Multi-label eye fundus image recognition method based on GACNN

Abstract

The invention relates to the technical field of image processing, in particular to a GACNN-based multi-label eye fundus image recognition method, which comprises the following steps of: acquiring an original eye fundus image and preprocessing the original eye fundus image; constructing a GACNN model, using the preprocessed original fundus image with the label to perform training, wherein the GACNN model comprises a convolutional neural network, a graph attention network and a fusion layer, and the convolutional neural network is used for extracting image features, the graph attention network is used for modeling a relationship among fundus multiple labels, regarding each label of a fundus image as a group of mutually dependent nodes, and training by using historical data to obtain a multi-label classifier, and the fusion layer fuses the features obtained by the convolutional neural network and the graph attention network to obtain a final classification result; and inputting a to-be-detected original fundus image into the trained GACNN model, and outputting an identification result with a label; According to the method, the correlation between the tags is fully considered when the multiple tags in the fundus image are identified, and the identification accuracy of the fundus image is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a multi-label fundus image recognition method based on GACNN (Graph Attention Convolutional Neural Network). Background technique [0002] Fundus images are the main basis for ophthalmologists to diagnose and treat fundus diseases, and fundus image processing is of great significance. Since the number of people with high myopia is constantly increasing and high myopia may lead to fundus lesions and blindness, this puts great pressure on ophthalmologists for screening. Using computer technology to process fundus images can effectively help doctors relieve this pressure. In the research of fundus image recognition, there are usually methods based on traditional image processing and methods based on deep learning. The classification method based on traditional image processing needs artificially designed features and processed images, but in the images of myopic fundus di...

AI Technical Summary

Problems solved by technology

[0004] Some multi-label classification algorithms have been able to learn and classify label data sets very well. However, in fundus images, the characteristics of fundus diseases are not obvious and there is a certain correlation between different diseases. If there is macular degeneration, there is a high probability. choroidal atrophy and other diseases

Due to the above factors, the existing multi-label classification algorithm cannot obtain more accurate classification results.

Images