Training method, training device, recognition method and recognition system for glaucoma recognition

Abstract

The invention discloses a training device for glaucoma recognition. The training device comprises an acquisition module; the image segmentation network is an artificial neural network based on deep learning and is trained through the preprocessed fundus image, the annotated image and the spatial weighted graph so as to output the probability that each pixel point in the preprocessed fundus image belongs to an optic disk and the probability that each pixel point belongs to an optic cup; generating an optic disc area image and an optic cup area image based on the probability that each pixel point in the preprocessed fundus image belongs to the optic disc and the probability that each pixel point belongs to the optic cup; the feature extraction module is used for acquiring glaucoma features based on the optic disc region image and the optic cup region image; and a classifier trained by feature information including glaucoma features and a glaucoma classification tag based on machine learning to output a probability belonging to glaucoma. According to the scheme, the accuracy of glaucoma recognition can be improved.

Description

technical field [0001] The present disclosure generally relates to a glaucoma recognition training method, training device, recognition method and recognition system. Background technique [0002] Currently, glaucoma is the second leading cause of blindness in the world. There are more than 10 million patients with primary glaucoma worldwide, and more than 10% of them may develop binocular blindness. If glaucoma is not diagnosed early, it may develop into irreversible blindness, so early glaucoma screening is of great significance. [0003] Among glaucoma screening technologies, fundus camera technology provides an economical and accurate way for early glaucoma screening. Medical research has confirmed that glaucoma can be detected at an early stage by measuring the cup-to-disk ratio of the optic nerve head (the ratio of the optic cup radius to the optic disc radius, referred to as the cup-to-disc ratio) by fundus imaging. With the development of artificial intelligence t...

AI Technical Summary

Problems solved by technology

[0004] However, in the above-mentioned glaucoma identification methods, complex image processing algorithms are required to initially locate the optic disc, and the accuracy of optic disc positioning will affect the accuracy of subsequent optic cup or optic disc segmentation, which in turn affects the accuracy of cup-to-disk ratio calculation.

In addition, in other existing glaucoma identification methods, the cup-to-disk ratio is used to identify glaucoma, and other features of the optic cup or optic disc extracted by the convolutional neural network are not used for glaucoma identification, so the accuracy of glaucoma identification remains to be determined. promote

Images