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

Feature selection method for FMRI (Functional Magnetic Resonance Imaging) data

A feature selection method and data technology, applied in the field of biomedical image pattern recognition, can solve problems such as inability to be detected well, and achieve the effect of stable feature importance measurement, overcoming limitations, and good fault tolerance

Inactive Publication Date: 2015-04-08
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF1 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the strong correlation between neighboring voxels in the brain, stable selection is a purely sparse method and does not detect this structure well

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
  • Feature selection method for FMRI (Functional Magnetic Resonance Imaging) data
  • Feature selection method for FMRI (Functional Magnetic Resonance Imaging) data
  • Feature selection method for FMRI (Functional Magnetic Resonance Imaging) data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] 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.

[0030] A feature selection method for FMRI data, the specific implementation steps are as follows:

[0031] Step A: Simulation data construction. Generate a 70*63 voxel fMRI image, where each voxel contains a zero-mean sequence of 160 time points. Construct three kinds of block stimulus time series (add Gaussian noise with signal-to-noise ratio equal to 2) and add them to the feature areas A, B, C, D, E respectively. The corresponding relationship between the block stimulus and the feature area is as follows: figure 1 , the location of the feature region such as figure 2 . We regard each time point as a sample and each voxel as a feature, so the final simulation data dimension is 160...

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 feature selection method for FMRI (Functional Magnetic Resonance Imaging) data, belongs to the technical field of biomedical image mode identification, and particularly relates to the feature selection method of a functional magnetic resonance image. The method comprises the following steps of randomly selecting a submatrix of data, calculating the weight vectors of selected features by using an elastic net method, and converting the obtained weight vectors into stable score vectors; repeating the process p (p is greater than 1,000) times to obtain the selected time vector of each feature, acquiring feature importance metrics according to the calculated accumulated stable score vectors and time vectors, and performing feature sequencing and selection. The method disclosed by the invention has the characteristics of high fault tolerance, high stability and the like. A novel effective technology is provided for feature selection and sequencing in the fields of magnetic resonance data mode identification and the like.

Description

technical field [0001] The method belongs to the technical field of biomedical image pattern recognition, and specifically relates to a feature selection method of functional magnetic resonance images. Background technique [0002] Resting-state functional magnetic resonance refers to the study of the spontaneous activity of brain neurons using blood oxygen level-dependent (BOLD) functional magnetic resonance imaging technology in a quiet resting state without specific cognitive tasks. [0003] The pattern recognition system mainly consists of four parts: data acquisition, data preprocessing, feature selection and extraction, and classification decision-making. Among them, feature selection and extraction is to select and extract the features that best reflect the nature of classification based on the original data. Due to the high-dimensional and small sample characteristics of magnetic resonance data, which contains a large number of redundant features that are meaningles...

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): G06K9/00G06K9/62
Inventor 陈华富李志强王亦伦
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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