A fundus retinal vessels segmentation scheme based on the improved deep learning u-net model

Abstract

Retinal vascular segmentation is very important for diagnosing fundus diseases. However, the existing methods of retinal vascular segmentation have some problems, such as low microvascular segmentation and wrong segmentation of pathological information. To solve these problems, we developed a fundus retinal vessels segmentation based on the improved deep learning U-Net model. First, enhance the retinal images. Second, add the residual module in the process of designing the network structure, which solved the problem of the traditional deep learning U-Net model is not deep enough. By using the improved deep learning U-Net model, it can connect the output of the convolutional layer with the output of the deconvolution layer to avoid low-level information sharing, and solved the problem of performance degradation of deep convolutional neural networks in residual networks under extreme depth conditions. By verifying on the DRIVE (digital retinal images for vessel extraction) dataset, the segmentation accuracy, sensitivity, and specificity of the proposed method are 96.50%, 93.1%, and 98.63% respectively.