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

FMRI data feature selection method based on stability selection

A technology of data characteristics and stability, applied in the field of biomedical image pattern recognition, can solve problems such as weak error correction ability, high time-consuming, errors, etc., and achieve the effect of auxiliary diagnosis and treatment

Inactive Publication Date: 2016-08-24
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF2 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, both the Randomized Ward Logistic algorithm and the RSS algorithm rely too much on the clustering algorithm, and the error correction ability for the errors introduced by clustering is weak; and for high-dimensional data, the clustering method is computationally intensive and time-consuming.

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
  • FMRI data feature selection method based on stability selection
  • FMRI data feature selection method based on stability selection
  • FMRI data feature selection method based on stability selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] 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 intended to limit the application scope of the present invention.

[0027] The specific implementation steps are as follows:

[0028] Step 1: Simulation data construction. Each sample is fully characterized by a 100*100 voxel fMRI image. We generate a total of two groups of 50 samples each. Among the 100*100 features of these two groups of samples, there are five 10*10 block-shaped difference regions, such as figure 2 The sub-figures of true differential features are shown by the white squares in the sub-figures. The specific construction method is as follows:

[0029] The first two blocks: by (First group), (Second group) construction, where i=1,2,...,50 corresponds to 50 samples of each group, k=1,2 corresponds to the number of ...

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 belongs to the technical field of biomedicine image pattern recognition and specifically relates to an fMRI data feature selection method based on stability selection. The method comprises the following steps: obtaining grouping information in a random manner according to correlation between spatial neighborhood features; selecting samples randomly to obtain feature matrixes based on groups; then, solving weight of each group through a Lasso model, obtaining weight of each feature and furthermore, updating score vector of each feature; repeating the steps above for many times to obtain accumulated score vectors of the features; and then, carrying out feature ordering and selection. The method has the advantages of being simple to calculate, high in feature selection accuracy and high in error control capability and the like, and provides a new effective technique for feature ordering and selection in the fields of magnetic resonance data pattern recognition and the like.

Description

technical field [0001] The invention belongs to the technical field of biomedical image pattern recognition, and in particular relates to a feature selection method for functional magnetic resonance imaging (fMRI). Background technique [0002] At present, brain functional imaging technology has been widely used, among which functional magnetic resonance imaging fMRI is developed on the basis of magnetic resonance imaging (magnetic resonance imaging, MRI) technology, through functional magnetic resonance imaging technology for many physiological and It is a non-invasive means of detecting and imaging brain functional activity. [0003] The pattern recognition system is mainly composed 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. fMRI data ha...

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): G06T7/00G06K9/62
CPCG06T7/0012G06T2207/10088G06T2207/30016G06F18/2111
Inventor 高晴隋煜陈华富
Owner UNIV OF ELECTRONIC 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