DA-U-Net: Densely Connected Convolutional Networks and Decoder with Attention Gate for Retinal Vessel Segmentation

Abstract

Abstract The segmentation of retinal vessels is greatly significant for doctors to diagnose the fundus diseases. However, existing methods have various problems in the segmentation of the retinal vessels, such as insufficient segmentation of retinal vessels, weak anti-noise interference ability. Aiming to the shortcomings of existed methods, this paper proposes an improved model based on the U-Net networks, which contains densely-connected convolutional network and a novel attention gate (AG) model, referred as Densely-Attention-U-Net (DA-U-Net), to automatically segment the retinal blood vessels. The method can alleviate the vanishing-gradient problem, strengthen feature propagation, substantially reduce the number of parameters, and automatically learn to focus on target structures without additional supervision. By verifying the method on the DRIVE datasets, the segmentation accuracy rate is 96.09%, higher than that of U-Net and R2U-Net.