Keratoconus recognition method and device

Abstract

The invention provides a keratoconus recognition method and device, and the method comprises the steps: taking various types of corneal morphological data as the input data of a neural network, extracting the high-dimensional features of the data for classification, obtaining a classification result related to various types of keratoconus, and converting the manual observation of corneal topographic map data into a machine recognition process. According to the method, the neural network is used for replacing manual work to subdivide the types of the keratoconus, reference information used fordiagnosis is rapidly and accurately provided, and therefore the working efficiency of doctors can be improved, and high accuracy is achieved.

Description

technical field [0001] The invention relates to the field of medical data identification, in particular to a keratoconus identification method and equipment. Background technique [0002] Keratoconus is an eye disease characterized by corneal dilatation, central thinning, protruding forward, and conical shape. It is a contraindication for myopia correction surgery. Such as figure 1 As shown, the normal cornea is on the left and the keratoconus is on the right. [0003] Such as figure 2 As shown, corneal topography is a technology that displays a series of corneal surface data such as curvature and thickness collected by professional instruments in the form of topographic maps for judging the severity of keratoconus. The number of people who are willing to undergo myopia correction surgery is increasing year by year, and all people who intend to undergo myopia correction surgery need to evaluate the corneal shape through corneal topography. [0004] In clinical diagnosis...

AI Technical Summary

Problems solved by technology

Although this data conversion step is convenient for doctors to evaluate with the naked eye, there is a certain degree of information loss. Some information that cannot be detected by the naked eye is missing during the color conversion of the original data to the topographic map

Therefore, the existing keratoconus identification methods are inefficient and the accuracy needs to be improved

Images