Magnetic resonance image reconstruction method and system based on sharpness enhancement, medium and equipment

A magnetic resonance image and sharpness technology, applied in image enhancement, image data processing, 2D image generation, etc., can solve problems that are difficult to solve, limit, and difficult to estimate, so as to reduce jagged artifacts and improve anti-noise performance , the effect of compact structure

Pending Publication Date: 2022-08-05
SOUTH CHINA UNIV OF TECH +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, solving for L 0 The minimization problem is a non-deterministic polynomial problem (NP-hard), which is difficult to solve in practical situations
However, for high-dimensional signals, it is difficult to obtain the desired reconstruction quality
In addition, the degree of sparsity in greedy algorithms must be provided as prior information, which is difficult to estimate in practical situations
Another possible approach is to smooth the L 0 Norm (smoothed L 0 ,SL0) algorithm, which attempts to directly approximate L by using a continuous function 0 norm, but the SL0 algorithm usually needs multiple iterations to converge, and it is not robust to noise, which greatly limits its practical application

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 reconstruction method and system based on sharpness enhancement, medium and equipment
  • Magnetic resonance image reconstruction method and system based on sharpness enhancement, medium and equipment
  • Magnetic resonance image reconstruction method and system based on sharpness enhancement, medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0098] like figure 1 As shown, this embodiment provides a sharpness enhancement-based magnetic resonance image reconstruction method, including the following steps:

[0099] Step 1: Collect undersampled observation signals, construct a sparse signal reconstruction problem, and convert the ill-posed target problem into a constrained minimization problem.

[0100] First, the observation signals of brain MR images are collected through the pseudo-radial sampling mode and the two-dimensional Cartesian sampling mode, respectively. The original MR images are as follows: figure 2 and image 3 shown in (a1) of , where (a2) are the pseudo-radial sampling map and the Cartesian sampling map, respectively.

[0101] Based on CS theory, sparse signal Signal can be observed by undersampling Refactoring, described as follows:

[0102] y=UFx+e (1)

[0103] in is the discrete Fourier transform, is the undersampling matrix, is to obey complex Gaussian noise. Due to the under-sa...

Embodiment 2

[0183] This embodiment provides a sharpness enhancement-based magnetic resonance image reconstruction system, including: a signal acquisition module, a sparse signal reconstruction problem building module, a transformation module, a first loop module, a second loop module, a shape parameter adjustment module, and a double loop iterative module;

[0184] In this embodiment, the signal acquisition module is used to acquire the undersampling observation signal;

[0185] In this embodiment, the sparse signal reconstruction problem building module is used to construct a sparse signal reconstruction problem;

[0186] In this embodiment, the transformation module is used to transform the ill-posed target problem into a constraint minimization problem;

[0187] In this embodiment, the first loop module is used to perform the first loop stage: use the SL0 minimization method to solve the noisy constraint minimization target problem;

[0188] In this embodiment, the second loop module...

Embodiment 3

[0192] This embodiment provides a storage medium. The storage medium may be a storage medium such as a ROM, a RAM, a magnetic disk, an optical disc, etc., and the storage medium stores one or more programs. When the programs are executed by the processor, the intelligent reflection-based implementation of the first embodiment is realized. A joint sparse channel estimation method for face-assisted IoT.

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 sharpness enhancement-based magnetic resonance image reconstruction method and system, a medium and equipment, and the method comprises the steps: collecting an undersampling observation signal, constructing a sparse signal reconstruction problem, and converting an unsuitable target problem into a constraint minimization problem; using an SL0 minimization method to solve a constrained minimization target problem with noise; analyzing deviation caused by artifacts in the noise data, and proposing a sharpness enhancement model based on deviation to correct the deviation; shape parameters are automatically adjusted through SURE; and performing double-loop iteration of MR image reconstruction, generating an initial reconstruction result in combination with a classical SL0 method, and correcting a noise error result through a deviation-based sharpness enhancement model to obtain an MR image. According to the method, the L0 minimization-based MR image reconstruction problem of the original NP-hard is solved, double circulation is designed, shape parameters are automatically adjusted by using SURE, and the method has good performance in the aspects of objective quality indexes and visual inspection.

Description

technical field [0001] The present invention relates to the technical field of magnetic resonance image reconstruction, in particular to a sharpness enhancement-based magnetic resonance image reconstruction method, system, medium and device. Background technique [0002] Magnetic Resonance Imaging (RI) is a major diagnostic imaging modality in the medical clinical field, which provides a good visualization of human organs and tissues. However, the relatively slow scan time of MRI has fundamentally hindered its development. Excessive acquisition time may cause discomfort to the patient, resulting in aliasing artifacts in the reconstruction results, and the longer the data acquisition time, the greater the probability of noise generation. An effective method is to use Compressed Sensing (CS) theory to maintain the quality of MRI reconstruction in limited acquisition samples, thereby speeding up the imaging process. CS theory can effectively reconstruct clinically acceptable ...

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): G06T11/00G06T5/00
CPCG06T11/008G06T5/002G06T5/003G06T2200/12G06T2210/41
Inventor 陈真李文源曹瑞章秀银严静东张涛廖生武
Owner SOUTH CHINA UNIV OF TECH
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