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

An ant colony method for constructing brain effect connection networks from fMRI and DTI data

A connection network and ant colony algorithm technology, applied in the field of brain effect connection network construction, to achieve the effect of low distribution and regularity requirements, strong anti-noise ability, and reasonable and reliable structure

Inactive Publication Date: 2018-12-18
BEIJING UNIV OF TECH
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] Aiming at the deficiencies of existing brain effect network construction methods and the new methods and challenges brought by multimodal magnetic resonance data fusion technology

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
  • An ant colony method for constructing brain effect connection networks from fMRI and DTI data
  • An ant colony method for constructing brain effect connection networks from fMRI and DTI data
  • An ant colony method for constructing brain effect connection networks from fMRI and DTI data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Set forth below the specific embodiment of the present invention and detailed steps, the frame that the present invention realizes is as follows figure 2 shown, including:

[0031] Step 1: Data Acquisition.

[0032] Firstly, in order to verify the effectiveness of this method, a set of matching simulated fMRI data and DTI data was generated using a simulation data generation method. A commonly used Dynamic Causal Modeling (DCM) model is used to generate simulated fMRI data, the model is as follows:

[0033] zt+1 =σAz t +Cu (1)

[0034] where {z t} is the neural sequence, t is the current moment, A is the standard network matrix, σ is the attenuation coefficient, C is the control matrix, and u is the external input with Gaussian noise. For example, to generate a BOLD fMRI data containing 6 brain region nodes, the process is as follows image 3 shown. Then a set of DTI data matching the fMRI data is generated. The DTI data generation principle is that the number o...

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 an ant colony method for constructing a brain effect connection network from fMRI and DTI data, which fully utilizes the relationship between brain structure and function and the characteristics of ant colony algorithm which can carry out information fusion easily. The purpose of invention is to obtain brain effect connection network which is more suitable for brain physiological structure by combining brain structure information and functional information with ant colony algorithm to search the brain effect connection network. The method comprises the following steps:preprocessing two sets of magnetic resonance data and selecting the same region of interest; using DTI data to obtain the structure constraint information of ROI, and using the structure information to compress the searching space of ant colony to avoid a lot of unnecessary searching of ant colony. Then the structure information is fused into the heuristic function in the ant colony random searchto enhance the purpose of ant search and improve the optimization efficiency of the algorithm. Finally, the ant colony algorithm searches for the best matching brain effect connection network with fMRI data by iterative search. This method accurately identifies the brain effect connection network.

Description

technical field [0001] The invention relates to a brain effect connection network construction method of fMRI functional magnetic resonance imaging data and DTI diffusion tensor imaging data, in particular to an ant colony learning method based on multimodal information fusion. Background technique [0002] Magnetic resonance imaging (MRI) is a medical imaging technique with high spatial resolution and high tissue contrast. Among them, structural magnetic resonance imaging (sMRI), magnetic resonance diffusion tensor imaging (DTI), functional magnetic resonance imaging (functional magnetic resonance imaging, fMRI) and other multimodal magnetic resonance imaging techniques can non-invasively The structure and functional connection information of the human brain can be obtained systematically from different aspects such as gray matter, white matter fibers, and blood oxygenation levels, which provides favorable conditions for experimental research in cognitive neuroscience, and ...

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): G06N3/00G16H50/70G06K9/62
CPCG06N3/006G16H50/70G06F18/25
Inventor 冀俊忠刘金铎
Owner BEIJING 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