Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image segmentation method of retinal blood vessels based on improved unet++

A retinal blood vessel and image segmentation technology, applied in the field of medical image processing, can solve problems such as loss of details in segmentation results, and achieve the effect of solving loss of details, improving semantic information, and improving segmentation performance.

Active Publication Date: 2022-08-02
KUNMING UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The invention provides a retinal blood vessel image segmentation method based on improved UNet++, fully uses features of different scales to solve the problem of loss of details in the segmentation results, and achieves better segmentation performance

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
  • Image segmentation method of retinal blood vessels based on improved unet++
  • Image segmentation method of retinal blood vessels based on improved unet++
  • Image segmentation method of retinal blood vessels based on improved unet++

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Example 1: as Figure 1-4 As shown, based on the improved UNet++ retinal blood vessel image segmentation method, the specific steps of the method are as follows:

[0034] Step1. Expand the dataset by randomly cropping the retinal images in the DRIVE dataset;

[0035]Step2. Use the MultiRes feature extraction module to extract image features, and use the SeNet module to extract channel attention, and fuse with the image features extracted by the MultiRes feature extraction module to obtain feature maps with different attention weights;

[0036] Step3. Perform the Step2 operation through 4 repetitions, and fuse the results of each repetition through a weighted summation function ξ to fuse the features obtained by the 4 Step2 operations, and finally use the fused features to perform retinal blood vessel image segmentation;

[0037] Step4. Evaluate the segmentation results of the model by comparing with the manual segmentation results of experts.

[0038] As a preferred s...

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 retina blood vessel image segmentation method based on improved UNet++, and belongs to the technical field of medical image processing. The invention selects the deep supervision network UNet++ as the image segmentation network model to improve the use efficiency of features; introduces the MulitRes feature extraction module to improve the feature learning effect of small blood vessels in a low-contrast environment. The generalization ability of the network and the expressive ability of the network structure are further improved, and the SeNet channel attention module is added after feature extraction to perform squeezing and excitation operations, thereby enhancing the receptive field in the feature extraction stage and increasing the weight of target-related feature channels. Based on the DRIVE retinal image data set, the improved UNet++ network model of the present invention is verified, and the evaluation indicators such as overlap ratio, intersection ratio, accuracy, and sensitivity have been improved to a certain extent compared with the existing model.

Description

technical field [0001] The invention relates to a retina blood vessel image segmentation method based on improved UNet++, in particular to an end-to-end neural network nested retina blood vessel image segmentation model method, which belongs to the technical field of medical image processing. Background technique [0002] As a non-invasive diagnostic method in modern ophthalmology, fundus and retinal blood vessel image segmentation has become an important part of computer-aided diagnosis of retinal diseases. For diseases such as diabetic retinopathy, hypertension, glaucoma, hemorrhage, venous occlusion and neovascularization, regular and accurate measurement of the width and growth status of blood vessels can provide effective evaluation value for these diseases. Therefore, it has high application value to carry out the computer-aided diagnosis of eye diseases by performing blood vessel segmentation on retinal images to analyze the retinal blood vessel morphology. At presen...

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 Patents(China)
IPC IPC(8): G06T7/00G06T7/10G06N3/04G06N3/08
CPCG06T7/0012G06T7/10G06N3/084G06T2207/20132G06T2207/30041G06N3/048G06N3/045
Inventor 王江峰刘利军冯旭鹏黄青松
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com