Eye disease diagnosis device and method based on deep neural network by using fundus image

Abstract

The present invention relates to an apparatus and a method for diagnosing eye diseases using eye fundus images, and more particularly, to an apparatus and a method for diagnosing eye diseases using eye fundus images, which normalize a learning data set by image preprocessing including reduction of a region of interest (ROI), plane-limited contrast adaptive histogram equalization, data enhancement, and the like, and to a method for diagnosing eye diseases using eye fundus images. The present invention relates to a device and a method for diagnosing eye diseases based on a deep neural network using fundus images, and more particularly, to a device and a method for diagnosing eye diseases based on a deep neural network using fundus images, which are capable of diagnosing a plurality of eye diseases such as normal (Nomal), glaucoma (GLC), age-related macular degeneration (AMD), and diabetic retinopathy (DR) by applying a deep neural network, and to a method for diagnosing eye diseases based on a deep neural network using fundus images.

Description

technical field [0001] The present invention relates to a device and method for diagnosing eye diseases using fundus images. Histogram equalization) and image preprocessing such as data enhancement to normalize the learning data set, and can diagnose normal (Nomal), including glaucoma (Glaucoma: GLC), age-related macular degeneration (Age Related macula degeneration: AMD), diabetic retinopathy (Diabetic Retinopathy: DR) eye disease diagnosis device and method based on deep neural network using fundus images. Background technique [0002] Diabetic Retinopathy (DR), Glaucoma (GLC), and Age-related macular degeneration (AMD) are the leading causes of vision loss and blindness worldwide. [0003] Diabetic retinopathy is a vascular complication of the retina that causes damage to the retina, resulting in severe vision loss if not treated promptly. [0004] From 2000 to 2030, the global diabetes population growth rate is estimated to increase from 2.8% to 4.4%, which equates to ...

AI Technical Summary

Problems solved by technology

Therefore, the quality of the fundus image may affect the clinician's ability to perform an accurate examination and diagnosis

[0013] Although a variety of ophthalmic diseases can be diagnosed from fundus images in this way, conventional ophthalmic disease diagnosis devices using artificial intelligence can only detect one specific ophthalmic disease from fundus images

[0014] That is, the conventional eye disease diagnosis apparatus using artificial intelligence has a problem that it detects only one eye disease from a fundus image, but cannot detect two or more eye diseases

Images