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

A hierarchical clustering method for analyzing functional MR images.

P Filzmoser1, R Baumgartner, E Moser

  • 1Department of Statistics and Probability Theory, Vienna University of Technology, Austria.

Magnetic Resonance Imaging
|July 14, 1999
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

Visual Parameter Selection for Spatial Blind Source Separation.

Computer graphics forum : journal of the European Association for Computer Graphics·2022
Same author

Evaluation of robust outlier detection methods for zero-inflated complex data.

Journal of applied statistics·2022
Same author

Robust principal component analysis for compositional tables.

Journal of applied statistics·2022
Same author

A head coil system with an integrated orbiting transmission point source mechanism for attenuation correction in PET/MRI.

Physics in medicine and biology·2018
Same author

Immediate and delayed neuroendocrine responses to social exclusion in males and females.

Psychoneuroendocrinology·2018
Same author

A new method for correlation analysis of compositional (environmental) data - a worked example.

The Science of the total environment·2017

This study presents a new method using hierarchical k-means clustering for analyzing functional magnetic resonance imaging (fMRI) data. The approach effectively separates time-invariant anatomic structures from time-varying functional signals in fMRI scans.

Area of Science:

  • Neuroimaging
  • Biomedical Engineering
  • Data Science

Background:

  • Functional magnetic resonance imaging (fMRI) is crucial for understanding brain activity.
  • Distinguishing between stable anatomic structures and dynamic functional signals in fMRI data presents a challenge.
  • Existing methods may lack efficiency or data-driven approaches for structure identification.

Purpose of the Study:

  • To introduce a novel, hierarchical clustering method for fMRI data analysis.
  • To efficiently detect and separate anatomic and functional structures within fMRI datasets.
  • To provide a data-driven approach for determining the optimal number of clusters.

Main Methods:

  • Hierarchical clustering using k-means algorithm to partition fMRI data.

Related Experiment Videos

  • Employing independent tests to verify cluster structure and determine stopping criteria.
  • Utilizing resulting cluster centers for a single-step computation of final results.

    • Main Results:

    • The method achieved perfect separation of time-invariant (anatomic) and time-varying (functional) information in synthetic fMRI data.
    • Successful separation was demonstrated at contrast-to-noise ratios of two and higher.
    • The algorithm proved flexible, computationally fast, and determined cluster numbers in a data-driven manner.

    Conclusions:

    • The novel hierarchical clustering method offers an effective and efficient approach for fMRI data analysis.
    • This technique accurately distinguishes between anatomic and functional information in brain imaging.
    • Demonstrated in vivo performance on human motor cortex EPI-fMRI data validates the method's practical applicability.