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

A Multi-Excitation Echo Plane Magnetic Resonance Imaging Method Based on Neural Network

A magnetic resonance imaging and neural network technology, which is applied in the measurement of magnetic variables, measurement devices, instruments, etc., can solve the problems of inability to reliably estimate phase changes, large phase errors, and unrealistic reconstruction time, and is easy to popularize and implement. , Accurate phase estimation, the effect of fast reconstruction

Active Publication Date: 2022-06-21
FUDAN UNIV
View PDF21 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in fact, these conventional model-based algorithms cannot reliably estimate the phase change, especially where the phase error is larger where the field is severely inhomogeneous, and various improvement methods are only limited to the improvement of image resolution, while Long reconstitution times further make these techniques impractical for clinical use

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 Multi-Excitation Echo Plane Magnetic Resonance Imaging Method Based on Neural Network
  • A Multi-Excitation Echo Plane Magnetic Resonance Imaging Method Based on Neural Network
  • A Multi-Excitation Echo Plane Magnetic Resonance Imaging Method Based on Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] Below, taking DWI and DTI applications as examples, the specific embodiments of the present invention will be described in detail in conjunction with the accompanying drawings, figure 1 is the network structure diagram of the multiple excitation plane echo reconstruction method of the neural network, figure 2 A schematic diagram of the process flow of this method. It should be pointed out that, without departing from the concept of the present invention, several modifications and improvements to the following steps all belong to the protection scope of the present invention.

[0027] Step 1: The subjects were divided into two groups, and one group of subjects underwent conventional SSH-EPI DWI and SSH-EPI DTI scans in head scans.

[0028] Step 2: The second group of subjects were subjected to 4-shot MSH-EPI DWI and MSH-EPI DTI-weighted magnetic resonance imaging sequences except for the conventional SSH-EPI DWI and SSH-EPI DTI in the head scan. DWI contains 0-1000s / m...

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 belongs to the technical field of magnetic resonance imaging, and specifically relates to a multiple excitation planar echo magnetic resonance imaging method based on a deep learning neural network. The present invention provides a brand-new method for accurate phase correction and rapid image reconstruction for multiple excitation planar echo magnetic resonance imaging. Compared with the traditional model-based undersampling image reconstruction algorithm, the present invention utilizes a deep learning neural network, by applying deep learning to the aliasing correction of Multiple Stimulation Echo Plane (MSH‑EPI) images, using Alias-free single-shot echo-planar (SSH‑EPI) images were used as targets. An aliased SSH‑EPI image with the same undersampling factor and trajectory as the multiple shot echo-planar is fed into the network to improve the accuracy of the phase estimation.

Description

technical field [0001] The invention belongs to the technical field of magnetic resonance imaging, and in particular relates to a multi-excitation plane echo magnetic resonance reconstruction method based on a deep learning neural network. Background technique [0002] Echo Planar Imaging (EPI) includes single-shot (SSH) and multiple-shot EPI (Multi-shot, MSH). Due to its high efficiency and insensitivity to motion, it is currently a diffusion-weighted imaging method. Widely used acquisition sequences for Diffusion Weighted Imaging (DWI), Magnetic Resonance Imaging (MRI) and cardiac imaging. Based on the Multi-shot Echo Planar Imaging (MSH-EPI) technology, the problems of low spatial resolution, serious geometric distortion, blurred images and obvious artifacts of a single echo plane are solved. It has very high application value in applications requiring high spatial resolution such as high-resolution diffusion weighting. By reducing the phase-encoding steps per excitatio...

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): G01R33/565
CPCG01R33/565
Inventor 张会王鹤
Owner FUDAN 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