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

Lag-adjusted functional network connectivity reveals sensorimotor and higher cognitive network alterations in depression.

Research square·2026
Same author

MindGrab: A spectrally-motivated architecture for accessible deep learning in neuroimaging.

NeuroImage·2026
Same author

Robustness of NeuroMark-derived functional networks to fMRI spatial normalization across the human lifespan.

NeuroImage·2026
Same author

Structural co-modulation: An individualized measure of inter-component interactions in source-based morphometry.

NeuroImage·2026
Same author

Measuring the Impacts of Urbanicity and Different Exposome Factors on Human Brain through Exposure Network Mapping.

Neuroscience bulletin·2026
Same author

Large-scale brain dynamics are organized by a directional coordination hierarchy.

bioRxiv : the preprint server for biology·2026

Related Experiment Video

Updated: Jul 28, 2025

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.8K

GLACIER: GLASS-BOX TRANSFORMER FOR INTERPRETABLE DYNAMIC NEUROIMAGING.

Usman Mahmood1,2, Zening Fu1,2, Vince Calhoun1,3

  • 1Tri-institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, USA.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)
|June 2, 2023
PubMed
Summary

We developed a transparent deep learning model for neuroimaging. This interpretable "glass-box" model accurately estimates dynamic brain connectivity from functional MRI data, outperforming existing methods.

Keywords:
Interpretable DLfMRIneuroimaging

More Related Videos

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

7.3K
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

8.9K

Related Experiment Videos

Last Updated: Jul 28, 2025

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.8K
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

7.3K
Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models
14:14

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

8.9K

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Machine Learning

Background:

  • Deep learning models excel at tasks but are often "black boxes", limiting their use in interpretable fields like neuroimaging.
  • Lack of transparency in deep learning hinders application in neuroimaging where interpretability is crucial.

Purpose of the Study:

  • Introduce a novel "glass-box" deep learning model for neuroimaging applications.
  • Enable transparent and interpretable analysis of brain connectivity using deep learning.

Main Methods:

  • Developed a deep learning model that integrates spatial and temporal dimensions.
  • Applied the model to estimate dynamic functional connectivity from functional MRI datasets.
  • Generated interpretable connectivity matrices.

Main Results:

  • The "glass-box" model achieved state-of-the-art performance on multiple functional MRI datasets.
  • Successfully estimated task-based flexible connectivity matrices, surpassing static methods.
  • Provided interpretable connectivity matrices, addressing the "black-box" limitation.

Conclusions:

  • The proposed "glass-box" deep learning model offers a transparent and interpretable approach for neuroimaging.
  • This model advances the analysis of dynamic brain connectivity, outperforming current methodologies.
  • Facilitates the application of deep learning in neuroimaging by ensuring result transparency.