A MRI Diffusion Weighted Imaging Method Based on Deep Learning and Convex Set Projection

A diffusion-weighted imaging and convex set projection technology, which is applied in the use of nuclear magnetic resonance imaging systems for measurement, magnetic resonance measurement, medical science, etc. The effect of ensuring stability and shortening scanning time

Active Publication Date: 2020-07-28
朱高杰
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is: the present invention provides a magnetic resonance diffusion weighted imaging method based on deep learning and convex set projection, which solves t

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 MRI Diffusion Weighted Imaging Method Based on Deep Learning and Convex Set Projection
  • A MRI Diffusion Weighted Imaging Method Based on Deep Learning and Convex Set Projection
  • A MRI Diffusion Weighted Imaging Method Based on Deep Learning and Convex Set Projection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] Step 1 includes the following steps:

[0068] Step 1.1: Convex set projection layer POCS, CNN network and phase constraint layer PCON are composed of network modules. The convex set projection layer POCS and CNN network in each network module are connected in a many-to-many manner, and the CNN network and phase constraint layer PCON are in a multi-to-many connection. For one connection, the network modules are repeatedly superimposed to build a network;

[0069] Step 1.2: Scan the multi-excitation diffusion weighted sequence including pre-scan and navigation echo, collect the pre-scan data, generate a correction matrix based on the pre-scan data, and calculate the sensitivity of all receiving coils based on the correction matrix as figure 1 402 in;

[0070] Step 1.3: Acquire the imaging signals and navigation echo signals in the sequence, use the imaging signals of each excitation as the input data of the network, correct the phase error between multiple excitation ima...

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 magnetic-resonance diffusion weighted imaging method based on deep learning and projection onto convex sets, and relates to the field of magnetic-resonance diffusion weightedimaging. The method includes the steps that 1, network modules composed of projection-onto-convex-set (POCS) layers, CNNs and phase constraint (PCON) layers are repeatedly stacked to complete networkconstruction, sequences containing navigator echoes are scanned, and input data and training mark data of a constructed network are obtained; 2, the training mark data serves as a target, corresponding information is input into the constructed network for back propagation to train network parameters, and an input-output mapping relationship is obtained; 3, sequences without navigator echoes are scanned, imaging signals and coil sensitivity distribution are obtained, and corresponding information is input into a trained network for forward propagation to obtain an output image to complete reconstruction. The problem that as an existing traditional magnetic-resonance diffusion weighted imaging method is limited by the parallel image performance, the image resolution ratio is difficult to increase is solved, and the effect of increasing the resolution ratio and the quality of the reconstruction image is achieved.

Description

technical field [0001] The invention relates to the field of magnetic resonance diffusion weighted imaging, in particular to a magnetic resonance diffusion weighted imaging method based on deep learning and convex set projection. Background technique [0002] Magnetic resonance diffusion imaging technology is a new technology that relies on the random movement of water molecules in the body to provide image contrast. The diffusion of water molecules in tissues conforms to a random thermal motion model, and the magnitude and direction of diffusion are affected by biofilms and biomacromolecules in tissues. When a gradient magnetic field exists, the diffusion motion of water molecules will cause the dephasing of the magnetization vector, resulting in magnetic Resonance signal reduction, the degree of magnetic resonance signal reduction depends on tissue type, structure, physical and physiological state and microenvironment. In the above process, the gradient magnetic field spe...

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): A61B5/055
CPCG01R33/54
Inventor 朱高杰
Owner 朱高杰
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