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 Experiment Videos

Learning functional structure from fMR images.

Xuebin Zheng1, Jagath C Rajapakse

  • 1BioInformatics Research Center, School of Computer Engineering Nanyang Technological University, Singapore.

Neuroimage
|March 17, 2006
PubMed
Summary
This summary is machine-generated.

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

Integrating multimodal features with deep learning for protein solubility prediction.

Journal of cheminformatics·2026
Same author

LABMA: Latent-bottleneck attention-based multimodal architecture for integration of transcriptomics, proteomics, and MRI in neurodegeneration.

Computers in biology and medicine·2026
Same author

Immunomodulatory and anti-apoptotic effects of heme oxygenase-1 in hypoxia stress of small yellow croaker (Larimichthys polyactis).

Fish & shellfish immunology·2026
Same author

Encoding and Decoding of Brain Dynamic Functional Connectivity for ADHD Diagnosis.

IEEE journal of biomedical and health informatics·2026
Same author

Entropy-based byte patching transformer for self-supervised pretraining of SMILES data.

iScience·2026
Same author

Sub-chronic exposure to copper nanoparticles and copper sulfate dysregulated the microbiota-gut-liver axis in large yellow croaker, Larimichthys crocea.

Marine pollution bulletin·2025
Same journal

Lifespan Trajectories of the Brain's Functional Complexity Characterized by Multiscale Sample Entropy.

NeuroImage·2026
Same journal

Pleasant fragrance modulates dyadic social sharing of positive emotion: Sharer-centered socioemotional enhancement effect and its neural couplings.

NeuroImage·2026
Same journal

Altered Functional Hierarchical and Sequential Organization in Individuals with Schizophrenia during Auditory Processing.

NeuroImage·2026
Same journal

Mechanical Deformation Explains Distinct Neuroimaging Patterns and Etiologies in Brain Trauma.

NeuroImage·2026
Same journal

Ventral striatum temporal interference brain stimulation enhances the reward-positivity event-related potential and reduces anxiety.

NeuroImage·2026
Same journal

NeuroHarm‑Kit: An Open‑Source Toolbox for Benchmarking Deep‑Learning Harmonization of Multi‑Site T1‑Weighted MRI.

NeuroImage·2026
See all related articles

We introduce a new Bayesian network method to discover brain connectivity without needing a prior model. This approach statistically defines interactions between brain regions, even for large or unknown networks.

Area of Science:

  • Neuroscience
  • Computational Neuroscience
  • Machine Learning

Background:

  • Effective connectivity analysis in neuroscience often relies on predefined models.
  • Existing methods like Structural Equation Modeling (SEM) and Dynamic Causal Modeling (DCM) are limited to testing hypothesized or known anatomical models.
  • There is a need for exploratory methods to uncover brain connectivity structures without prior assumptions.

Purpose of the Study:

  • To propose a novel, model-agnostic method for learning the structure of effective connectivity in brain networks.
  • To utilize Bayesian networks for representing and quantifying statistical interactions between brain regions.
  • To demonstrate the applicability of this method to complex cognitive tasks and large-scale brain networks.

Main Methods:

Related Experiment Videos

  • Development of a Bayesian network framework to infer effective connectivity from functional Magnetic Resonance Imaging (fMRI) data.
  • The method learns network structure exploratorily, without requiring an a priori anatomical or hypothesized model.
  • Conditional probabilities within the Bayesian network are used to statistically define the connectivity between brain regions.

Main Results:

  • The proposed Bayesian network approach successfully learns effective connectivity structures from both synthetic and real fMRI data.
  • Demonstrated the method's capability in analyzing brain networks during silent word reading and counting Stroop tasks.
  • The approach proved effective even when dealing with a large or unknown number of brain regions.

Conclusions:

  • Bayesian networks offer a powerful, exploratory tool for uncovering effective brain connectivity.
  • This novel method overcomes limitations of model-dependent approaches, providing a more comprehensive statistical understanding of neural interactions.
  • The technique is robust and applicable to complex cognitive neuroscience research involving fMRI data.