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

Volumetric segmentation of brain images using parallel genetic algorithms.

Yong Fan1, Tianzi Jiang, David J Evans

  • 1National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100080, China.

IEEE Transactions on Medical Imaging
|December 11, 2002
PubMed
Summary

A new parallel genetic algorithm improves active model-based segmentation for brain imaging. This method enhances accuracy and stability in segmenting complex structures like lateral ventricles from MRI scans.

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

Prior contact lens wear reduces susceptibility of the superficially-injured cornea to bacterial adhesion.

PloS one·2026
Same author

Prior contact lens wear reduces susceptibility of the superficially-injured cornea to bacterial adhesion.

bioRxiv : the preprint server for biology·2025
Same author

Cross-membrane cooperation among bacteria can facilitate intracellular pathogenesis.

Nature communications·2025
Same author

Retraction Note: Topical antibiotics reduce CD11c + cell numbers in the healthy murine cornea and modulate their response to contact lens wear.

Scientific reports·2025
Same author

TRPV1 Defends the Healthy Murine Cornea against <i>Staphylococcus aureus</i> Adhesion Independently of Sensory Nerve Firing.

bioRxiv : the preprint server for biology·2025
Same author

The <i>Pseudomonas aeruginosa</i> T3SS can contribute to traversal of an <i>in situ</i> epithelial multilayer independently of the T3SS needle.

mBio·2025

Area of Science:

  • Medical Image Processing
  • Computational Neuroscience
  • Biomedical Engineering

Background:

  • Active model-based segmentation is a successful technique in medical imaging, often treated as a partial differential equation problem.
  • Existing methods face challenges with speed and stability, limiting their performance for complex anatomical structures.

Purpose of the Study:

  • To introduce a novel parallel genetic algorithm-based active model method for improved medical image segmentation.
  • To enhance the accuracy and robustness of segmenting the lateral ventricles in magnetic resonance brain images.

Main Methods:

  • Defined an objective function for segmentation.
  • Initialized a parallel genetic algorithm using a surface extracted by a finite-difference method-based active model.

Related Experiment Videos

  • Employed the parallel genetic algorithm to refine the segmentation results.

    • Main Results:

    • The proposed method successfully overcomes numerical instability issues inherent in traditional active models.
    • Achieved accurate and robust segmentation of the lateral ventricles, complex structures within the human brain.
    • Demonstrated improved performance compared to existing active model-based segmentation techniques.

    Conclusions:

    • The parallel genetic algorithm-based active model offers a significant advancement in medical image segmentation.
    • This approach provides a stable and accurate method for delineating complex brain anatomy, particularly the lateral ventricles.
    • The technique holds promise for various applications in neuroimaging analysis and clinical diagnostics.