Method and device for detection of retinopathy of prematurity based on deep neural network

Abstract

The embodiment of the invention provides a method and a device for detection of retinopathy of prematurity (ROP) based on a deep neural network, belonging to the image processing field. The method comprises the steps of: collecting a plurality of eyeground image data, performing marking of the plurality of eyeground image data based on a preset rule, and generating image data to be processed; dividing the image data to be processed into a training set and a test set according to a preset proportion; establishing a deep neural network model; training the deep neural network model based on the training set; processing the data in the test set through the trained deep neural network model to obtain processed output data; and finally, obtaining a ROP diagnostic result based on the output data.Therefore, the manpower resource is reduced, the detection efficiency is improved, part of work of ophthalmologists is omitted, and the method and the device for detection of retinopathy of prematurity based on the deep neural network have an important guidance meaning for clinic detection of the retinopathy of prematurity.

Description

technical field [0001] The present invention relates to the field of image processing, in particular, to a detection method and device for retinopathy of prematurity based on a deep neural network. Background technique [0002] Retinopathy of prematurity (ROP) is a retinal vascular proliferative lesion that mainly occurs in premature or low birth weight infants. The survival rate of weight infants gradually increased, and the number of infants with ROP gradually increased. ROP is very harmful to children's eyesight. In addition to retinal degeneration, myopia, amblyopia, etc., it can lead to lifelong blindness in children. At present, in some hospitals with better medical conditions, for premature infants and low birth weight infants who are at risk of ROP, the usual method is to use professional equipment to collect a group of fundus image data of newborns, in order to observe the entire eyeball of the infants. , it is necessary to collect multi-angle images of the fundus...

AI Technical Summary

Problems solved by technology

After the fundus image data collection is completed, professional ophthalmologists will diagnose this set of image data. However, due to the lack of professional ophthalmolog

Images