An attention mechanism U-shaped densely connected retinal blood vessel segmentation method

A retinal blood vessel, densely connected technology, applied in the field of attention mechanism U-shaped densely connected retinal blood vessel segmentation, to avoid learning redundant features, enhance performance, and reduce network computational complexity.

Active Publication Date: 2019-03-08
JIANGXI UNIV OF SCI & TECH
View PDF10 Cites 72 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 densely connected retinal vessel segmentation method with an attent

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
  • An attention mechanism U-shaped densely connected retinal blood vessel segmentation method
  • An attention mechanism U-shaped densely connected retinal blood vessel segmentation method
  • An attention mechanism U-shaped densely connected retinal blood vessel segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] Explanation of the experiment: The data in this example come from the 02_test retinal images of healthy people in the DRIVE database.

[0058] The present invention will be further described below in combination with specific embodiments.

[0059] Step A01, retinal vessel image preprocessing

[0060] Step A01.1 converts the linear combination of RGB three channels into a single intensity channel I pre , which is defined as follows:

[0061] I pre =a 1 I g +a 2 I R +a 3 I b (1)

[0062] In formula (1), I g , I R , I b are green, red and blue channel images respectively; a 1 ,a 2 ,a 3 are the proportional weights of the green, red and blue channel images respectively, and their coefficients are 0.78, 0.12 and 0.1 respectively; then binarize [0,255] to get the mask of the image, such as image 3 and Figure 4 shown;

[0063] Step A01.2 First, put the image 3 The retinal image is firstly denoised by bilateral filtering, where the pixel neighborhood diam...

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 attention mechanism U-shaped densely connected retinal (a novel retinal blood vessel segmentation method fusing DenseNet and Attention U-net network) blood vessel segmentation method, comprising the steps of retinal blood vessel image preprocessing and constructing a retinal blood vessel segmentation model. The method of the invention can effectively solve the problemsthat adjacent blood vessels are easy to connect, the micro blood vessels are too wide, the small blood vessels are easy to break, the blood vessel intersection is insufficient in segmentation, the image noise is too sensitive, the gray value of the object and the background is crossed, the optic disc and the lesion focus are missegmented, and the like. The method of the invention integrates a plurality of network models under the condition of low complexity, the excellent segmentation results are obtained on DRIVE dataset, the accuracy and sensitivity are 96.95% and 85.94%, respectively, whichare about 0.59% and 7.92% higher than those published in the latest literature.

Description

technical field [0001] The invention relates to a U-shaped densely connected retina (a new type of retina fused with DenseNet and Attention U-net network) blood vessel segmentation method with an attention mechanism, which better solves the problems of insufficient microvessel segmentation, too wide microvessel segmentation, and crossed blood vessels in the existing algorithm. Segmentation breaks at the lesion, blood vessel breakage at the lesion, lesion and optic disc mis-segmented into blood vessels, etc. Background technique [0002] The human retina is a light-sensitive tissue covering the inner surface of the eye, and the retinal blood vessels are the only part of the systemic vascular system that can be directly observed without trauma. Information such as the number, branch, angle, and width of retinal blood vessels can be used as information related to retinal blood vessels. The basis for the diagnosis of the disease. The convolutional neural network method has powe...

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
IPC IPC(8): G06T7/11G06N3/04
CPCG06T7/11G06T2207/20172G06T2207/30101G06T2207/30041G06T2207/20081G06T2207/10024G06N3/045
Inventor 梁礼明盛校棋杨国亮吴健冯新刚
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