Multichannel retinal vessel image segmentation method based on U-net network

Abstract

The invention discloses a multichannel retinal vessel image segmentation method based on a Unet network. The method comprises the following steps: firstly, performing amplification processing and a series of preprocessing on a data set image to improve the image quality; secondly, combining a multi-scale matched filtering algorithm with an improved morphological algorithm to construct a multi-channel feature extraction structure of the Unet network; and then, carrying out network training on the three channels to obtain a required segmentation network, and carrying out adaptive threshold processing on an output result. According to the method, the Unet network and the multi-scale matched filtering algorithm are combined, compared with a pure Unet network, more blood vessel features can beextracted, higher segmentation accuracy and sensitivity are achieved, and the problems of insufficient segmentation and wrong segmentation of small blood vessels of the retinal blood vessel image arerelieved.

Description

technical field [0001] The invention relates to an image segmentation method, in particular to an image segmentation method improved by combining a U-net network in deep learning with an image matching filtering method. This method is practically applied in the segmentation of retinal blood vessel images. Background technique [0002] At present, the algorithms of image segmentation can be mainly divided into two categories: supervised learning methods and unsupervised learning methods. The unsupervised learning method mainly uses some characteristics of the image itself, manually sets the process and method of feature extraction, and has good segmentation results for the unique attributes of some images, but the use of this method largely depends on previous experience. , does not have good generalization when facing different images for segmentation processing. The most important feature of the supervised learning method is that the artificial segmentation results of the...

AI Technical Summary

Problems solved by technology

However, the problems existing in the traditional FCN are also obvious: its network structure classifies pixels, so the connection between pixels is inevitably ignored, and the receptive field of the convolution operation is too small to make good use of the context information, resulting in Incomplete feature extraction

Images