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

Segmentation method and realization system of ophthalmology sd-oct high reflection point based on image decomposition

A SD-OCT, high-reflection technology, applied in the field of image processing, can solve the problem of not destroying the structure information of high-reflection points, and achieve the effect of meeting the requirements of accuracy, reducing influence and increasing contrast.

Active Publication Date: 2022-07-15
SHANDONG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problems to be solved by the present invention include: (1) It is necessary to eliminate the influence of noise on the segmentation of high reflection points without destroying the structural information of high reflection points

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
  • Segmentation method and realization system of ophthalmology sd-oct high reflection point based on image decomposition
  • Segmentation method and realization system of ophthalmology sd-oct high reflection point based on image decomposition
  • Segmentation method and realization system of ophthalmology sd-oct high reflection point based on image decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] An ophthalmological SD-OCT high-reflection point segmentation method based on image decomposition, such as figure 1 shown, including the following steps:

[0046] (1) The original SD-OCT image is filtered by improved bilateral filtering to reduce noise interference and increase the contrast between the high reflection point and the background.

[0047] (2) Using image decomposition technology to decompose the filtered image in step (1) into a smooth part and a sparse part, and high reflection points exist in the sparse part; the purpose is to reduce the influence of the background on the segmentation of the high reflection points, so that the high reflection points Using a simple threshold method can get better segmentation results.

[0048] (3) The high-reflection point candidates are separated from the sparse part by a simple adaptive threshold method, and the discrete points and large areas in the threshold result are removed by morphological processing to obtain th...

Embodiment 2

[0050] The ophthalmic SD-OCT high-reflection point segmentation method based on image decomposition, the difference is:

[0051] In step (1), since the high-reflection points are brighter points in the image, the influence of the size of the pixel value on the filtering result is added to the original bilateral filtering method, that is, the point with a larger pixel value has a greater influence on the filtering result, and the pixel value has a greater influence on the filtering result. Points with smaller values ​​have less influence on the filtering result. The improved bilateral filtering formula is shown in formula (I):

[0052]

[0053] In formula (I), q is the pixel currently being processed; S represents the neighborhood with q as the center and radius d; p represents the pixel in the neighborhood of S; I p Represents the pixel value of point p; G k (p) represents the weight of the spatial distance from point p to point q. The farther the distance is, the less in...

Embodiment 3

[0067] The implementation system of the ophthalmology SD-OCT high-reflection point segmentation method based on image decomposition described in embodiment 1 or 2, such as figure 2 As shown, it includes a filtering processing module, an image decomposition module, a high-reflection point candidate point separation module and a high-reflection point acquisition module that are connected in sequence;

[0068] The filtering processing module is used to realize the above step (1); the image decomposition module is used to realize the above step (2); The point candidate points are separated from the sparse part; the high-reflection point acquisition module is used to remove discrete points and large areas in the threshold result using morphological processing in the above step (3), and obtain the final high-reflection point.

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 relates to an ophthalmological SD-OCT high-reflection point segmentation method and implementation system based on image decomposition, including: (1) using improved bilateral filtering to filter the original OCT image; (2) using image decomposition technology to filter the processed image The image is decomposed into a smooth part and a sparse part, and high-reflection points exist in the sparse part; (3) use a simple adaptive threshold method to separate the high-reflection point candidates from the sparse part, and use morphological processing to remove the threshold results. The discrete points and the larger area are obtained to obtain the final high reflection point. The invention uses the improved bilateral filtering method to denoise the OCT, increases the contrast between the high reflection point and the background part, and reduces the influence of noise on the segmentation of the high reflection point. The algorithm of the invention is simple in principle, easy to implement, high in precision and fast in running speed, which can not only meet the requirements of doctors on accuracy but also meet the requirements of real-time performance.

Description

technical field [0001] The invention relates to an ophthalmic SD-OCT high-reflection point segmentation method and an implementation system based on image decomposition, and belongs to the technical field of image processing. Background technique [0002] Retinal disease is a common cause of blindness worldwide, and early clinical detection can help prevent blindness in patients. Since Spectral Domain Optical Coherence Tomography (SD-OCT) can accurately display lesions such as drusen, Hyperreflective Dots (HRD), intraretinal and subretinal effusions, optical coherence tomography has been widely used. It is widely used in the diagnosis of retinal diseases. However, the detection and segmentation of these lesions is not an easy task due to the presence of artifact noise. [0003] Professor Coscas of France first reported the existence of high reflection points (about 6-60 pixels in OCT images) in SD-OCT images in 2009, which appeared as small high points in SD-OCT images, di...

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 Patents(China)
IPC IPC(8): G06T7/136G06T5/00G06T7/90G06T7/187
CPCG06T7/136G06T7/90G06T7/187G06T2207/10101G06T2207/30041G06T5/70
Inventor 付树军张波廖胜海王红李玉亮胡明征李一啸刘旭雅
Owner SHANDONG 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