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

An accurate and efficient bayesian method for automatic segmentation of brain MRI.

J L Marroquin1, B C Vemuri, S Botello

  • 1Centro de Investigaci6n en Matematicas, Guanajuato 36000, Mexico.

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

This study introduces a fully automatic 3-D brain segmentation method for MR scans. The novel approach enhances accuracy and efficiency by using class-specific intensity models and a robust registration technique.

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

Use of Schizosaccharomyces strains for wine fermentation-Effect on the wine composition and food safety.

International journal of food microbiology·2016
Same author

Selection of appropriate Schizosaccharomyces strains for winemaking.

Food microbiology·2014
Same author

A NOVEL INTRINSIC UNSCENTED KALMAN FILTER FOR TRACTOGRAPHY FROM HARDI*

Proceedings. IEEE International Symposium on Biomedical Imaging·2014
Same author

Electrophysiological auditory responses and language development in infants with periventricular leukomalacia.

Brain and language·2011
Same author

QEEG norms for the first year of life.

Early human development·2011
Same author

Wave-front recovery from two orthogonal sheared interferograms.

Applied optics·2010

Area of Science:

  • Medical Imaging
  • Neuroscience
  • Computer Vision

Background:

  • Automatic 3-D brain segmentation from MR scans is complex.
  • Existing methods often lack full automation.
  • Accurate segmentation is crucial for neurological studies.

Purpose of the Study:

  • To present an efficient and accurate fully automatic 3-D brain segmentation procedure for MR scans.
  • To address limitations of existing automated segmentation techniques.
  • To improve the precision of brain tissue classification in medical imaging.

Main Methods:

  • Utilized separate parametric smooth models for each tissue class intensity, avoiding a single bias field.
  • Employed a brain atlas and robust registration for nonrigid transformation to segment brain from non-brain tissue.

Related Experiment Videos

  • Introduced a novel expectation-maximization variant incorporating spatial coherence for optimal segmentation.

    • Main Results:

    • Demonstrated an efficient and accurate fully automatic 3-D segmentation of brain MR scans.
    • The method successfully segmented brain from non-brain tissue.
    • Experimental results on synthetic and real data showed competitive performance compared to published methods.

    Conclusions:

    • The developed procedure offers a fully automatic, efficient, and accurate solution for 3-D brain segmentation.
    • The novel approach with class-specific models and advanced registration shows promise for clinical applications.
    • This method advances automated analysis of brain MR imaging data.