Choroid layer automatic partitioning method based on HD-OCT retina image

An automatic segmentation, retinal technology, applied in image analysis, image enhancement, image data processing and other directions, can solve problems such as inappropriate HD-OCT images

Inactive Publication Date: 2014-01-15
NANJING UNIV OF SCI & TECH
View PDF5 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The existing choroidal layer segmentation methods are not suitable for HD-OCT images, because different imaging images have different imaging characteristics, such as the reflectance of the RNFL layer in the EDI-OCT image is significantly lower than that of the RPE layer, while the two layers in the HD-OCT image The reflectivity of the person is equivalent to

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
  • Choroid layer automatic partitioning method based on HD-OCT retina image
  • Choroid layer automatic partitioning method based on HD-OCT retina image
  • Choroid layer automatic partitioning method based on HD-OCT retina image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] combine figure 1 , the autochoroidal layer segmentation method based on HD-OCT retinal image of the present invention comprises the following steps:

[0056] Step 1, collecting HD-OCT retinal images, using existing OCT imaging equipment to collect retinal images;

[0057] Step 2, using improved bilateral filtering to denoise the input image. Specifically, the isotropic Gaussian neighborhood window of the traditional bilateral filtering is changed to an anisotropic Gaussian neighborhood window, where the formula of the traditional bilateral filtering algorithm is:

[0058] h ( x ) = k - 1 ( x ) ∫ - ∞ ∞ ∫ - ∞ ∞ f ( ...

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 choroid layer automatic partitioning method based on a high-definition frequency domain optical coherence tomography (HD-OCT) image, and belongs to the technical field of image processing. According to the method, input HD-OCT images are subjected to denoising preprocessing first, a high-reflectance zone near a retina nerve fiber layer is removed by locating an internal limiting membrane, then the lower boundary of a retinochrome epithelial layer, namely the upper boundary of a choroid layer is located through high-reflectance information, finally candidate CSI boundary points obtained through the image features of the lower boundary of the choroid layer are connected through a graph searching method, and the CSI boundary of choroid membranes is obtained. Test results show that choroid layer partitioning accuracy is high and is equal to that of manual partitioning results, the method can replace the complex time-consuming work that a clinician measures the thickness of the choroid membranes manually, and significance in improving of working efficiency of a doctor is achieved.

Description

technical field [0001] The invention relates to an image segmentation processing method, in particular to an automatic choroid layer segmentation method based on high-resolution frequency-domain optical coherence tomography (HD-OCT) retinal images. Background technique [0002] HD-OCT retinal image is a high-resolution frequency-domain optical coherence tomography image, which can effectively present the choroid-scleral interface (CSI) of the choroidal layer, and clinical experiments have shown that HD-OCT images are compatible with enhanced depth imaging optical coherence tomography (EDI-OCT) images can be used to measure the thickness of the choroidal layer. Traditional retinal layer segmentation methods are not suitable for choroidal layer segmentation, because the CSI boundary of the choroidal layer is weak on the image and there is a phenomenon of boundary breakage due to the influence of blood vessels. In the past two years, the following three choroidal layer segment...

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): G06T7/00G06T5/00
Inventor 陈强牛四杰时佳佳沈宏烈
Owner NANJING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap