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

A method for constructing an ICA-CNN classification framework for resting-state complex fMRI data from patients and healthy subjects

A healthy person, resting state technology, applied in the field of biomedical signal processing, can solve the problem of fMRI data shortage and other problems, achieve the effect of reducing the amount of training and improving the accuracy rate

Active Publication Date: 2021-11-05
DALIAN UNIV OF TECH
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a resting-state complex fMRI data ICA-CNN framework for classification of patients and healthy persons, which effectively solves the problem of fMRI data shortage

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 method for constructing an ICA-CNN classification framework for resting-state complex fMRI data from patients and healthy subjects
  • A method for constructing an ICA-CNN classification framework for resting-state complex fMRI data from patients and healthy subjects
  • A method for constructing an ICA-CNN classification framework for resting-state complex fMRI data from patients and healthy subjects

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Combined with the following technical solutions and attached figure 1 , describe a specific embodiment of the present invention in detail.

[0032] Existing K 1 = 42 patients with schizophrenia and K 2 = 40 healthy people (K = K 1 +K 2 =82) Complex fMRI data acquired at rest. In the time dimension, T=146 scans were performed, each scan obtained 53×63×46 whole brain data, and the number of voxels in the brain was V=62336. The steps of adopting the present invention to identify patients with schizophrenia and healthy people are as attached figure 1 shown.

[0033] Step 1: Input multi-subject resting-state complex fMRI data and the category of the subjects

[0034] Step 2: For all single subjects Z k Perform PCA dimension reduction, the model order N is from 20 to 140, and take a value every 10, that is, l=13, and obtain 13 different model order N dimensionality reduction data

[0035] Step 3: For all model orders First use the complex EBM algorithm to p...

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 method for constructing an ICA‑CNN classification frame of resting-state complex fMRI data of patients and healthy people, belonging to the field of biomedical signal processing. The present invention takes the functional network of interest separated from resting-state complex fMRI data by ICA as the research object, uses 2D CNN learning features with fewer parameters, and realizes the classification of patients and healthy people; Data augmentation was performed on ICA results to solve the problem of fMRI data shortage. Compared with the existing 3D CNN network, it not only reduces the amount of training, but also improves the accuracy. For example, for the complex fMRI data collected in the resting state of 82 subjects, applying the DMN components extracted by ICA, the slice recognition accuracy rate is higher than that of 3D CNN (0.728vs 0.701), and the subject recognition obtained after the subjects' decision-making is accurate The rate was further improved (0.914vs 0.701).

Description

technical field [0001] The present invention relates to the field of biomedical signal processing, in particular to independent component analysis (ICA) and convolutional neural network ( convolutional neural networks (CNN) classification framework. Background technique [0002] Resting-state fMRI (resting-state fMRI, rs-fMRI) has been widely used in the study of brain function and disease due to its advantages of high resolution, non-invasive, and easy acquisition on patient subjects. Previous studies have shown that rs-fMRI is valuable in extracting brain function information related to neurological diseases. More importantly, due to the additional use of unique phase information, resting-state complex fMRI data contains more brain function information than amplitude fMRI data, and has more potential in the study of brain function and diseases. [0003] At present, deep learning has shown great advantages in the diagnosis of many neurological diseases, including schizoph...

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): G06K9/62G06N3/04
CPCG06N3/045G06F18/2134G06F18/2135G06F18/214
Inventor 林秋华邱悦
Owner DALIAN 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