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

Functional Magnetic Resonance Clustering Imaging Method Based on Gaussian Hidden Variable Dimensionality Reduction Clustering Center

A functional magnetic resonance and clustering center technology, applied in the field of medical imaging, can solve the problems of insufficient memory and slow operation, and achieve the effect of reducing the amount of processed data, avoiding memory overflow, and reducing the occupation of computing resources.

Active Publication Date: 2022-05-03
SICHUAN UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It cannot cluster large data sets on a personal computer, and suffers from slow operation and insufficient memory

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
  • Functional Magnetic Resonance Clustering Imaging Method Based on Gaussian Hidden Variable Dimensionality Reduction Clustering Center
  • Functional Magnetic Resonance Clustering Imaging Method Based on Gaussian Hidden Variable Dimensionality Reduction Clustering Center
  • Functional Magnetic Resonance Clustering Imaging Method Based on Gaussian Hidden Variable Dimensionality Reduction Clustering Center

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] Example 1: see figure 1 , a functional magnetic resonance clustering imaging method based on Gaussian latent variable dimensionality reduction clustering centers, comprising the following steps:

[0046] (1) collect functional magnetic resonance data of the brain, and preprocess the functional image data of the functional magnetic resonance of the brain, and obtain the preprocessed data set X, Among them, I is the number of voxels in the data set X, x i is the time series of the i-th voxel, the time series length of each voxel is N, I>>N;

[0047] The preprocessing is as follows: the functional imaging data of brain functional magnetic resonance are firstly corrected for head movement, normalized to the EPI template, spatially smoothed, and then the low-frequency noise of the signal is filtered out;

[0048] (2) Estimate the essential dimension of the principal component eigenvalues ​​of the covariance matrix of the Z score of the data set X, determine the optimal di...

Embodiment 2

[0069] (1) Sampling to obtain the functional magnetic resonance data of the brain, the functional items of the functional magnetic resonance data of the brain are first corrected for head movement, normalized to the EPI template, smoothed in space, and then the low-frequency noise of the signal is filtered out to obtain the preprocessed data set X , at this time, the data set X is a matrix with I rows and N columns;

[0070] (2) Then proceed to the following steps:

[0071] (21) X is normalized to Z score, and calculates covariance matrix C to Z score matrix, at this moment, covariance matrix C is N rows and N columns, and data volume ratio matrix X (1 row N columns) reduces greatly;

[0072] (22) Estimate the essential dimension of the principal component eigenvalues ​​of the covariance matrix C, determine the optimal dimension M, use the optimal dimension to perform Gaussian process hidden variable analysis and dimension reduction on the covariance matrix, and obtain the dim...

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 functional magnetic resonance clustering imaging method based on Gaussian latent variable dimensionality reduction clustering center. The distance index establishes a fMRI big data cluster imaging model. The Gaussian process latent variable analysis is used to reduce the dimension of the data covariance matrix, the data vector after dimension reduction is used as the cluster center, and then the minimum absolute value distance from the cluster center is used to classify the corresponding voxels of the magnetic resonance data set , and combined with experimental design pattern correlation analysis to identify task-related activation regions and construct activation indicators. The invention determines the cluster center by reducing the dimension of the covariance matrix to determine the cluster center, avoids the conventional method of directly clustering the large magnetic resonance data set, improves the imaging efficiency, and saves the computing resources. Functional magnetic resonance imaging is currently a new technical attempt.

Description

technical field [0001] The invention relates to a medical imaging method, in particular to a functional magnetic resonance clustering imaging method based on a Gaussian hidden variable dimensionality reduction clustering center. Background technique [0002] fMRI using blood oxygen level-dependent contrast provides a measure of oxygenated blood flow in the brain in response to tasks or stimuli and is an important, non-invasive method for interpreting brain function. technology with high temporal and spatial resolution. In a typical fMRI experiment, external stimuli presented at intervals of a few seconds will cause changes in voxel signal intensity and delays in the hemodynamic response. Typically, these fMRI datasets can be processed using two classes of voxel-based analysis methods: statistical methods and data-driven methods based on estimated hemodynamic response function models. [0003] Several commonly used data-driven cluster analysis techniques include k-center an...

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): G06K9/62G06V10/762
CPCG06V2201/03G06F18/23213
Inventor 张江陈华富
Owner SICHUAN 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