Eyeball cornea nerve segmentation method and device based on convolutional neural network model

Abstract

The embodiment of the invention provides an eyeball cornea nerve segmentation method and device based on a convolutional neural network model. The method comprises the following steps: acquiring an eyeball cornea layer image of an in-vivo confocal microscope; inputting the eyeball cornea layer image of the in-vivo confocal microscope into a preset convolutional neural network model to obtain an eyeball cornea nerve segmentation result corresponding to the eyeball cornea layer image of the in-vivo confocal microscope and a parameter result corresponding to the eyeball cornea nerve segmentation result, wherein the parameter result comprises a length parameter, a width parameter and a density parameter of corneal nerves of eyeballs. According to the embodiment of the invention, the cutting and parameter calculation of the corneal nerve fiber can be completed at the same time, so that the automatic cutting and parameter evaluation of the corneal nerve can be realized quickly and efficiently, and the auxiliary diagnosis process of ocular surface diseases such as dry eyes can be realized.

Description

technical field [0001] The invention relates to the medical-industrial interdisciplinary technical field combining ophthalmology and artificial intelligence methods, in particular to a method and device for segmenting eyeball and corneal nerves based on a convolutional neural network model. Background technique [0002] The corneal nerve (Corneal Nerve Fiber, CNF) is the nerve ending in the epithelium of the corneal layer of the eye. It has multiple functions such as feeling touch, pain, temperature, mechanical and chemical stimulation, and providing metabolic nutrition and support for the cornea. Nerve density is closely related to various ocular surface diseases such as dry eye. Therefore, in the non-invasive in vivo confocal microscopy (In Vivo Confocal Microscopy, IVCM) imaging of human corneal layers, the fine segmentation of corneal nerves and the calculation of parameters such as length and density are of great significance. [0003] In current medical practice, the ...

AI Technical Summary

Problems solved by technology

These methods have the problems of low accuracy rate and insufficient segmentation detection speed in practice, and cannot be applied to specific scientific research and clinical practice.

Images