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

Brain atlas individualization method and system based on magnetic resonance and twin graph neural network

A neural network and brain map technology, applied in medical science, diagnosis, diagnostic recording/measurement, etc., can solve the problems of slow convergence of iterative schemes and long reconstruction time, and achieve the goals of reducing reconstruction time, improving variance, and ensuring consistency Effect

Active Publication Date: 2022-07-19
ZHEJIANG LAB
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above scheme still has some disadvantages, such as only considering the characteristics of a single fMRI data node or its first-order domain node, and its iterative scheme converges slowly and takes a long time to reconstruct

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 atlas individualization method and system based on magnetic resonance and twin graph neural network
  • Brain atlas individualization method and system based on magnetic resonance and twin graph neural network
  • Brain atlas individualization method and system based on magnetic resonance and twin graph neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0039] The invention provides a brain atlas individualization method and system based on magnetic resonance and twin graph neural network, which can express the differences between individuals as much as possible under the condition of ensuring the consistency of the functional areas of the subjects. Construct functional connectivity and adjacency matrices based on subject rs-fMRI data and T1-weighted MRI data as model input; use group atlas to design sampling masks to obtain regions with relatively high consistency as sampling regions, and introduce these two into into the loss function; design a reconstruction model based on the twin graph neural network for training; finally, since the brain map has no real value as an evaluation, select some indicators that can evaluate the rationality of the individual brain map, such as evaluati...

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 atlas individualization method and system based on magnetic resonance and twin graph neural network. First, the resting state functional magnetic resonance data (rs-fMRI) is extracted by using the functional connection based on the region of interest, and at the same time Perform Fisher transformation and exponential transformation on the feature; secondly, extract the corresponding adjacency matrix from the T1-weighted magnetic resonance data in the dataset; As output, a Siamese graph neural network is designed for training and testing. Compared with other rs-fMRI individualized atlas schemes, the present invention utilizes the data characteristics of rs-fMRI and group atlas to design the individualized brain map reconstructed by the twin network architecture and the central sampling mode on task-state magnetic resonance data. The activation distribution is more uniform, while having a shorter reconstruction time.

Description

technical field [0001] The present invention relates to the field of medical imaging and deep learning, in particular to a method and system for individualizing a brain atlas based on a magnetic resonance and twin graph neural network. Background technique [0002] The cerebral cortex provides an important foundation for human perception, movement, and other cognitive functions. In neuroscience, brain division is of great significance for the cognition, localization and analysis of brain function. [0003] Cerebral cortical regions exhibit different functions, structures, connections, and topologies, and thus can be partitioned by means of clustering. There are quite a few non-invasive methods to obtain relevant information in the cerebral cortex, such as magnetic resonance imaging (MRI), magnetoencephalography (MEG), and so on. Among them, MRI has become a widely used imaging technology due to its relatively high spatial and temporal resolution and no radiation. Resting-...

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): A61B5/055A61B5/245A61B5/00
CPCA61B5/055A61B5/245A61B5/7264A61B5/7267A61B5/4064G06T7/0012G06T2207/10088G06T2207/20084G06T2207/30016
Inventor 张瑜邱文渊李军陈子洋孙超良李劲松
Owner ZHEJIANG LAB
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