A U-shaped retinal vessel segmentation method adaptive to scale information

A technology of retinal blood vessels and scale information, applied in the field of U-shaped retinal blood vessel segmentation with adaptive scale information, to achieve the effect of overcoming incomplete utilization, reducing the complexity of network parameters, and increasing the training set

Active Publication Date: 2019-04-26
JIANGXI UNIV OF SCI & TECH
View PDF7 Cites 52 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a U-shaped retinal vessel segmentation method with adaptive scale information in view of the complexity and variety of retinal vessel features and the shortcomings of existing segmentation algorithms

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 U-shaped retinal vessel segmentation method adaptive to scale information
  • A U-shaped retinal vessel segmentation method adaptive to scale information
  • A U-shaped retinal vessel segmentation method adaptive to scale information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The invention proposes a U-shaped retinal image segmentation that adapts to the morphological structure and scale information of the target image based on the U-shaped network structure fusion of dense deformable convolution, pyramid-shaped hole convolution and deconvolution layer with attention mechanism Algorithm; this model can capture the shape features of blood vessels more efficiently and with higher precision, which can simplify the cumbersome process of manual extraction of retinal blood vessels by ophthalmologists, and convert it from qualitative analysis to quantitative analysis, avoiding the existence of different ophthalmologists due to subjective factors. The error can provide help for clinical ophthalmologists in the diagnosis and treatment of diseases.

[0059] Explanation of the experiment: The data in this example come from the 03_test retinal images of healthy people in the DRIVE database.

[0060] The present invention will be further described below ...

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 U-shaped retinal vessel segmentation method adaptive to scale information. The U-shaped retinal vessel segmentation method comprises the following steps: preprocessing a retinal vessel image; And constructing a retinal vessel segmentation model 2. The method can effectively solve the problems that adjacent blood vessels are easy to connect, microvessels are too wide, tiny blood vessels are easy to break, segmentation at the intersection of the blood vessels is insufficient, image noise is too sensitive, a target and a background gray value are crossed, and a visual disc and a focus are segmented by mistake. According to the method, multiple network models are fused under the condition of low complexity, an excellent segmentation result is obtained on a DRIVE dataset, and the accuracy rate and the sensitivity of the method are 97.48% and 85.78% respectively. And the ROC curve value reaches 98.72% and reaches the current medical practical application level.

Description

technical field [0001] The invention relates to a U-shaped densely connected retinal blood vessel segmentation method adaptive to target scale information, which better solves the problem that the existing algorithm is not robust to blood vessel scale, attitude and texture edge information, and helps to solve the algorithm There are problems such as insufficient segmentation of microvessels, too wide segmentation of microvessels, segmentation and breakage at the intersection of blood vessels, breakage of blood vessels in lesions, and wrong segmentation of lesions and optic discs into blood vessels. Background technique [0002] Blood vessels are one of the most important components of the retina, and retinal vessel segmentation and division of vascular morphological attributes, such as length, width, tortuosity, and angle, can be used in the diagnosis, screening, treatment, and evaluation of various cardiovascular and ophthalmic diseases. In recent years, the deep learning m...

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): G06T7/11G06T7/00G06N3/04
CPCG06T7/0012G06T7/11G06T2207/20081G06T2207/20012G06T2207/30041G06N3/048
Inventor 梁礼明盛校棋蓝智敏吴健冯新刚
Owner JIANGXI 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