Artificial intelligence diopter accurate measurement method based on eye image

Abstract

The invention discloses an artificial intelligence diopter accurate measurement method based on an eye image. The method comprises the following steps: collecting an ocular surface image with Placido ring projection and a clear fundus image as model training data; preprocessing and amplifying all data; determining and constructing a network architecture used by the classification and regression model, and training, testing and verifying the two types of models to achieve optimal performance; and fusing the two optimal models by adopting an integrated learning voting method, constructing a hybrid model, and calculating and outputting an optimal solution, wherein the output result is the diopter. The human eye diopter is calculated and measured based on the objective eye image by means of the AI method, errors caused by adjustment and the like are avoided, effective overall scheme design, process optimization and algorithm parameter setting are carried out for specific application examples, and the problem is solved that in current child and teenager vision screening and ophthalmology clinical work, the real diopter acquisition difficulty is large due to the limitations of wide crowd, long time consumption, high requirements and the like.

Description

technical field [0001] The invention belongs to the field of ophthalmic medical technology, and relates to artificial intelligence technology, in particular to an artificial intelligence diopter precision measurement method based on eye images. Background technique [0002] Uncorrected refractive error affects nearly half of the world's population as a major cause of visual impairment. Especially myopia, the number of patients in my country has reached 550 million, and the prevalence rate of high school and college students has exceeded 80%. In recent years, it has attracted great attention from the country and the government. Providing patients with accurate and efficient diopter measurements is fundamental to diagnosing and correcting refractive errors and a range of other ophthalmic procedures. At present, the commonly used diopter measurement methods in ophthalmology clinical work are mainly computer optometry and subjective optometry to obtain diopter by adjusting the...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the deficiencies of inaccurate, convenient and efficient diopter measurement in the current existing methods, and provide an artificial intelligence diopter precision measurement method based on eye images

Images