Fundus image lesion segmentation method based on deep network aggregation

Abstract

The invention discloses a fundus image lesion segmentation method based on deep network aggregation, and the method comprises the following steps: 1), obtaining a plurality of fundus lesion images, carrying out the manual segmentation of the lesion contour in each fundus lesion image, obtaining a true value label, and constructing a training set and a test set; 2) adding a deep aggregation networkmodule into a backbone network of the U-Net model; 3) migrating the U-Net model obtained in the step 2) to focus segmentation of the fundus image, training the U-Net model, and taking the trained U-Net model as a fundus image focus segmentation model; and 4) segmenting the fundus image to be segmented by using the fundus image lesion segmentation model. The method can effectively solve the problem of poor fundus image lesion segmentation effect based on the deep convolutional neural network in the prior art.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to a fundus image lesion segmentation method based on deep network aggregation. Background technique [0002] Image segmentation is a research hotspot in the field of computer vision, which aims to divide a given image into several disjoint regions according to features such as color, brightness, and texture. Image segmentation technology provides a wealth of visual perception information for applications such as medical imaging, especially making it possible to segment fundus images of patients with diabetic retinopathy. The lesion segmentation of the fundus image is quite different from the segmentation of the natural image. First, the image size of the fundus image is often large, but the corresponding lesion area is relatively small, and the position of the lesion in the image is relatively scattered; therefore, the fundus image Lesion segmentation has always been a difficult poin...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art, and provide a fundus image lesion segmentation method based on deep network aggregation, which can effectively solve the problem of fundus image lesion segmentation based on deep convolutional neural network in the prior art bad question

Images