Resource Constrained U-Net for Extraction of Retinal Vascular Trees

TL;DR

This paper presents a modified U-Net model designed for extracting retinal vascular trees from fundus images, achieving competitive performance with limited computational resources and training data.

Contribution

Introduction of a resource-efficient U-Net variant tailored for retinal vessel segmentation with minimal performance loss.

Findings

Model performs comparably to state-of-the-art methods on retinal vessel extraction.

Efficient use of limited training data and computational resources.

Potential for deployment in resource-constrained clinical settings.

Abstract

This paper demonstrates the efficacy of a modified U-Net structure for the extraction of vascular tree masks for human fundus photographs. On limited compute resources and training data, the proposed model only slightly underperforms when compared to state of the art methods.