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

Effect of an annotation-free artificial intelligence system for simultaneous detection and diagnosis on breast ultrasonography: a multireader, multicase study across diverse healthcare professionals.

Ultrasonography (Seoul, Korea)·2026
Same author

Predictions of Oncotype DX<sup>®</sup> High-Risk Classification Using Magnetic Resonance Imaging-Based Intratumoral Heterogeneity.

Bioengineering (Basel, Switzerland)·2026
Same author

Phantom Quantification of Magnetoencephalography Source Imaging Distortion Caused by Deep Brain Stimulation.

Brain sciences·2026
Same author

Comparative Analysis of ACR TI-RADS and K-TIRADS: Inter-System Agreement and Diagnostic Performance Using a Single Study Cohort.

Journal of the Korean Society of Radiology·2026
Same author

Clinical safety and breast symmetry after injectable acellular dermal fibers reconstruction: an MR-based volumetric study.

Gland surgery·2026
Same author

A Transformer-Based Machine Learning Framework for Risk Stratification of Left Bundle Branch Block After Transcatheter Aortic Valve Replacement.

Diagnostics (Basel, Switzerland)·2026

Related Experiment Video

Updated: Dec 6, 2025

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

5.9K

BrainNET: Inference of Brain Network Topology Using Machine Learning.

Gowtham Krishnan Murugesan1, Chandan Ganesh1, Sahil Nalawade1

  • 1Department of Radiology, UT Southwestern Medical Center, Dallas, Texas, USA.

Brain Connectivity
|October 8, 2020
PubMed
Summary

A new machine learning method, BrainNET, accurately infers brain networks from functional magnetic resonance imaging (fMRI) data. BrainNET outperforms traditional methods in identifying brain connectivity changes in attention-deficit/hyperactivity disorder (ADHD).

Keywords:
brainconnectivity analysisfMRImachine learning

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

1.4K
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

1.2K

Related Experiment Videos

Last Updated: Dec 6, 2025

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

5.9K
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

1.4K
Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

1.2K

Area of Science:

  • Neuroimaging and computational neuroscience
  • Machine learning applications in brain network analysis

Background:

  • Functional magnetic resonance imaging (fMRI) is crucial for understanding brain connectivity.
  • Existing methods for inferring brain network topology from fMRI data have limitations, including reliance on arbitrary thresholds and lower accuracy in complex conditions.

Purpose of the Study:

  • To develop and validate BrainNET, a novel, efficient machine learning-based method for functional magnetic resonance image (fMRI) network inference.
  • To quantify the contribution of various regions of interest (ROIs) to a specific ROI using an advanced algorithm.
  • To compare BrainNET's performance against traditional correlation and partial correlation methods.

Main Methods:

  • BrainNET utilizes extremely randomized trees to estimate network topology from fMRI data, generating an adjacency matrix without arbitrary thresholds.
  • The method was validated using simulated fMRI data with known ground truth under various confounding conditions.
  • Real-world performance was assessed using a publicly available dataset of typically developing children and children with attention-deficit/hyperactivity disorder (ADHD).

Main Results:

  • BrainNET demonstrated superior performance in simulations, accurately identifying true neural connections across diverse confounding factors.
  • In the ADHD dataset, BrainNET identified significant graph metric differences between groups (p < 0.05).
  • Traditional correlation and partial correlation methods failed to detect significant graph metric changes between ADHD groups.

Conclusions:

  • BrainNET is a novel and effective network inference method for fMRI data, adapted from gene regulatory network approaches.
  • BrainNET significantly outperforms Pearson correlation and partial correlation in both simulated and real-world fMRI data, including ADHD studies.
  • BrainNET offers a robust tool for understanding brain network changes in various conditions and disease states, applicable to individual subjects without pretraining.