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

Dynamic magnetic resonance parallel reconstruction method based on adaptive orthogonal dictionary learning

A dictionary learning and magnetic resonance technology, applied in the field of medical image reconstruction, can solve problems such as low accuracy

Pending Publication Date: 2019-08-20
TAIZHOU UNIV
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can only use the sparseness between two frames as the prior knowledge of reconstruction each time, resulting in lower accuracy than offline methods

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
  • Dynamic magnetic resonance parallel reconstruction method based on adaptive orthogonal dictionary learning
  • Dynamic magnetic resonance parallel reconstruction method based on adaptive orthogonal dictionary learning
  • Dynamic magnetic resonance parallel reconstruction method based on adaptive orthogonal dictionary learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0072] A kind of dynamic magnetic resonance parallel reconstruction method based on adaptive orthogonal dictionary learning of the present invention comprises the following steps:

[0073] S1: Input the original dMRI sequence X, and the input measurement value y is the undersampling data in the k-t space, using the pseudo-random ray undersampling mode (see appendix figure 2 ), the first loop iteration number OutLoop of the input algorithm, the second loop iteration number InnerLoop of the input algorithm, and the input dictionary learning parameter;

[0074] S2: Initialize, set the initial value of the reconstructed image to here is the reconstructed MR subsequence image after the kth iteration, x zf Zero-fill data after undersampling in the k-t space, and initialize the dictionary D as a DCT dictionary.

[0075] S3: iterative update,

[0076] for i=1:OutLoop

[0077] for j=1: InnerLoop

[0078] Update the adaptive dictionary D;

[0079] Update image block sparse rep...

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 dynamic magnetic resonance parallel reconstruction method based on adaptive orthogonal dictionary learning. A relatively slow dictionary learning algorithm which originally runs in an offline mode is applied to the online mode. A first frame of high-precision sampling serves as a reference, real-time online reconstruction of any n adjacent frames of MR images is achieved,a three-dimensional image small block serves as a reconstruction object, and an orthogonal dictionary serves as a sparse constraint condition and a singular value decomposition algorithm to improve the reconstruction speed and precision.

Description

[0001] Technical field: [0002] The invention belongs to the technical field of medical image reconstruction, in particular to a dynamic magnetic resonance parallel reconstruction method based on adaptive orthogonal dictionary learning. [0003] Background technique: [0004] Magnetic resonance imaging (MRI) technology has the advantages of no wound, no radiation, high resolution and multi-dimensional imaging. It can not only display the anatomical information of human tissues, but also display their functional information. MRI is widely used in various systems of clinical medicine, and is another important clinical detection method after CT. However, the slow speed of MR imaging is a major disadvantage, especially dynamic magnetic resonance imaging (dMRI), which needs to obtain MRI image sequences with high temporal and spatial resolution in a short period of time, which is currently a difficult problem in the medical field. Too long scanning time plus the patient's organ mo...

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
IPC IPC(8): G06T11/00G06T15/00G06T9/00
CPCG06T11/003G06T15/005G06T2207/10088G06T2207/20056G06T2207/20081
Inventor 王悦汪洋蒋慧敏雷必成
Owner TAIZHOU 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