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

Do spatial navigation and episodic memory rely on the same systems? Evidence from a naturalistic experience with children and adults.

Journal of experimental psychology. General·2025
Same author

The Cerebellum and Striatum in Reward Processing: Caring About Being Right vs. Caring About Reward.

bioRxiv : the preprint server for biology·2025
Same author

Language and the Cerebellum: Structural Connectivity to the Eloquent Brain.

Neurobiology of language (Cambridge, Mass.)·2024
Same author

An <i>in vivo</i> Dissection, and Analysis of Socio-Affective Symptoms related to Cerebellum-Midbrain Reward Circuitry in Humans.

bioRxiv : the preprint server for biology·2024
Same author

A Social Network Analysis of Hemodialysis Clinics: Attitudes Toward Living Donor Kidney Transplant among Influential Patients.

Kidney360·2024
Same author

The backbone network of dynamic functional connectivity.

Network neuroscience (Cambridge, Mass.)·2022

Related Experiment Video

Updated: Jul 26, 2025

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.3K

A transformer model for learning spatiotemporal contextual representation in fMRI data.

Nima Asadi1, Ingrid R Olson2,3, Zoran Obradovic1

  • 1Department of Computer and Information Sciences, College of Science and Technology, Temple University, Philadelphia, PA, USA.

Network Neuroscience (Cambridge, Mass.)
|June 19, 2023
PubMed
Summary

This study introduces a novel transformer-based framework for learning representations from functional Magnetic Resonance Imaging (fMRI) data. The approach effectively captures spatiotemporal context for improved downstream analysis.

Keywords:
Attention mechanismDeep learningDynamic functional connectivityFeature learningGraph convolution networksTransformer models

More Related Videos

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

1.1K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.7K

Related Experiment Videos

Last Updated: Jul 26, 2025

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.3K
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

1.1K
Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.7K

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Data Science

Background:

  • Representation learning is crucial for analyzing complex data like fMRI.
  • fMRI data presents challenges due to dynamic dependencies and spatiotemporal complexities.
  • Contextually informative representations are vital for accurate fMRI analysis.

Purpose of the Study:

  • To propose a novel framework for learning fMRI data embeddings.
  • To leverage spatiotemporal contextual information within fMRI data.
  • To enhance feature extraction for downstream neuroimaging tasks.

Main Methods:

  • A framework based on transformer models is proposed.
  • The approach integrates multivariate BOLD time series and functional connectivity networks.
  • Attention mechanisms and graph convolutional neural networks are employed to capture spatiotemporal context.

Main Results:

  • The framework generates meaningful features from fMRI data.
  • Demonstrated benefits on two resting-state fMRI datasets.
  • The proposed method offers advantages over existing architectures.

Conclusions:

  • The developed framework effectively learns informative representations from fMRI data.
  • This approach enhances the analysis of complex neuroimaging datasets.
  • The method shows promise for various downstream applications in neuroscience.