Gaze into the Details: Locality-Sensitive Enhancement for OCTA Retinal Vessel Segmentation

TL;DR

This paper introduces LSENet, a novel deep learning model that enhances OCTA retinal vessel segmentation by addressing local contrast issues and vessel discontinuities through innovative modules.

Contribution

LSENet incorporates three new modules—PIE, MFF, and CRD—to improve vessel continuity and detail preservation over traditional U-Net-based methods.

Findings

Achieves state-of-the-art performance on three public datasets.

Requires fewer parameters than existing models.

Effectively reduces vessel fragmentation and detail loss.

Abstract

Existing deep learning frameworks for Optical Coherence Tomography Angiography (OCTA) vessel segmentation are largely derived from the U-Net architecture, which serves as the foundation for most current designs. However, most of these methods focus only on holistic representation, struggling to address the problem of low local contrast unique to OCTA, which leads to vessel discontinuities and loss of detail. To address these problems, we propose LSENet, which builds upon the U-Net architecture by introducing three core innovative modules: To address vessel discontinuities, we introduce the Patch Information Enhance module (PIE), which replaces standard skip connections to execute patch-wise attention. To mitigate detail loss, the Multiscale Feature Fusion module (MFF) is proposed to feed the PIE module rich, multi-scale information by extracting visually interpretable features from both the original input and preceding layers. Finally, the Connectivity Refinement Decoder (CRD) is designed to refine features from all levels and utilize a large kernel in the final convolutional layer to reduce fragmentation. Experiments on three public datasets (OCTA-500, ROSE-1, and ROSSA) demonstrate that our proposed LSENet achieves state-of-the-art performance while requiring fewer parameters.