Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Brain fiber clustering method based on space path similarity

A clustering method and spatial path technology, applied in the research field of brain nerve fibers, can solve the problems of intricate fibers and the inability to visualize and analyze fiber trajectories, and achieve the effect of reducing errors

Active Publication Date: 2017-05-31
ZHEJIANG UNIV OF TECH
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Through the tracking of fibers, people have been able to obtain thousands of fibers in the brain. However, these fibers are intricate and obstruct each other, and people cannot directly observe the organizational structure of brain fibers with the naked eye.
Due to the complexity of fibers, people cannot visualize and analyze fiber trajectories well. How to cluster and render a large number of fiber trajectories is still a very important issue.

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
  • Brain fiber clustering method based on space path similarity
  • Brain fiber clustering method based on space path similarity
  • Brain fiber clustering method based on space path similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical scheme of the present invention will be further explained below in conjunction with the drawings.

[0037] The brain fiber clustering method based on spatial path similarity of the present invention includes the following steps:

[0038] 1) Import fiber data, track the fiber path, and calculate the similarity of each fiber;

[0039] 2) Due to the diversity of fiber data, some tissues have relatively scattered fibers and a small number of fibers, and some tissues have relatively dense fibers with a very large number of fibers. According to the size of the fiber data, two different fiber clustering methods are used: DPC (NGK) fiber clustering method and DPC (GK) fiber clustering method.

[0040] 2.1) For simple fiber data, the amount of fiber data is small, and the DPC (NGK) fiber clustering method is adopted: the clustering algorithm is quickly searched according to the density peak point, that is, the DPC algorithm, and the corresponding density threshold and radi...

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 brain fiber clustering method based on space path similarity. The method comprises the following steps: 1) importing fiber data, tracing a fiber path, and calculating the similarity of each fiber; 2) respectively using two different fiber clustering methods according to the fiber data volume, namely a DPC (NGK) fiber clustering method and a DPC (GK) fiber clustering method because the fiber data is diversified, fibers of one part of tissues are relatively disperse and the fiber quantity is small, and fibers of another part of tissues are relatively dense and the fiber quantity is extremely large; and 3) mapping the clustered fiber data to a corresponding color space, and performing color encoding and visualized display, thereby achieving the effect of obviously distinguishing different types of fibers.

Description

Technical field [0001] The invention relates to the study of brain nerve fibers, and is a brain fiber clustering method based on spatial path similarity. Background technique [0002] The dispersion of water molecules is the basis of nuclear magnetic resonance technology. DWI, DTI and HARDI non-invasive detection technologies are all developed on the basis of dispersion and diffusion of water molecules. Through MRI technology, people can already track the direction of brain white matter fibers. DTI is the most commonly used MRI technique to detect the white matter structure of the brain, but its model is limited by Gaussian hypothesis and cannot solve the problem of multi-fiber crossing. HARDI technology describes the displacement process of water molecules as a mixture of Gaussian models, and compensates for the shortcomings of DTI technology by calculating the characteristic direction and characteristic value of the dispersion tensor of each component. Can better describe the...

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 Applications(China)
IPC IPC(8): G06F19/00G06K9/62
CPCG16H50/70G06F18/2321
Inventor 梁荣华李志鹏徐超清池华炯孙国道
Owner ZHEJIANG 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
Eureka Blog
Learn More
PatSnap group products