A level set and deep learning combined retinal layer segmentation method and system

A technology of deep learning network and retinal layer, which is applied in the field of OCT retinal layer segmentation method and system, can solve a large number of labeled samples and other problems, and achieve the effect of saving computation and fine segmentation

Inactive Publication Date: 2019-06-14
SHANDONG NORMAL UNIV
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

During the research and development process, the inventors found that although deep learning and machine learning methods perform well in hierarchical segmentation, they require a large number of labeled samples

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 level set and deep learning combined retinal layer segmentation method and system
  • A level set and deep learning combined retinal layer segmentation method and system
  • A level set and deep learning combined retinal layer segmentation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] This embodiment provides an OCT retinal layer segmentation method based on the combination of the level set model and the FCN deep learning network. The method preprocesses the images collected by the optical coherence tomography equipment, and then uses the prior information of the retinal layer thickness , evolve the active contour to the boundary to be segmented through the level set model.

[0056] Please refer to the attached figure 1 , the OCT retinal layer segmentation method comprises the following steps:

[0057] S101. Collect normal retinal OCT images and diseased retinal OCT images, and perform preprocessing on the normal retinal OCT images and diseased retinal OCT images respectively.

[0058] Specifically, optical coherence tomography (OCT) equipment is used to collect normal retinal OCT images and lesioned retinal layer OCT images respectively, and de-drying and other preprocessing are performed on the normal retinal OCT images and lesioned retinal OCT im...

Embodiment 2

[0088] Please refer to the attached figure 2 , this embodiment provides a retinal layer segmentation system combining level set and deep learning, the system includes:

[0089] The image acquisition module is used to collect normal retinal OCT images and diseased retinal OCT images, and make classification labels;

[0090] The data set construction module is used to process normal retinal OCT images and diseased retinal OCT images, and construct training sets and test sets;

[0091] A model training module for training a deep learning network using the image data in the training set;

[0092] The rough segmentation module is used to process the image data in the test set by using the trained deep learning network to obtain the rough classification result of the retinal layer;

[0093] The contour evolution module is used to use the result of the rough classification of the retinal layer as a level set function, and use the gradient descent method to evolve each level set fu...

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 level set and deep learning combined retina layer segmentation method and system, and the method comprises the steps: carrying out the preprocessing of an image collected byoptical coherence tomography equipment, enabling an active contour to evolve to a to-be-segmented boundary through a level set model through employing the priori information of the thickness of a retina layer, collecting normal retina OCT images and pathological retina OCT images, making classification labels, and constructing a training set and a test set; training a deep learning network by using the image data in the training set; processing the image data in the test set by using the trained deep learning network to obtain a retinal layer coarse classification result; and taking a retina layer coarse classification result as a level set function, evolving each level set function by adopting a gradient descent method, and obtaining a fine retina layer boundary.

Description

technical field [0001] The present disclosure relates to the field of image segmentation, specifically an OCT retinal layer segmentation method and system based on a combination of a level set model and an FCN deep learning network. Background technique [0002] Optical coherence tomography (OCT) provides a noninvasive, noncontact imaging technique that can be used to generate high spatial resolution images of retinal structures. Accurate quantification of retinal structure can be a very tedious task due to the high precision and large amount of data it requires, and a critical step in the quantification of retinal layer thickness is segmentation. [0003] At present, the OCT retinal layer boundary segmentation methods mainly include: graph search algorithm, active contour and level set method and machine learning method. The graph search algorithm uses dynamic programming technology to locate the retinal layers of normal people and age-related macular degeneration patients...

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): G06T7/00G06K9/62A61B3/10
Inventor 李登旺阮亚男牛四杰孔问问吴敬红薛洁陈美荣刘婷婷
Owner SHANDONG NORMAL UNIV
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