Residual Spatial Attention Network for Retinal Vessel Segmentation

TL;DR

This paper introduces RSAN, a novel neural network architecture with residual blocks, DropBlock, and spatial attention, achieving state-of-the-art retinal vessel segmentation results on public datasets.

Contribution

The paper proposes RSAN, combining residual structures, DropBlock, and spatial attention to enhance feature extraction and reduce overfitting in retinal vessel segmentation.

Findings

RSAN outperforms existing methods on DRIVE and CHASE DB1 datasets.

The integration of DropBlock and spatial attention improves segmentation accuracy.

RSAN achieves state-of-the-art performance in retinal vessel segmentation.

Abstract

Reliable segmentation of retinal vessels can be employed as a way of monitoring and diagnosing certain diseases, such as diabetes and hypertension, as they affect the retinal vascular structure. In this work, we propose the Residual Spatial Attention Network (RSAN) for retinal vessel segmentation. RSAN employs a modified residual block structure that integrates DropBlock, which can not only be utilized to construct deep networks to extract more complex vascular features, but can also effectively alleviate the overfitting. Moreover, in order to further improve the representation capability of the network, based on this modified residual block, we introduce the spatial attention (SA) and propose the Residual Spatial Attention Block (RSAB) to build RSAN. We adopt the public DRIVE and CHASE DB1 color fundus image datasets to evaluate the proposed RSAN. Experiments show that the modified residual structure and the spatial attention are effective in this work, and our proposed RSAN achieves the state-of-the-art performance.