Fundus image retinal vessel segmentation method and system based on deep learning

Abstract

The invention discloses a fundus image retinal vessel segmentation method and a fundus image retinal vessel segmentation system based on deep learning. The fundus image retinal vessel segmentation method comprises the steps of performing data amplification on a training set, enhancing an image, training a convolutional neural network by using the training set, segmenting the image by using a convolutional neural network segmentation model to obtain a segmentation result, training a random forest classifier by using features of the convolutional neural network, extracting a last layer of convolutional layer output from the convolutional neural network, using the convolutional layer output as input of the random forest classifier for pixel classification to obtain another segmentation result, and fusing the two segmentation results to obtain a final segmentation image. Compared with the traditional vessel segmentation method, the fundus image retinal vessel segmentation method uses the deep convolutional neural network for feature extraction, the extracted features are more sufficient, and the segmentation precision and efficiency are higher.

Description

technical field [0001] The invention relates to the fields of machine learning and image processing, and is aimed at the research of medical image semantic segmentation technology, especially a method and system for retinal blood vessel segmentation of fundus images based on deep learning. Background technique [0002] In recent years, with the development of image processing technology, image segmentation technology has begun to be applied to the field of fundus image segmentation. At present, many researchers at home and abroad have proposed a variety of retinal blood vessel segmentation algorithms for fundus images, which are mainly divided into the following: Directions: methods based on vessel tracking, methods based on matched filtering, methods based on deformation models, and methods based on machine learning. [0003] The method based on matched filtering is to convolve the filter with the image to extract the target object. Since the gray level of the retinal vesse...

AI Technical Summary

Problems solved by technology

The main difficulty of this method lies in feature extraction and image segmentation. For machine learning methods, feature engineering is very important. Traditional methods mainly use Gabor filtering and other methods, and the extraction features are limited. In recent years, with the development of deep learning, using deep learning The feature extraction of images has a good effect, and some people try to use deep learning for blood vessel segmentation

Images