Unlock instant, AI-driven research and patent intelligence for your innovation.

Deep learning magnetic resonance spectrum reconstruction method based on matrix decomposition

A matrix decomposition and deep learning technology, applied in the field of deep learning, can solve problems such as long spectral reconstruction time

Active Publication Date: 2020-06-23
XIAMEN UNIV
View PDF13 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method is limited by traditional optimization methods, and the spectral reconstruction time is still relatively long

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
  • Deep learning magnetic resonance spectrum reconstruction method based on matrix decomposition
  • Deep learning magnetic resonance spectrum reconstruction method based on matrix decomposition
  • Deep learning magnetic resonance spectrum reconstruction method based on matrix decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to make the technical solution of the present invention clearer, the following embodiments will further illustrate the present invention in conjunction with the accompanying drawings. It should be understood that the preferred embodiments are only for illustrating the present invention, but not for limiting the protection scope of the present invention.

[0044] In the embodiment of the present invention, an exponential function is used to generate a magnetic resonance signal as a training set label, the undersampled data is input as a training set, network parameters are obtained through several iterations of training, and finally the undersampled data to be reconstructed is input into the network to obtain the reconstructed magnetic resonance signal. resonance spectrum.

[0045] 1) Generate the time-domain signal of the magnetic resonance spectrum by using the exponential function

[0046] This embodiment generates 40,000 free induction attenuation signals, ...

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 deep learning magnetic resonance spectrum reconstruction method based on matrix decomposition, and relates to a magnetic resonance spectrum reconstruction method. The methodcomprises the following steps: 1) generating a time domain signal of a magnetic resonance spectrum by utilizing an exponential function; 2) establishing a training set containing full-sampling time domain signals and under-sampling time domain signals; 3) designing a deep learning network structure based on matrix decomposition; 4) designing a data verification layer of the deep learning network based on matrix decomposition; 5) designing a feedback function of the deep learning network based on matrix decomposition; 6) generating a spectrum reconstruction model of the deep learning network based on matrix decomposition; 7) training relative optimal parameters of the network; 8) reconstructing a magnetic resonance signal needing undersampling reconstruction, and 9) performing Fourier transform on the reconstructed time domain signal to obtain a reconstructed spectrum. the magnetic resonance signal reconstruction method has the advantages that the magnetic resonance signal reconstruction method not only has excellent time performance of a deep learning method, but also has relatively reliable theoretical support on the basis of a traditional reconstruction method, and the magnetic resonance signals can be rapidly reconstructed in a high-quality manner.

Description

technical field [0001] The invention relates to a magnetic resonance spectrum reconstruction method, in particular to a deep learning method for solving a magnetic resonance spectrum reconstruction problem based on matrix decomposition. Background technique [0002] Magnetic resonance spectroscopy is one of the important analytical tools in the fields of medicine, chemistry and biology. The sampling time of magnetic resonance spectroscopy is proportional to the number of measured points, and the sampling time increases with the increase of resolution and matrix dimension. A fast sampling method is to accelerate data acquisition by undersampling, and obtain expected resolution and complete data by spectral reconstruction. [0003] In spectral reconstruction, some researchers exploit the mathematical properties of the magnetic resonance signal to reconstruct the spectrum. One of the better effects is to use the low-rank characteristics of the time signal of magnetic resonanc...

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): G06F17/16G06N3/04G06N3/08G01R33/561
CPCG06F17/16G06N3/08G01R33/561G06N3/045
Inventor 屈小波
Owner XIAMEN UNIV