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

Higher-order singular value decomposition based magnetic resonance image denoising method

A high-order singular value, magnetic resonance image technology, applied in the field of medical image processing, can solve problems such as the influence of noise, and achieve the effect of improving image quality and preserving image details

Active Publication Date: 2014-12-10
SOUTHERN MEDICAL UNIVERSITY
View PDF5 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the basis learned by the image itself is susceptible to noise in the image, especially when the noise is severe

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
  • Higher-order singular value decomposition based magnetic resonance image denoising method
  • Higher-order singular value decomposition based magnetic resonance image denoising method
  • Higher-order singular value decomposition based magnetic resonance image denoising method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] Such asfigure 1 As shown, a magnetic resonance image denoising method based on high-order singular value decomposition includes the following steps in sequence.

[0050] (1) Perform a variance-stabilized transformation on the original MRI image with Rice noise added, transform the Rice noise that depends on the signal distribution into noise independent of the signal distribution, and obtain the transformed noise image.

[0051] (2) Take each pixel in the transformed noise image as the target pixel or take pixels at a certain distance interval as the target pixel, take the target pixel and its surrounding pixels as the reference block, perform the following operations for the first high-order singularity Value decomposition for denoising.

[0052] specifically is:

[0053] (a) Find similar blocks of the reference block one by one through the k-nearest neighbor method to form a high-dimensional array. block size p and the number of similar blocks K The value of is di...

Embodiment 2

[0076] In order to verify the effect of the method of the present invention, the simulation data is used as the denoising object, and the processing process of the magnetic resonance denoising method based on high-order singular value decomposition of the present invention is carried out.

[0077] The present invention is based on the magnetic resonance denoising method of high-order singular value decomposition, and concrete implementation comprises the following steps:

[0078] (1) Input the magnetic resonance image with Rice noise added, and transform the Rice noise which depends on the signal distribution into the noise which is independent of the signal distribution through variance stabilization transformation.

[0079] (2) For each pixel in the transformed image (in order to improve the calculation efficiency, a pixel is taken as the target pixel at a certain distance in this embodiment, and the distance of each target pixel is p -1, p is the block size), take the surr...

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

Disclosed is a higher-order singular value decomposition based magnetic resonance image denoising method. The method includes: (1) subjecting an original image to variance stability transformation; (2) subjecting the transformed image to first higher-order singular value decomposition denoising, specifically, (a) searching similar blocks of reference blocks one by one to form a higher-dimensional array for the reference blocks corresponding to pixels of each object, (b) subjecting the higher-dimensional array to higher-order singular value decomposition transformation to form coefficients and adaptive bases, (c) performing first threshold operation, and (d) performing higher-order singular value decomposition inverse transformation; (3) performing weighted average and pixel binning; (4) performing weighted average to obtain an image after first weighted average; (5) subjecting the image after first weighted average to second higher-order singular value decomposition denoising to obtain an image after second denoising; (6) subjecting the image after second denoising to variance stability inverse transformation to obtain a filtered image. By the method, magnetic resonance image noise can be suppressed effectively, and image quality is improved.

Description

technical field [0001] The invention belongs to the technical field of medical image processing, in particular to a magnetic resonance image denoising method based on high-order singular value decomposition. Background technique [0002] Magnetic resonance imaging is one of the important inspection methods of current clinical medical imaging. However, due to the influence of the imaging mechanism, noise will inevitably be introduced during the imaging process. The noise in the image will greatly reduce the quality of the image, making the edges of the image blurred and the fine structure difficult to identify, thus affecting clinical diagnosis and reducing the reliability of analysis tasks, such as image registration, image segmentation and parameter measurement of some related tissues (such as perfusion images and related parameters of relaxation time). Therefore, it is necessary to reduce noise for clinical diagnosis and image analysis. [0003] There are two ways to re...

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): G06T5/00
Inventor 冯衍秋张鑫媛徐中标陈武凡
Owner SOUTHERN MEDICAL UNIVERSITY
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