Retinal vessel segmentation method combining U-Net and adaptive PCNN

Abstract

The invention discloses a retinal vessel segmentation method combining U-Net and adaptive PCNN. The method comprises the steps of performing data augmentation on a fundus image database selected in anexperiment; graying processing is carried out on the data set pictures; carrying out CLAHE processing on the data set pictures to increase the contrast between retinal vessels and the background; partitioning the image; constructing and training a U-Net neural network model, and enhancing a picture; building a self-adaptive PCNN neural network model; and carrying out blood vessel segmentation byusing the adaptive PCNN. On one hand, the invention provides the fundus blood vessel image enhancement method based on the improved U-Net quadratic iteration, the background can be significantly inhibited, the blood vessel region is highlighted, the noise interference is weakened, and the picture contrast is increased, so that the picture quality of a data set is improved. The invention further provides a fundus blood vessel image segmentation method based on the self-adaptive PCNN. Accurate parameters are estimated by using an Otsu algorithm, then a U-Net secondary iteration enhancement output result is sent to an adaptive PCNN, and effective segmentation of a complete fundus vessel is realized.

Description

technical field [0001] The invention discloses a retinal blood vessel segmentation method combining U-Net and adaptive PCNN, which is used for precise segmentation of retinal blood vessels. Background technique [0002] The incidence of diabetes, cardiovascular and cerebrovascular diseases and various ophthalmic diseases is increasing with the continuous improvement of people's living standards, and people's health is seriously threatened. The morphological changes of retinal blood vessels are closely related to the occurrence of these diseases, and can reflect the incidence of these diseases to a certain extent. However, due to the particularity of retinal blood vessels, the cost of acquisition and manual segmentation is high, and the data set is scarce, there are many difficulties in the segmentation of blood vessels in retinal images: [0003] 1) The contrast between the blood vessels and the background in the fundus image is low. Due to the impact of the acquisition eq...

AI Technical Summary

Problems solved by technology

[0019] The present invention combines U-Net and PCNN to complement each other's advantages and disadvantages, and proposes a retinal vessel segmentation method combining U-Net and adaptive PCNN. In the case that it is difficult to meet the requirements of subsequent processing, the U-Net model is improved, and a method based on the improved U-Net secondary iterative fundus blood vessel image enhancement method is proposed

Images