A frequency-driven method for retinal vessel segmentation

Haoren Xiong

doi:10.1016/j.cmpb.2026.109676

A frequency-driven method for retinal vessel segmentation

2026-10-07

0

PRE

AI

DOI：10.1016/j.cmpb.2026.109676

Original

Save

Abstract

En 中文

Retinal vessel segmentation is essential for diagnosing and monitoring ocular and systemic diseases. However, most existing deep learning methods operate predominantly in the spatial domain, limiting their ability to capture fine vessel structures and maintain topological continuity, especially for thin and low-contrast vessels. Existing frequency-aware approaches mostly rely on fixed transforms or simple feature concatenation, lacking task-adaptive spectral modeling. We developed a frequency-driven framework to address these limitations.

A frequency-driven method for retinal vessel segmentation

Abstract

Journal

Organization

Cited Papers