainable parameters. Ablation studies show that the MGC block contributes the largest gain over the U-Net baseline, while projection dimension and state size provide practical accuracy-efficiency control. These results indicate that selective state-space modeling is a promising global-context mechanism for parameter-efficient retinal vessel segmentation. Code is available at: https://github.com/areyesan/UPEN_Mamba.