Eye fundus image analysis system and method and electronic equipment

Abstract

The embodiment of the invention provides an eye fundus image analysis system and method and electronic equipment. The system comprises a feature extraction module, an eye fundus prediction module and a segmentation prediction module, wherein the feature extraction module samples an eye fundus image to be analyzed to extract an eye fundus feature map; The eye fundus prediction module analyzes eye fundus categories corresponding to the eye fundus image according to the eye fundus feature map, wherein the eye fundus categories comprise normal eye fundus and various myopia associated eye fundus; and the segmentation prediction module samples the eye fundus feature map to analyze a segmentation prediction map corresponding to the eye fundus image, and indicates the category of each pixel in the eye fundus image, and the categories of the pixels comprise a background pixel category, an optic disk pixel category, a plurality of arc spot pixel categories and a plurality of atrophic spot pixel categories. According to the method, a machine learning technology is utilized to solve the problem that traditional classification of the myopia eye fundus is only rough categories related to pathological myopia, so that better diagnosis and treatment or daily eye using suggestions are provided for detected personnel.

Description

technical field [0001] The present invention relates to a fundus analysis method for myopia, in particular to the technical field of fundus image analysis using a neural network model, and more specifically to a fundus image analysis system, method and electronic equipment. Background technique [0002] In recent years, the age of myopia among teenagers in my country has been getting lower and lower. Teenagers' vision problems have gradually become the main problem that plagues many parents, schools and teachers. The prevention and control of teenagers' vision has also risen to the national strategic level. [0003] The occurrence of myopia is often due to bad eye habits and heavy academic burden. Most teenagers use their eyes too much, resulting in elongated eye axis. At the same time, there will be corresponding image features in fundus photos, such as It is said that the common leopard-shaped fundus is that the retina is thinned due to the stretching of the eye axis, and ...

AI Technical Summary

Problems solved by technology

[0004] However, the current myopic fundus is often limited to identifying whether the current fundus is abnormal, and cannot give a more detailed analysis of the unique conditions of the myopic fundus, making it difficult for relevant personnel to provide better diagnosis and treatment or daily use for myopia patients according to specific conditions. eye advice

Images