Cerebral functional magnetic resonance imaging blind source separation method based on grouping SIM algorithm

A functional magnetic resonance and blind source separation technology, applied in computing, computer components, instruments, etc., can solve problems such as undersampling, and achieve the effect of suppressing overfitting problems, accurate analysis results, and accurate and reliable separation results.

Active Publication Date: 2017-08-25
NAT UNIV OF DEFENSE TECH
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to retain more effective information, the PCA process generally retains as many principal components as possible. However, this may lead to undersampling problems, and even cause the GroupICA separation results to produce source signals that do not actually exist but meet the assumptions of the algorithm.

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
  • Cerebral functional magnetic resonance imaging blind source separation method based on grouping SIM algorithm
  • Cerebral functional magnetic resonance imaging blind source separation method based on grouping SIM algorithm
  • Cerebral functional magnetic resonance imaging blind source separation method based on grouping SIM algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Such as figure 1 As shown, the implementation steps of the brain functional magnetic resonance imaging blind source separation method based on the group SIM algorithm in this embodiment include:

[0032]1) For the preprocessed functional magnetic resonance imaging of each subject, the dimensionality reduction at the individual level is first performed by the PCA method, and then the dimensionality reduction data of all subjects are combined to obtain a group data set , and then perform group-level dimensionality reduction on the group data set through the PCA method;

[0033] 2) Analyze and process the data set of the group after dimensionality reduction through the SIM algorithm to obtain the brain source network at the group level;

[0034] 3) The brain source network at the group level is de-reconstructed and then standardized to obtain the brain source network and corresponding time fluctuations of each subject;

[0035] 4) The brain source network and time fluctu...

Embodiment 2

[0047] This embodiment is basically the same as Embodiment 1, and its main difference is that step 1.3) converts all matrices subpcaM i The detailed steps of grouping into a new data matrix groupM are different. In this embodiment, the matrix subpcaM i A row of can be regarded as a spatial component, step 1.3) will all matrix subpcaM i The detailed steps of combining into a new data matrix groupM include: each matrix subpcaM i Each row of is used as a row of groupM, and a new data matrix groupM is formed according to the combination of rows.

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 cerebral functional magnetic resonance imaging blind source separation method based on a grouping SIM algorithm. The implementing steps include: for each tested cerebral functional magnetic resonance imaging after pre-processing, firstly, conducting individual-level dimensionality reduction through a PCA method, secondly, combining all the tested data after dimensionality reduction to obtain a group data set, and thirdly, conducting group-level dimensionality reduction of the group data set through the PCA method; subjecting the group data set after dimensionality reduction to analysis and processing through an SIM algorithm, and obtaining a group-level brain source network; subjecting the group-level brain source network to reverse reconstruction and then standardization to obtain each tested brain source network and corresponding time fluctuation; and subjecting each tested brain source network and the corresponding time fluctuation to weighted averaging, and obtaining the average brain source network of the group and the corresponding time fluctuation. The method of the invention has the advantages of the principle fitting the reality, being low in data calculation, high in algorithm operation speed, and real and reliable data analysis result.

Description

technical field [0001] The invention relates to the field of blind source separation of brain functional magnetic resonance imaging data, in particular to a brain functional magnetic resonance imaging blind source separation method based on a group SIM (Group Signal Intensity Maximizing, GroupSIM) algorithm. Background technique [0002] Brain functional imaging is to express the brain activity in an intuitive image form by observing the secondary reactions such as blood flow and metabolism caused by neural activity or the changes in electrical and magnetic signals, so that we can detect it under non-invasive conditions. Real-time functional activity of the living brain. Brain functional imaging technology has developed rapidly, and now more than a dozen have entered the practical stage. Among them, the functional Magnetic Resonance Image (fMRI) technology developed since the mid-1990s has been widely used in basic research and clinical treatment of the brain. In the brain...

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 Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/2134
Inventor 李明胡德文张岩武兴杰
Owner NAT UNIV OF DEFENSE TECH
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