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

Brain/MINDS Marmoset Brain Atlas 2.0: Population Cortical Parcellation With Multi-Modal Templates.

Scientific data·2026
Same author

A Deep Learning-based Pipeline for Segmenting the Cerebral Cortex Laminar Structure in Histology Images.

Neuroinformatics·2024
Same author

A Novel Directed Seed-Based Connectivity Analysis Toolbox Applied to Human and Marmoset Resting-State FMRI.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2024
Same author

Commonality and variance of resting-state networks in common marmoset brains.

Scientific reports·2024
Same author

A reappraisal of the default mode and frontoparietal networks in the common marmoset brain.

Frontiers in neuroimaging·2024
Same author

Group Surrogate Data Generating Models and similarity quantification of multivariate time-series: A resting-state fMRI study.

NeuroImage·2023

Related Experiment Video

Updated: Oct 10, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.2K

Vector Auto-Regressive Deep Neural Network: A Data-Driven Deep Learning-Based Directed Functional Connectivity

Takuto Okuno1, Alexander Woodward1

  • 1Connectome Analysis Unit, RIKEN Center for Brain Science, Wako, Japan.

Frontiers in Neuroscience
|December 13, 2021
PubMed
Summary

We developed a novel deep learning framework, Vector Auto-Regressive Deep Neural Network (VARDNN), for estimating directed functional connectivity (dFC) in the brain. VARDNN outperforms existing methods and accurately identifies brain changes in Alzheimer's disease patients.

Keywords:
Alzheimer’s diseaseGranger causalitydirected functional connectivityfMRIvector auto-regressive deep neural network

More Related Videos

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

1.3K
Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms
08:36

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

7.4K

Related Experiment Videos

Last Updated: Oct 10, 2025

Modeling the Functional Network for Spatial Navigation in the Human Brain
05:55

Modeling the Functional Network for Spatial Navigation in the Human Brain

Published on: October 13, 2023

1.2K
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

1.3K
Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms
08:36

Dynamic Inter-subject Functional Connectivity Reveals Moment-to-Moment Brain Network Configurations Driven by Continuous or Communication Paradigms

Published on: March 21, 2019

7.4K

Area of Science:

  • Neuroscience
  • Computational Neuroscience
  • Machine Learning

Background:

  • Elucidating causal relationships in brain regions is crucial for understanding functional circuitry and diagnosing neurological conditions.
  • Current functional connectome estimation methods lack the integration of advanced deep learning architectures.
  • A need exists for innovative approaches to accurately map brain connectivity.

Purpose of the Study:

  • To introduce a novel deep learning framework, Vector Auto-Regressive Deep Neural Network (VARDNN), for functional connectome estimation.
  • To develop new directed functional connectivity (dFC) measures based on the VARDNN architecture.
  • To evaluate the performance of VARDNN-based measures against existing methods and apply them to clinical fMRI data.

Main Methods:

  • Developed a Vector Auto-Regressive Deep Neural Network (VARDNN) architecture comprising interconnected deep neural network nodes.
  • Introduced two novel directed functional connectivity (dFC) measures: VARDNN-DI and VARDNN-GC.
  • Validated VARDNN measures against established methods like partial correlation and Granger causality using simulated and real fMRI data.

Main Results:

  • VARDNN-based dFC measures demonstrated superior performance compared to existing techniques, particularly with increasing numbers of brain regions.
  • The VARDNN-DI measure successfully identified lesioned regions in Alzheimer's disease (AD) subjects, consistent with prior research.
  • VARDNN effectively differentiated between healthy controls and AD patients in a subject-wise evaluation using fMRI data.

Conclusions:

  • The VARDNN framework offers a powerful and effective approach for whole-brain directed functional connectivity estimation.
  • VARDNN-based methods show significant potential for diagnosing neurological disorders and understanding brain circuitry.
  • An open-source VARDNN toolbox is available for researchers to conduct functional connectome analyses.