Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 23, 2026

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Published on: October 20, 2023

Automatic selection of ROIs in functional imaging using Gaussian mixture models.

J M Górriz¹, A Lassl, J Ramírez

¹Departamento Teoría de la Se nal, Telemática y Comunicaciones, Universidad Granada, Spain. gorriz@ugr.es

Neuroscience Letters

|May 21, 2009

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

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026

Same author

An explainable framework for the relationship between dementia and metabolism patterns.

NeuroImage·2026

Same author

Statistical agnostic regression: A machine learning method to validate regression models.

Journal of advanced research·2025

Same author

A novel Slide-seq based image processing software to identify gene expression at the single cell level.

Journal of pathology informatics·2024

Same author

Nonlinear Weighting Ensemble Learning Model to Diagnose Parkinson's Disease Using Multimodal Data.

International journal of neural systems·2023

Same author

Comparing ensemble methods combined with different aggregating models using micrograph cell segmentation as an initial application example.

Journal of pathology informatics·2023

This study introduces an automated method using Gaussian mixture models (GMMs) to identify brain regions of interest in 3D functional images. This technique aids in extracting features for diagnosing brain diseases.

Area of Science:

Neuroimaging
Computational Neuroscience
Medical Image Analysis

Background:

Functional brain imaging generates complex data requiring efficient analysis.
Identifying specific regions of interest (ROIs) is crucial for understanding brain activity and disease diagnosis.
Existing methods may lack the precision or efficiency needed for large datasets.

Purpose of the Study:

To develop an automated method for selecting ROIs in 3D functional brain images.
To utilize Gaussian mixture models (GMMs) for information compression and feature extraction.
To provide a foundation for advanced diagnostic tools for brain diseases.

Main Methods:

Applied Gaussian mixture models (GMMs) to approximate the grey-level distribution of brain images.

More Related Videos

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

Published on: January 5, 2024

Related Experiment Videos

Last Updated: Jun 23, 2026

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Published on: October 20, 2023

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

A Randomized, Sham-Controlled Trial of Cranial Electrical Stimulation for Fibromyalgia Pain and Physical Function, Using Brain Imaging Biomarkers

Published on: January 5, 2024

Employed the expectation-maximization (EM) algorithm to determine GMM parameters via maximum likelihood estimation.

Represented each Gaussian component as a multivariate function defining contiguous brain regions with similar activation.

Main Results:

Successfully implemented an automatic ROI selection method.
Achieved significant information compression of brain image data.
Demonstrated the potential for GMM-based feature extraction for disease diagnosis.

Conclusions:

The proposed GMM-based approach offers an effective way to process 3D functional brain images.
This method facilitates efficient feature extraction for potential brain disease diagnosis.
The technique provides a novel and powerful tool in neuroimaging analysis.