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

Model-free functional MRI analysis based on unsupervised clustering.

Axel Wismüller1, Anke Meyer-Bäse, Oliver Lange

  • 1Department of Electrical and Computer Engineering, Florida State University, Tallahassee, FL 32310-6046, USA.

Journal of Biomedical Informatics
|March 16, 2004
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

Machine-Learning-Based Survival Prediction in Glioblastoma Using Graph-Theoretical Analysis of Structural Network Alterations.

Cancers·2026
Same author

Multimodal contrastive prognostication framework for early neurological outcome prediction in post-cardiac arrest patients.

Scientific reports·2026
Same author

Suicide attempt history, childhood trauma, and functional brain network alterations in major depressive disorder: a resting-state functional connectivity-based multivariate pattern analysis.

Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology·2026
Same author

Microvascular Perfusion MRI Improves Therapy Monitoring and Detects Early Recurrences of Gliomas: A Large-Scale Trial of 2000 Follow-Up Examinations.

AJNR. American journal of neuroradiology·2025
Same author

Inferring causal relations from multivariate data using Large-Scale Augmented Granger Causality (lsAGC).

NeuroImage·2025
Same author

Algebraic methods and computational strategies for pseudoinverse-based MR image reconstruction (Pinv-Recon).

Scientific reports·2025

Neural gas networks offer a novel approach for analyzing complex functional MRI (fMRI) data, outperforming traditional methods in identifying brain activation sites. This advanced technique enhances signal correlation and reduces quantization error in fMRI studies.

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Machine Learning

Background:

  • Conventional functional MRI (fMRI) analysis methods struggle with complex neural response patterns and unknown fMRI responses.
  • Existing techniques like Kohonen's self-organizing map have limitations in identifying subtle activation sites.

Purpose of the Study:

  • To adapt and rigorously evaluate the "neural gas" network for analyzing complex fMRI data.
  • To compare the performance of "neural gas" against Kohonen's map and fuzzy clustering for fMRI analysis.

Main Methods:

  • Adaptation and application of the "neural gas" network algorithm to fMRI data analysis.
  • Comparative quantitative evaluation using a systematic fMRI study, including Kohonen's self-organizing map and fuzzy clustering.

Related Experiment Videos

Main Results:

  • "Neural gas" and fuzzy clustering demonstrated superior performance over Kohonen's map in identifying signal components highly correlated with fMRI stimuli.
  • "Neural gas" exhibited lower quantization error compared to the other two methods.
  • Kohonen's map showed advantages in computational efficiency.

Conclusions:

  • The "neural gas" network is a promising algorithm for analyzing complex fMRI data, particularly for identifying activation sites.
  • This method offers improved accuracy in detecting neural responses compared to traditional approaches.
  • The study validates the applicability of "neural gas" on experimental fMRI data.