DR-VNet: Retinal Vessel Segmentation via Dense Residual UNet

TL;DR

This paper introduces DR-VNet, a deep learning model that improves retinal vessel segmentation, especially for tiny vessels, by combining residual dense blocks and squeeze-and-excitation modules, validated on three datasets.

Contribution

It proposes a novel deep learning pipeline integrating residual dense and squeeze-and-excitation blocks for enhanced retinal vessel segmentation.

Findings

Outperforms state-of-the-art methods on sensitivity metric

Effective in capturing small and thin vessels

Validated on three different datasets

Abstract

Accurate retinal vessel segmentation is an important task for many computer-aided diagnosis systems. Yet, it is still a challenging problem due to the complex vessel structures of an eye. Numerous vessel segmentation methods have been proposed recently, however more research is needed to deal with poor segmentation of thin and tiny vessels. To address this, we propose a new deep learning pipeline combining the efficiency of residual dense net blocks and, residual squeeze and excitation blocks. We validate experimentally our approach on three datasets and show that our pipeline outperforms current state of the art techniques on the sensitivity metric relevant to assess capture of small vessels.