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

A method for denoising magnetic resonance images

A magnetic resonance image and image technology, applied in the field of image processing, can solve the problems of increased processing complexity and increased processing time, and achieve the effects of increasing speed, reducing blur, and increasing processing speed

Inactive Publication Date: 2021-05-11
CHENGDU UNIV OF INFORMATION TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The improved method of non-local mean algorithm using collaborative filtering of two or more algorithms improves the performance of denoising and increases the complexity of processing, thus increasing the processing time

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 method for denoising magnetic resonance images
  • A method for denoising magnetic resonance images
  • A method for denoising magnetic resonance images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053]In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be described in further detail below with reference to the accompanying drawings and examples.

[0054] Such as figure 1 As shown, a magnetic resonance image denoising method, comprising the following steps:

[0055] Step 1: tensor decomposition;

[0056] Step 11: Find the tensor matrix of the noise image;

[0057] Use the CP decomposition method in the tensor decomposition to calculate the partial derivatives Ix and Iy in the X and Y directions respectively, and calculate the partial derivatives in the two directions respectively:

[0058] Ix2=Ix.^2;

[0059] Iy2=Iy.^2;

[0060] Ixy=Ix.*Iy;

[0061] Three values ​​constitute the tensor matrix ST=[Ix2, Ixy; Ixy, Iy2] of the noise image. The basic method of tensor decomposition is as figure 2 As shown, the original image matrix is ​​estimated with the smaller two matrices, while the main stru...

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 discloses a magnetic resonance image denoising method, comprising the steps of: tensor decomposition; image block splitting; calculation of similarity weight; pixel value estimation; The denoising effect enables more original image information to be preserved and reduces the blurring of the edge of the image. Improved processing speed of MRI images. It can be combined with other improved non-local mean denoising algorithms to improve the speed of image processing and ensure the effect of denoising.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a magnetic resonance image denoising method. Background technique [0002] The proportion of medical images in clinical diagnosis and research is getting higher and higher, and their status is becoming more and more important. It can provide doctors with complete and accurate image information of relevant parts inside the human body in a non-invasive manner, and provides a very important reference for doctors' examination and diagnosis. There are many imaging technologies, including: X-ray, tomography, ultrasound, nuclear imaging, magnetic resonance imaging and other technical means. Among them, magnetic resonance imaging (MRI) technology can provide very clear images of organs and tissues of the human body, so it is widely used in medical treatment. Due to limited conditions, the signal-to-noise ratio of the acquired magnetic resonance images is usually relatively low...

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): G06T5/00
CPCG06T2207/10088G06T5/70
Inventor 吴涛谢磊陈曦
Owner CHENGDU UNIV OF INFORMATION 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