A two-dimensional visualization method for fMRI data based on popular learning algorithms

A popular learning and data technology, applied in the field of biomedical image pattern recognition, to achieve the effect of high stability, high efficiency and stability

Active Publication Date: 2020-05-12
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there is no good method to reduce the dimensionality of fMRI data on the basis of maintaining the spatial topological relationship of brain voxels, and visualize it in a two-dimensional plane

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 two-dimensional visualization method for fMRI data based on popular learning algorithms
  • A two-dimensional visualization method for fMRI data based on popular learning algorithms
  • A two-dimensional visualization method for fMRI data based on popular learning algorithms

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The specific implementation of the present invention will be described in further detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0036] A method for 2D visualization of fMRI data based on popular learning algorithms. The specific implementation steps are as follows:

[0037] Step A: Raw Data Construction

[0038] Read the Broadman template data matrix, and extract the coordinates of voxel points belonging to the 17-19 functional area (that is, find out the spatial positions of all voxel points with values ​​17, 18, and 19 in the read three-dimensional matrix). The spatial coordinates of these voxel points and the numbers of brain regions are formed into an m*4 matrix (m is the number of extracted voxels). Take this matrix as our input original data set X={x 1 , x 2 , x 3 ,...,x n} T , where x i =(ri ,p i ...

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 two-dimensional visualization method for fMRI data based on a popular learning algorithm. The method belongs to the technical field of biomedical image pattern recognition, and specifically relates to a dimensionality reduction visualization method for functional magnetic resonance image data. The invention utilizes popular learning algorithms to perform dimensionality reduction processing on fMRI data and realizes two-dimensional visualization of brain voxels, and has high efficiency and high stability. Moreover, the dimensionality reduction mechanism of the t-SNE algorithm itself also determines that the results of two-dimensional visualization can maintain the original spatial topological relationship of the data. The present invention proposes a new and effective method for the two-dimensional visualization of functional magnetic resonance data. For the first time, popular learning algorithms are applied to the two-dimensional visualization of brain fMRI data, which can be used as a supplementary method for traditional cortical expansion maps and expansion maps.

Description

technical field [0001] The method belongs to the technical field of biomedical image pattern recognition, and specifically relates to a dimensionality reduction visualization method for functional magnetic resonance image data. Background technique [0002] In recent years, blood oxygenation level-dependent functional magnetic resonance imaging (BOLD-fMRI) technology has developed rapidly. Compared with other existing brain functional imaging techniques, fMRI not only has higher temporal resolution, but also spatial resolution can reach millimeter level. Therefore, we can use fMRI to accurately and reliably localize specific cortical regions of brain activity. In order to visualize the cortical regions of these brain activities, the visualization of fMRI data is particularly important. [0003] The two-dimensional visualization of functional magnetic resonance data refers to the presentation of the processed and analyzed fMRI data in a two-dimensional plane in an intuitive...

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): G06T11/00
CPCG06T11/005G06T2207/10088G06T2207/20081
Inventor 陈华富颜红梅王冲黄伟
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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