A feature extraction method for Alzheimer's disease brain network based on continuous homology technology

A network feature, brain network technology, applied in the field of brain network analysis, can solve the problems of poor calculation accuracy, lack of clear selection rules, heavy calculation load, etc., and achieve the effect of reducing the calculation load

Active Publication Date: 2022-04-19
HARBIN ENG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But this method mainly has two deficiencies: (1) threshold selection problem
The threshold value of the graph theory method is selected by artificial selection strategy, and there is no clear selection rule, and the functional network constructed based on a selected threshold value lacks accuracy; (2) the basis of the graph theory method is to abstract the network into a pairwise interconnection mode, but this method has a large computational load and is only suitable for large-scale brain region segmentation methods. When faced with small and medium-scale brain network partition strategies, it shows disadvantages such as poor calculation accuracy and poor stability. The research must go deep into the microscopic field, and the graph theory method has gradually shown its shortcomings

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 feature extraction method for Alzheimer's disease brain network based on continuous homology technology
  • A feature extraction method for Alzheimer's disease brain network based on continuous homology technology
  • A feature extraction method for Alzheimer's disease brain network based on continuous homology technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] to combine figure 1 , the realization of the present invention comprises the following steps:

[0029] (1) The diagnosis of Alzheimer's disease requires functional magnetic resonance scanning for further diagnosis. Extract the resting state functional magnetic resonance data of the patient. The data imaging adopts a 3T magnetic resonance scanner, the deflection angle is 77°, the repetition time TR is 2m, the recovery time is 32ms, the imaging matrix is ​​64×64, and the field of view FOV is 256×256mm 2 , the number of scanning layers is 34, the volume imaging is 150, and the voxel thickness is 4mm. SPM8 is used to complete time layer correction, head movement correction, standardization, smoothing and other processing, and DPABI is used to complete covariate removal and local consistency verification.

[0030](2) Select the AAL (Anatomical Automatic Labeling) brain network segmentation template, divide the brain into 90 functionally specific local ROI brain regions, ab...

Embodiment 2

[0050] Step 1: Data preprocessing. Magnetic resonance scans were performed on patients with Alzheimer's disease to obtain resting-state functional magnetic resonance data. And preprocessing work such as time layer correction, head motion correction, standardization, smoothing and removal of covariates is performed on the obtained magnetic resonance time series data.

[0051] Step 2: Brain network division. Select the brain region segmentation template, physically segment the whole brain map, and determine the nodes in the brain network connection. For the brain region segmentation results of each node, extract the preprocessed time series data in step 1, and perform overall mean value processing on the time series of each voxel in each brain region to obtain a set of time series values.

[0052] Step 3: Brain network construction. Using the mean value of the time series of each brain region node obtained in step 2, do a temporal correlation analysis between different brain ...

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 extraction method for Alzheimer's disease brain network based on persistent coherence technology, which belongs to the technical field of brain network analysis; the invention uses data preprocessing, brain network division, brain network construction, and continuous coherence to construct brain network filtering Statistical analysis of flow and continuous interval data and feature extraction of Alzheimer's disease brain network realize the feature extraction of the patient's brain network; the invention avoids the threshold selection problem in the graph theory method by constructing a multi-scale brain network with variable threshold; Among them, the continuous feature discovery mechanism of network complex flow can also effectively reduce the computational burden, and is an effective brain network analysis technology. It is an innovative research idea to apply the continuous homology theory to the brain analysis of Alzheimer's disease patients to study the brain mechanism and discover the characteristics of the brain network connection of the disease. , Diagnosis and treatment plan formulation is of great significance.

Description

technical field [0001] The invention belongs to the technical field of brain network analysis, and in particular relates to a feature extraction method for Alzheimer's disease brain network based on continuous coherence technology. Background technique [0002] Alzheimer's disease (Alzheimer's disease, AD) is a common neurological disease in the elderly, which mainly affects the central nervous system in the brain of the elderly, causing degenerative changes. When patients have obvious clinical symptoms of Alzheimer's disease, most of the disease has entered the advanced stage and cannot be treated at all. Therefore, the early diagnosis and intervention of Alzheimer's disease has become the focus of most researches. [0003] Research on the early diagnosis of Alzheimer's disease mainly focuses on the extraction of marker features, including neuropsychological features and biological features. Neuropsychological characteristics, oriented to the diagnosis of AD with clinical...

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): G06T7/00G06T7/10
Inventor 李金边晨源梁洪鲍佩华何兵兰海青王铮李延召罗昊燃高岳
Owner HARBIN ENG UNIV
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