fMRI data classification and identification method and device based on brain area function connection

A technology of data classification and recognition methods, which is applied in image data processing, character and pattern recognition, image analysis, etc., and can solve problems such as the curse of dimensionality

Active Publication Date: 2021-01-15
NANJING UNIV OF TECH
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods construct brain functional connectivity matrix based on all brain regions. However, the signal changes of R-fMRI image data only exist in some brain r...

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 classification and identification method and device based on brain area function connection
  • fMRI data classification and identification method and device based on brain area function connection
  • fMRI data classification and identification method and device based on brain area function connection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0024] This embodiment provides a method for classifying and identifying fMRI data based on the functional connectivity of brain regions. According to the determined subject of fMRI data classification and identification, the subject's fMRI data is divided into two corresponding categories: Class A and Class B, such as figure 1 As shown, the data classification identification method mainly includes the following steps:

[0025] Step 1: fMRI data acquisition: According to the object to be studied, the brain images of the subjects are divided into Type A and Type B, and the resting-state functional magnetic resonance imaging data of Type A and Type B subjects are obtained;

[0026] Step 2: Preprocess the acquired R-fMRI brain image data by DPARSF software to achieve data standardization and eliminate external interference signals, including slice time layer correction, head motion correction, spatial standardization, spatial smoothing, linear trend elimination, time Bandpass fil...

Embodiment 2

[0076]This embodiment provides a specific method for fMRI feature extraction and recognition based on the functional connectivity of partial brain regions. For example, autism is determined to be the subject of fMRI data classification and recognition, and fMRI data is divided into Class A and Class B, representing the brain respectively. The steps to connect abnormal subjects and normal brain connections are as follows:

[0077] Step 1: Select R-fMRI brain images of 184 subjects provided by NYU Langone Medical Center from ABIDE (http: / / fcon_1000.projects.nitrc.org / indi / abide / abide_I.html) , the age distribution of the subjects is under the age of 18. Among them, there were 79 Type A subjects, with a male-to-female ratio of 68 / 11, an average age of 14.52 years, and an average PIQ (Performance Intelligence Quotient) of 104; there were 105 Type-B subjects, with a male-to-female ratio of 79 / 26, an average age of 9.46 years, and a PIQ of 104. Mean 113.

[0078] Step 2: Use DPARS...

Embodiment 3

[0115] This embodiment provides an fMRI data classification and identification device based on functional connectivity of brain regions, which can implement the method described in Embodiment 1, and the device includes:

[0116] Brain image acquisition module: used to acquire brain magnetic resonance imaging (fMRI) data of subjects;

[0117] Data preprocessing module: used to preprocess the acquired brain magnetic resonance imaging data to obtain brain gray matter images;

[0118] Brain partitioning module: used to divide the gray matter image of the brain into multiple brain regions with different functions, and extract the average voxel time series of each brain region;

[0119] Brain region selection module: used to select some brain regions with significant differences from multiple functional brain regions based on fuzzy decision-making rough sets;

[0120] Transformation matrix module: used to calculate the Pearson correlation coefficient between different brain regions...

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 designs an fMRI data classification and recognition method and device based on brain area function connection. The method comprises the steps: acquiring fMRI data of a testee; preprocessing the obtained fMRI data to obtain a brain gray matter image; segmenting the brain gray matter image into a plurality of brain regions with different functions, and extracting an average voxel timesequence of each brain region; based on the fuzzy decision rough set, selecting a part of brain regions with significant differences from the plurality of functional brain regions; calculating Pearsoncorrelation coefficients among different brain regions based on the selected partial brain regions, and performing nonlinear processing on the coefficients by adopting Fisher-z transform to obtain afunctional connection matrix of the partial brain regions; sparsifying the correlation coefficient values in the matrix, reserving the correlation coefficient values above a threshold value, and expanding the matrix into a one-dimensional feature vector; and taking the obtained one-dimensional feature vector as input and sending the one-dimensional feature vector to a trained SVM recognition modelto obtain an output label of the testee and judge the fMRI data category of the testee.

Description

technical field [0001] The invention belongs to the technical field of data classification and recognition, and in particular relates to a fMRI data classification and recognition method based on brain region functional connections. Background technique [0002] In recent years, the rapid development of medical imaging has provided very important clinical reference value for the analysis of brain imaging data and the observation of brain activity status, which has brought the research of human brain into a new stage. Currently, the methods used to study brain activity mainly include: functional magnetic resonance imaging (fMRI), electroencephalography (EEG), magnetoencephalography (MEG), electron emission tomography (PET), single photon emission tomography (SPECT), etc. . Among them, fMRI technology is a non-radioactive and non-invasive means of detecting the dynamic activity of brain function, with high temporal and spatial resolution, and has become the most commonly used...

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): G06T7/00G06T7/11G06K9/62
CPCG06T7/0012G06T7/11G06T2207/10088G06T2207/20081G06T2207/30016G06F18/2411Y02D10/00
Inventor 王莉尹晓东丁杰梅雪沈捷
Owner NANJING UNIV OF 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