Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A processing method of fundus picture based on neural network

A neural network and processing method technology, applied in the field of fundus image processing, can solve the problems of low efficiency and low accuracy of diagnosis, and achieve the effect of improving efficiency and accuracy

Active Publication Date: 2019-01-15
CHANGZHOU IND TECH RES INST OF ZHEJIANG UNIV
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current judgment method is that the doctor makes a judgment by observing the fundus picture. Since the boundary between the optic cup area and the optic disc area in the fundus picture is not so clear, it takes a long time to judge the diameter ratio between them, and the diagnosis efficiency is low. less accurate

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A processing method of fundus picture based on neural network
  • A processing method of fundus picture based on neural network
  • A processing method of fundus picture based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] figure 1 Shown is a kind of embodiment 1 of the processing method of fundus picture based on neural network, comprises the following steps:

[0037] S1. Obtain several fundus pictures through camera shooting, figure 2 What is shown is a fundus picture. It can be seen that the actual picture taken by the fundus camera is relatively large, and most of the images used to identify and judge glaucoma come from the optic cup and disc. It is inconvenient to directly use the fundus picture to judge the cup and disc.

[0038] Therefore, in step S2, use the Hough transform circle detection method to find the circular area containing the optic disc; take the center of the circular area as the center, and use the preset length as the side length to cut out the optic disc and optic cup in the fundus image The square area of ​​is used as the initial sample image, from figure 2 It can be seen that the L1 part is a circular area, and the L2 part is a square area. Cutting out the o...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an eyeground picture processing method based on a neural network, comprising the following steps: S1, acquiring a plurality of eyeground pictures through shooting by a camera; S2, detecting an area including an optic disc and an optic cup in the fundus picture, and cutting the area including the optic disc and the optic cup from the fundus picture to obtain an initial samplepicture; 3, circling an optic disc region and an optic cup region on the initial sample picture and filling the optic disc region and the optic cup region with different color respectively to obtaina training sample picture; S4, constructing a neural network; 5, training the neural network through a plurality of pictures of the train samples, and determining the parameters of the neural network;this method can help doctors and nurses to judge the cup-to-dish ratio of fundus picture efficiently and accurately, and improve the efficiency and accuracy of glaucoma diagnosis.

Description

technical field [0001] The invention relates to a processing method of fundus pictures, in particular to separating optic cups and optic discs from fundus pictures, and training a large number of samples to obtain a neural network for automatically identifying and segmenting optic cups and optic discs from fundus pictures. Background technique [0002] Glaucoma is one of the major eye diseases that lead to blindness. It is expected to affect about 80 million people by 2020. Unlike eye diseases such as cataracts and myopia, glaucoma vision loss is irreversible. Therefore, early screening is essential for early treatment It is essential to preserve vision and maintain quality of life. There are three clinical modalities used to screen for glaucoma: tonometry, visual field testing, and optic disc assessment. Intraocular pressure measurement has certain risks and is not enough to be an effective examination tool for a large number of glaucoma patients with normal intraocular pr...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/11G06T7/13G06N3/04
CPCG06T7/11G06T7/13G06T2207/30041G06N3/045
Inventor 覃鹏志包勇文耀锋
Owner CHANGZHOU IND TECH RES INST OF ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com