Magnetic resonance spectrum noise reduction method based on neural network

A neural network and magnetic resonance technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as poor performance of magnetic resonance spectral signals

Active Publication Date: 2020-11-10
XIAMEN UNIV
View PDF7 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method does not perform well for MRI ...

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
  • Magnetic resonance spectrum noise reduction method based on neural network
  • Magnetic resonance spectrum noise reduction method based on neural network
  • Magnetic resonance spectrum noise reduction method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The following embodiments will further illustrate the present invention in conjunction with the accompanying drawings.

[0052] In the embodiment of the present invention, 8 subjects are used as training sources, and another subject is used as a test source. The network parameters are obtained through several iterations of network training. Finally, the first 14 acquisition data of one subject used for the test were input into the network as the noise-reducing spectrum data containing high noise to verify the noise reduction effect of this method.

[0053] 1) Collect 116 magnetic resonance spectrum signals from the same subject. Collect 8 samples, allowing different collectors to have different contents of metabolites of interest, peak heights and phases of corresponding metabolites, and noise. Finally, 928 spectra are obtained to form the training source.

[0054] According to the training source, for the 116 collections of a subject, 14 were randomly selected from ...

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 spectrum noise reduction method based on a neural network, and relates to a magnetic resonance spectrum noise reduction method. The method comprises the following steps of: 1) averaging different combinations acquired for multiple times to construct a corresponding training model data set and a label set for solving a mapping relationship between a highsignal-to-noise ratio magnetic resonance spectrum and a low signal-to-noise ratio magnetic resonance spectrum; 2) constructing a deep learning network model for magnetic resonance spectrum noise reduction based on a long-short-term memory recurrent neural network of an iterative sliding window; 3) training the deep learning network model designed in the step 2) by using the data set generated inthe step 1), and training the parameters of the network in the step 2) by using an ADAM optimization algorithm to obtain the optimal parameters of the model; and 4) performing noise reduction processing on the time domain signal of the magnetic resonance spectrum with low signal-to-noise ratio by using the network model trained in the step 3), and performing Fourier transform on the time domain signal after noise reduction to obtain a corresponding magnetic resonance spectrum after noise reduction. The invention has the characteristics of no need of priori knowledge, high noise reduction speed, high noise reduction quality and good generalization, and is suitable for dense spectral peak noise reduction.

Description

technical field [0001] The invention relates to a magnetic resonance spectrum noise reduction method, in particular to a neural network-based magnetic resonance spectrum noise reduction method. Background technique [0002] Magnetic resonance spectroscopy is an inspection method that uses the chemical shift phenomenon in magnetic resonance to determine the molecular composition and spatial distribution. The sampling process of magnetic resonance spectroscopy will be affected by noise. In practice, repeated sampling is superimposed and averaged to reduce the influence of noise. However, too many sampling times will increase the sampling time, which will increase the difficulty and cost of sampling. [0003] In practical applications, for the time-domain signal of magnetic resonance spectroscopy, Cadzow (Yung, Ya Lin, Lian Pin, Hwang, "NMR signal enhancement based on matrix property mappings," Journal of Magnetic Resonance, Series A, 103, 109-114, 1993) It is a typical noise...

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): G06N3/08G06N3/04G06K9/00G06F17/14
CPCG06N3/049G06N3/084G06F17/14G06N3/044G06N3/045G06F2218/04
Inventor 屈小波
Owner XIAMEN UNIV
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