Magnetic resonance image denoising method based on improved multi-path matching pursuit algorithm

A technology for magnetic resonance images and reconstructed images, which is applied in the field of image processing and can solve problems such as a large amount of calculation.

Active Publication Date: 2019-01-11
SHAANXI NORMAL UNIV
View PDF12 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because atoms with different scales, frequencies, time and phases need to be screened one by one in each step to find the best atom that matches the signal structure, resulting in a large amount of calculation

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
  • Magnetic resonance image denoising method based on improved multi-path matching pursuit algorithm
  • Magnetic resonance image denoising method based on improved multi-path matching pursuit algorithm
  • Magnetic resonance image denoising method based on improved multi-path matching pursuit algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] see figure 1 , in one embodiment, it discloses a kind of magnetic resonance image denoising method, comprises the steps:

[0020] S100: Input the image y to be reconstructed and initialize it;

[0021] S200: Generate an initial population W according to the upper and lower limits of the parameters of the atoms of the image to be reconstructed;

[0022] S300: Initialize the number of iterations, use the adaptive genetic algorithm to accelerate the search for L optimal atoms, and use these L optimal atoms to match the residual signal respectively, update the candidate support set set of the atom and the residual signal, and obtain this The set of candidate support sets for the second iteration, if the number of iterations is less than the maximum number of iterations, repeat S300;

[0023] S400: performing secondary screening on the obtained set of candidate support sets;

[0024] S500: When the iteration requirement is met, find the candidate support set with the smal...

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

A magnetic resonance image denoising method relates to image processing. In this method, the adaptive genetic algorithm (AGA) is introduced into the iterative search of multiple candidate atoms matched with the local image features in multipath matching pursuit algorithm. The method combines the advantages of adaptive genetic algorithm and multi-path matching pursuit algorithm, thereby avoiding the shortcomings that genetic algorithm is easy to fall into the local optimum and getting the best matching parameters with high precision, reducing the computational load of multi-path matching pursuit algorithm and overcoming the shortcomings that the conventional method cannot be popularized and applied because of too much computational load.

Description

technical field [0001] The disclosure belongs to the field of image processing, in particular to a magnetic resonance image denoising method. Background technique [0002] Magnetic resonance imaging (MRI) is a technology that uses static magnetic field and radio frequency magnetic field to image human tissue. Ratio features. In recent years, it has been widely used clinically. However, during the scanning process of MR images, due to the influence of stimulated human tissues and electronic components, there are always random noises in the images, and there are a series of problems such as uneven gray levels and blurred boundaries. A lot of inconvenience came. Therefore, removing noise in raw MR images has always been a challenging problem, and many denoising methods and techniques have been applied to the denoising of MR images. [0003] Traditional MR image denoising methods can be performed in both spatial and frequency domains. Median filtering is a typical nonlinear...

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): G06T5/00G06N3/12
CPCG06N3/126G06T5/002G06T2207/20192G06T2207/30068G06T2207/10088G06T2207/20032
Inventor 范虹杨晶姚若侠
Owner SHAANXI NORMAL UNIV
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