A magnetic resonance imaging method and device

A magnetic resonance imaging and magnetic resonance image technology, applied in the field of medical imaging, can solve the problems of poor reconstruction image quality and slow reconstruction speed, and achieve the effects of improving reconstruction speed and image reconstruction stability.

Active Publication Date: 2021-02-23
SHANGHAI NEUSOFT MEDICAL TECH LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the acquisition acceleration factor is high and the collected k-space data is small, this method needs multiple iterations to converge, resulting in slow reconstruction speed or poor reconstruction image quality

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 magnetic resonance imaging method and device
  • A magnetic resonance imaging method and device
  • A magnetic resonance imaging method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] In order to facilitate the understanding of the technical solution provided by the present application, the background technology of the technical solution of the present application is briefly described below.

[0058] The inventor conducted research on traditional magnetic resonance imaging and found that in traditional magnetic resonance imaging methods, the processing of data fidelity items includes two methods: the first one: put the data fidelity items in the DNN model for processing, and the second Kind: Putting the data fidelity term outside the DNN reconstruction is achieved through an iterative process.

[0059] The specific implementation of the first processing method is as follows: the under-acquired k-space data is used as a data fidelity item, and it is directly used as a part of DNN reconstruction to realize image reconstruction. This method increases the DNN network parameters, which increases the training complexity of DNN. The processing time becomes lo...

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 present application discloses a magnetic resonance imaging method and device. After reconstructing the first image using the first deep neural network, the method uses the first part of k-space data and the second part k extracted from the complete k-space data. The -space data is subtracted to obtain residual k-space data, and then image reconstruction is performed on the residual k-space data to obtain a residual image, and finally the first image and the residual image are added to obtain a magnetic resonance image. In this way, the first part of k-space data actually collected is used in the processing after the first image is reconstructed, and the processing of the data fidelity item is placed outside the DNN reconstruction, and the DNN does not need to consider the data fidelity item The processing reduces the complexity and network parameters, and the image reconstruction speed is fast. In addition, the processing of the data fidelity item is completed through sparse constraint reconstruction without multiple iterations, and the reconstruction speed can be improved on the premise of improving the stability of image reconstruction.

Description

technical field [0001] The present application relates to the technical field of medical imaging, in particular to a magnetic resonance imaging method and device. Background technique [0002] Magnetic Resonance Imaging (MRI) has high soft tissue contrast and spatial resolution, can simultaneously obtain the morphological information and functional information of the inspection site, and can flexibly select imaging parameters and imaging layers according to needs, and has become the current An important means of medical imaging examination. [0003] However, restricted by the Nyquist sampling theorem and the strength of the main magnetic field, the imaging speed of magnetic resonance is very slow, which greatly limits the clinical application of magnetic resonance. [0004] In order to speed up the speed of magnetic resonance imaging, Deep Neural Networks (DNN for short) has recently been applied in the field of magnetic resonance accelerated imaging. [0005] In the proce...

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): G01R33/48G01R33/561
CPCG01R33/4826G01R33/561G01R33/5608G01R33/5611G01R33/4822G01R33/5619
Inventor 黄峰陈名亮
Owner SHANGHAI NEUSOFT MEDICAL TECH LTD
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