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

Biomarker mining method based on multi-atlas neuroimaging data

A biomarker and multi-atlas technology, which is applied in the field of biomarker mining based on multi-atlas neuroimaging data, can solve the problems of inability to consider sample weight information, multi-atlas information, wrong diagnosis and classification of Alzheimer's disease, etc. To achieve the effect of reducing the fine-tuning process and stable performance

Active Publication Date: 2022-03-01
HEBEI UNIV OF TECH
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention overcomes the defect that in the existing Alzheimer's disease classification technology, sample weight information and multi-atlas information cannot be considered, and it is easy to make mistakes in the diagnosis and classification of Alzheimer's disease

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
  • Biomarker mining method based on multi-atlas neuroimaging data
  • Biomarker mining method based on multi-atlas neuroimaging data
  • Biomarker mining method based on multi-atlas neuroimaging data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0043] The method for mining biomarkers based on multi-atlas neuroimaging data in this embodiment uses WILL's multi-atlas neuroimaging feature selection method to mine biomarkers, and then uses multi-core support vector machines for fusion classification. The specific steps as follows:

[0044] The first step, multi-atlas neuroimaging data preprocessing:

[0045] The entire brain of the sample is scanned by functional magnetic resonance to obtain the change value of the blood oxygen level-dependent signal of the entire brain region over a period of time, and then the sample data is registered to the three brain atlases to obtain the functions of the three brain atlases Magnetic resonance imaging data, and construct a functional brain network through the Pearson correlation coefficient; the three brain atlases are: Brainnetome atlas divides the brain into 263 brain regions, Power atlas divides the brain into 264 brain regions, and Stanford atlas divides the brain into For 470 ...

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 biomarker mining method based on multi-atlas neuroimaging data, relates to a method for identifying graphics, which can simultaneously consider high-order complementary relationships between multiple atlases and sample weight information, and adopts weight-based low-rank learning Multi-atlas feature selection method for feature analysis of neuroimaging data. This method adopts the method of first-order neighborhood aggregation, takes the sum of all connection strengths of each brain region as the feature of the brain region, and uses the loop iteration method to make the selected features more stable, and finally uses the multi-core support vector machine to The selected features are fused and classified to improve the diagnostic accuracy of Alzheimer's disease. The present invention overcomes the defect that the existing Alzheimer's disease classification technology cannot consider sample weight information and multi-atlas information, and is easy to misclassify Alzheimer's disease diagnosis.

Description

technical field [0001] The technical solution of the present invention relates to a method for recognizing patterns, in particular to a biomarker mining method based on multi-atlas neuroimaging data. Background technique [0002] Alzheimer's disease, also known as senile dementia, is a neurodegenerative disease of the brain and is irreversible. It can destroy human memory and other important physiological functions, and it is more common in the elderly. According to the development of the cognitive model and the degree of functional impairment, the onset of Alzheimer's disease can be divided into three stages: normal people, mild cognitive impairment and Alzheimer's disease. Clinically, it is mainly manifested as the decline of learning and living ability, memory impairment and forgetfulness, and is often accompanied by various daily behavior disorders. Therefore, patients in the middle and late stages will suffer from various inconveniences and endless pains, and even lif...

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): G16H50/70G16H50/20G06V10/80A61B5/055A61B5/00
CPCG16H50/70G16H50/20A61B5/0042A61B5/4088A61B5/055G06F18/2411
Inventor 郝小可姜涛李杰王如雪师硕闵虹杰温鹏肖云佳李想
Owner HEBEI UNIV OF TECH
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