SA-UNet: Spatial Attention U-Net for Retinal Vessel Segmentation

TL;DR

SA-UNet is a lightweight, data-efficient neural network with spatial attention for accurate retinal vessel segmentation, outperforming existing methods on benchmark datasets.

Contribution

Introduces SA-UNet with spatial attention and structured dropout, enhancing retinal vessel segmentation without extensive training data.

Findings

Achieves state-of-the-art results on DRIVE and CHASE_DB1 datasets.

Uses spatial attention to improve feature refinement.

Employs structured dropout to prevent overfitting.

Abstract

The precise segmentation of retinal blood vessels is of great significance for early diagnosis of eye-related diseases such as diabetes and hypertension. In this work, we propose a lightweight network named Spatial Attention U-Net (SA-UNet) that does not require thousands of annotated training samples and can be utilized in a data augmentation manner to use the available annotated samples more efficiently. SA-UNet introduces a spatial attention module which infers the attention map along the spatial dimension, and multiplies the attention map by the input feature map for adaptive feature refinement. In addition, the proposed network employs structured dropout convolutional blocks instead of the original convolutional blocks of U-Net to prevent the network from overfitting. We evaluate SA-UNet based on two benchmark retinal datasets: the Vascular Extraction (DRIVE) dataset and the Child Heart and Health Study (CHASE_DB1) dataset. The results show that the proposed SA-UNet achieves state-of-the-art performance on both datasets.The implementation and the trained networks are available on Github1.