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

Method based on D-S evidence theory for segmenting brain MRI image

A technology of evidence theory and image segmentation, applied in the field of medical image processing, can solve the problem that the segmentation effect of MRI images is not very good, and achieve the effect of good segmentation effect, good noise resistance, and low segmentation error rate.

Inactive Publication Date: 2018-02-13
NORTHWESTERN POLYTECHNICAL UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The traditional segmentation of brain MRI images only uses certain features, such as texture information, grayscale information, spatial information, etc., so the results obtained have great limitations. For images containing noise and blurred boundaries , the obtained MRI image segmentation effect is usually not very good

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
  • Method based on D-S evidence theory for segmenting brain MRI image
  • Method based on D-S evidence theory for segmenting brain MRI image
  • Method based on D-S evidence theory for segmenting brain MRI image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0042] Step 1: Perform median filtering on the original MRI image F to be segmented to generate a filtered image F m , the original image to be segmented as figure 2 As shown, the filtered image is as image 3 As shown, the median filtering is: using a 3×3 square template to use the following formula X=Med(X 1 ,X 2 ,...,X n ) to be evaluated, the template such as Figure 4 As shown, where since the template size is 3×3, n=9, X i is the 3×3 template pixel point P 1 ,P 2 ,P 3 ,P 4 ,P 5 ,P 6 ,P 7 ,P 8 ,P 9 any of the

[0043] Step 2: Combine the original image F and the filtered image F m Use the FCM algorithm for clustering to generate a corresponding c×n size membership matrix: U c×n and U' c×n , where c indicates that the image is divided into c categories, respectively A 1 ,A 2 ,...,A c , n means that the image has a total of n pi...

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 provides a method based on a D-S evidence theory for segmenting a brain MRI image, and related to the field of medical image processing. According to the method, grayscale information ofthe brain MRI image and neighborhood information among pixel points are fused, the image is segmented by integrating the information of the two aspects, redundancy and contradiction which are likelyto exist between the information are eliminated and complemented through the fusion of different pieces of information, the uncertainty is reduced, the accuracy and anti-noise performance of the segmented image are improved, and the error segmentation rate of the image pixel points is reduced.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to a brain MRI image segmentation method based on D-S evidence theory. Background technique [0002] With the rapid development of science and technology, magnetic resonance imaging (MRI, magnetic resonance imaging) is widely used in the diagnosis and treatment of brain diseases. Through brain MRI images, different tissues can be segmented to assist doctors in finding brain lesions. However, due to the low contrast of MRI images and the susceptibility to noise interference during the imaging process, aliasing between different tissues is easy to occur, which makes segmentation difficult. [0003] The D-S evidence theory algorithm is one of the most effective algorithms in information fusion, and it uses multi-source information collaboratively to obtain a more objective and essential understanding of things or targets. Evidence theory expands the basic event space in probabi...

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): G06T7/11G06K9/62
CPCG06T7/11G06T2207/10088G06T2207/20032G06F18/23G06F18/251
Inventor 蒋雯寿业航胡伟伟谢春禾邓鑫洋
Owner NORTHWESTERN POLYTECHNICAL UNIV
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