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 Video

Updated: Jun 5, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Hybrid genetic and variational expectation-maximization algorithm for gaussian-mixture-model-based brain MR image

GuangJian Tian1, Yong Xia, Yanning Zhang

  • 1China Realtime Database Co. Ltd, State Grid Electric Power Research Institute, Nanjing, China. tianguangjian@gmail.com

IEEE Transactions on Information Technology in Biomedicine : a Publication of the IEEE Engineering in Medicine and Biology Society
|January 15, 2011
PubMed
Summary

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

Retrieval-Augmented Representation for Semi-Supervised Medical Image Segmentation.

IEEE transactions on medical imaging·2026
Same author

PUFA-rich oil supplement improves hair condition of cats and dogs.

Open veterinary journal·2026
Same author

Berberine from Tibetan Medicine <i>Dracocephalum tanguticum</i> Maxim Suppresses Colorectal Tumor Growth and Inhibits CD8⁺ T Cells Ferroptosis via the NRF2-SLC7A11-GPX4 Axis.

Cancer management and research·2026
Same author

Risk factors for recurrence and surgical site infection after abdominal wall hernia repair: a systematic review and meta analysis.

Frontiers in surgery·2026
Same author

Confinement-Driven Redox Inversion and Predicted Ferromagnetism in One-Dimensional Sc<sub>3</sub>Cl<sub>8</sub> within Single-Walled Carbon Nanotubes.

Nano letters·2026
Same author

From weak but broad to potent and universal: A trispecific antibody against conserved SARS-CoV-2 spike epitopes.

Molecular therapy : the journal of the American Society of Gene Therapy·2026

This study introduces a hybrid genetic and variational expectation-maximization (GA-VEM) algorithm for brain MR image segmentation. The novel GA-VEM method enhances accuracy by combining global optimization with overfitting avoidance, outperforming traditional expectation-maximization techniques.

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Computational Neuroscience

Background:

  • The expectation-maximization (EM) algorithm is standard for Gaussian Mixture Model (GMM) estimation in brain MR image segmentation.
  • Traditional EM algorithms are susceptible to local optima and overfitting, limiting segmentation accuracy.
  • Existing methods often struggle with the inherent complexities of brain MR image data.

Purpose of the Study:

  • To develop a novel hybrid algorithm for improved brain MR image segmentation.
  • To address the limitations of traditional EM algorithms, specifically overfitting and local optima.
  • To enhance the accuracy and robustness of brain MR image segmentation using a combined approach.

Main Methods:

  • A hybrid genetic and variational EM (GA-VEM) algorithm was proposed.

More Related Videos

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Jun 5, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

  • The variational EM (VEM) algorithm estimates the GMM parameters.
  • Genetic algorithms (GA) initialize hyperparameters for VEM, enabling global optimization and overfitting avoidance.
  • The GA-VEM approach was compared against EM-based, VEM-based, and GA-EM methods, including established software packages.

    • Main Results:

    • The proposed GA-VEM algorithm demonstrated substantial improvements in brain MR image segmentation performance.
    • Comparative analysis showed superior results over traditional EM, VEM, and GA-EM algorithms.
    • The hybrid approach effectively mitigated issues of local optima and overfitting inherent in standard EM methods.
    • Performance was validated across both low-resolution and high-resolution brain MR datasets.

    Conclusions:

    • The hybrid GA-VEM algorithm offers a significant advancement for brain MR image segmentation.
    • This method provides a robust solution overcoming the limitations of conventional EM-based techniques.
    • The GA-VEM approach holds promise for more accurate and reliable neuroimaging analysis.