Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

PE-RBNAS: A robust neural architecture search with progressive-enhanced strategies for brain network classification.

Medical image analysis·2025
Same author

Triplet-Based Deep Hashing Incremental Learning for Brain Network Classification.

IEEE journal of biomedical and health informatics·2025
Same author

CSBNC-PAL: Consistency Semi-Supervised Brain Network Classification Framework With Prototypical-Adversarial Learning.

IEEE journal of biomedical and health informatics·2025
Same author

Intra- and Inter-Head Orthogonal Attention for Image Captioning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
Same author

MCAN: Multimodal Causal Adversarial Networks for Dynamic Effective Connectivity Learning From fMRI and EEG Data.

IEEE transactions on medical imaging·2024
Same author

Brain Network Evaluation by Functional-Guided Effective Connectivity Reinforcement Learning Method Indicates Therapeutic Effect for Tinnitus.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2024

Related Experiment Video

Updated: Jul 5, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.1K

MetaCAE: Causal autoencoder with meta-knowledge transfer for brain effective connectivity estimation.

Junzhong Ji1, Zuozhen Zhang1, Lu Han1

  • 1Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Institute of Artificial Intelligence, Faculty of Information Technology, Beijing University of Technology, Beijing, China.

Computers in Biology and Medicine
|January 17, 2024
PubMed
Summary

This study introduces MetaCAE, a novel machine learning method for estimating brain effective connectivity from fMRI data. MetaCAE improves accuracy on small datasets by using causal autoencoders and meta-knowledge transfer.

Keywords:
Brain effective connectivityCausal autoencoderMeta-knowledge transferMeta-learningSmall-sample fMRI data

More Related Videos

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K

Related Experiment Videos

Last Updated: Jul 5, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.1K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.7K
Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.6K

Area of Science:

  • Neuroscience
  • Machine Learning
  • Computational Neuroscience

Background:

  • Estimating brain effective connectivity from functional magnetic resonance imaging (fMRI) data is crucial in neuroscience.
  • Encoder-decoder models show promise but struggle with fMRI's non-stationarity and limited sample sizes, often leading to inaccurate causal direction identification.

Purpose of the Study:

  • To develop a novel machine learning method, MetaCAE, for accurate brain effective connectivity estimation from fMRI data.
  • To address the challenges of non-stationarity and small sample sizes inherent in fMRI datasets.

Main Methods:

  • Proposed MetaCAE utilizes a causal autoencoder (CAE) to capture causal dependencies in non-stationary fMRI time series.
  • Employs a temporal convolutional encoder for feature extraction and a structural equation model-based decoder for relationship decoding.
  • Incorporates model-agnostic meta-learning for transferring shared brain connectivity knowledge across subjects to enhance small-sample performance.

Main Results:

  • MetaCAE demonstrated superior performance in estimating brain effective connectivity compared to existing methods.
  • The approach effectively handled non-stationary fMRI data and improved accuracy with limited sample sizes.
  • Experiments on simulated and real-world fMRI data validated the efficacy of the proposed method.

Conclusions:

  • MetaCAE offers a robust solution for brain effective connectivity estimation, particularly in scenarios with non-stationary data and limited samples.
  • The integration of causal autoencoders and meta-knowledge transfer represents a significant advancement in neuroimaging analysis.
  • This method holds potential for advancing our understanding of brain network dynamics.