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

Method for screening ocular fundus images

A fundus image and image type technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of labor-intensive, low efficiency, and speed up the diagnosis of fundus diseases, so as to improve work efficiency, overcome noise errors, save money The effect of precious time

Inactive Publication Date: 2017-05-31
REDASEN TECH DALIAN CO LTD
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the above-mentioned problems existing in the prior art, the present invention provides a method for screening fundus images, which can complete the screening and classification of fundus pictures, speed up the diagnosis of fundus diseases, solve the problems of a large amount of labor and low efficiency, and finally provide To improve the health of society as a whole

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
  • Method for screening ocular fundus images
  • Method for screening ocular fundus images
  • Method for screening ocular fundus images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] This embodiment provides a method for screening fundus images, the specific steps are as follows:

[0041] ① Receive the photographed fundus pictures;

[0042] ② Preprocessing and separation of G channel images of 24-bit true color retinal images in RGB format;

[0043] ③ Adaptive histogram equalization is used to optimize the problems of uneven illumination, too concentrated gray scale distribution and low contrast in the image;

[0044] ④ Use the Morlet wavelet formula to segment the image and extract the vascular skeleton;

[0045] ⑤Using multi-scale Gaussian matching filter to optimize the tiny blood vessel part in the image;

[0046] ⑥ Binarization based on the hysteresis threshold method performs binarization processing on the image after Gaussian matching filtering, thereby excluding most of the non-vascular pixels;

[0047] ⑦The G-channel image is processed by Gabor wavelet transform. Since its core is a Gaussian function, the gray intensity distribution of t...

Embodiment 2

[0057] This embodiment specifically explains the Morlet wavelet transform, the Gabor wavelet fusion feature vector and the neural network technology for deep learning of image features involved in the first embodiment.

[0058] (1) Morlet wavelet transform method, specifically

[0059]

[0060] Among them, * indicates conjugate; Cω indicates normalization constant; ω indicates wavelet to be analyzed; b is displacement vector; θ is rotation angle; a is scale factor, r is filter; ) reflects the degree of similarity between the gray distribution curve of the image and the wavelet sequence function. When the local frequency of the image is close to the oscillation frequency of the wavelet function of the corresponding scale, the modulus value of Tω(b,θ,a) is relatively large, and along the scale In the axial direction, the line connecting the position of the maximum modulus value of the wavelet transform coefficient is defined as the "ridge" of the wavelet transform, and its ma...

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 discloses a method for screening ocular fundus images. According to a tree network structure and grayscale distribution features of retinal vessels, a vascular skeleton is checked from multi-scale discrete gauss through a Morlet wavelet and gauss matched filtering partitioning mode, and therefore the contrast between micro vessels and a background region is increased; meanwhile, combined with a Gabor wavelet algorithm, wavelet features of the algorithm and green channel grayscale information are utilized to form feature vectors; and artery and vein vessels and ocular features of intersections, arches, yellow spots, black spots, vitiligos, etc. of the vessels are subjected to marking learning training through the deep neural network technology. Through the method, screening and classification of the ocular fundus images can be completed, the diagnosis speed of ocular fundus diseases is increased, the problems of large manual consumption and low efficiency are solved, and finally effort is made for improving the health level of the entire society.

Description

technical field [0001] The invention belongs to the field of fundus medical technology, in particular to a method for screening fundus images. Background technique [0002] Fundus disease is an important cause of human blindness, which has seriously threatened people's health and quality of life; high blood pressure, arteriosclerosis, vascular obstruction, diabetes and senile macula and other common and difficult to cure diseases have been favored by society. It is an important issue that urgently needs to be solved in the medical field. [0003] In recent years, it has been clinically confirmed that the occurrence and development of many diseases in the human body will be reflected in the fundus to varying degrees. Therefore, many diseases can be detected at an early stage and diagnosed and treated in advance through the analysis of the characteristics of the fundus, so as to control the further development of the disease. develop. This recognition makes fundus medical tr...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/168G06K9/62
CPCG06T7/0012G06T2207/20081G06T2207/20084G06T2207/20064G06T2207/30041G06F18/2411G06F18/214
Inventor 张松涛李德衡薛丹
Owner REDASEN TECH DALIAN CO LTD
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