Color fundus image optic cup segmentation method based on deep learning

A fundus image and deep learning technology, applied in the direction of instruments, biological neural network models, character and pattern recognition, etc., can solve the problems of low accuracy of optic cup segmentation and difficulty in meeting large-scale data sets, so as to improve segmentation accuracy and Robust, easy-to-implement, and structurally simple effects

Pending Publication Date: 2020-10-09
TIANJIN POLYTECHNIC UNIV
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The optic cup segmentation method based on deep learning has made great breakthroughs compared with the traditional technology, but due to the particularity of medical images, it is difficult to meet the requirements of large-scale data sets required for deep network training, resulting in the current optic cup segmentation based on deep learning. low precision

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
  • Color fundus image optic cup segmentation method based on deep learning
  • Color fundus image optic cup segmentation method based on deep learning
  • Color fundus image optic cup segmentation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Deep learning network structure of the present invention such as figure 1 As shown, Seg-ResNet includes a total of 10 SERes modules, 5 maximum pooling layers, 4 upsampling layers and a loss function layer. The convolution kernel in the network has two sizes, 1×1 and 3×3, and the step size is 1, and each layer of convolution is followed by activation using the ReLU function to increase the nonlinear capability of the network. The convolution size of the max pooling layer is 2×2 with a stride of 2. The SERes in the network structure is a combination module of the residual structure and the channel weighting structure. Each SERes module includes three convolutional layers, and the BatchNorm layer is used in the convolution to perform batch normalization on the data. First, using ResNet as the basic network, the channel weighting structure is used to adjust the response value of each feature channel, and the high-level features are fused with the bottom-level features to 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 relates to a color fundus image optic cup segmentation method based on deep learning. The method comprises the following steps: 1) inputting a fundus image; 2) segmenting the optic diskby utilizing a Seg-ResNet network; the segmented optic disk area is used as an interested area of optic cup segmentation; then, a Seg-ResNet network is used for carrying out optic cup segmentation onthe optic disk area; the network is based on a residual basic structure, channel weighting is carried out by considering the relationship between feature channels, modeling is carried out on the dependency relationship between the channels, the feature response value of each channel is adaptively adjusted, feature fusion is carried out on multiple layers, and the position information of pixel points is positioned while image semantic information is captured; and 3) outputting an optic cup segmentation result using the Seg-ResNet network. According to the method, the optic cup segmentation testis carried out on the public data sets GlucomaRepo and Driver-GS, and the result shows that the segmentation accuracy and the algorithm robustness are improved by the test result.

Description

technical field [0001] The invention relates to a color fundus image cup segmentation method based on deep learning. The method involves image processing, deep learning and residual network, and can segment the color fundus image cup. Background technique [0002] Glaucoma is an optic nerve disease in which optic nerve fibers are damaged due to elevated intraocular pressure. It is irreversible and has a very high blinding rate, second only to cataract. Clinically, glaucoma can be preliminarily diagnosed by measuring parameters such as cup-to-disk ratio, and the detection of the optic cup is helpful to establish a retinal coordinate system, which can be used as a basis for further judgment of retinal damage such as drusen, exudates, and bleeding points. Exceptions and their locations. The automatic detection technology of the color fundus image cup provides a stable, accurate and efficient solution for the intelligent diagnosis of ophthalmic diseases. Therefore, in recent y...

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): G06K9/32G06K9/62G06N3/04
CPCG06V10/25G06N3/045G06F18/213G06F18/25
Inventor 肖志涛耿磊张新新吴骏张芳刘彦北王雯王曼迪
Owner TIANJIN POLYTECHNIC 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