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 robust method for extraction and automatic segmentation of brain images.

N Kovacevic1, N J Lobaugh, M J Bronskill

  • 1Sunnybrook and Women's College Health Sciences Centre, Toronto, Ontario, Canada.

Neuroimage
|November 5, 2002
PubMed
Summary

A novel protocol accurately extracts and segments brain tissues (gray matter, white matter, CSF) from MR images. This robust and fast method shows excellent reproducibility and accuracy for clinical applications in both healthy and diseased brains.

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

Associations between fatigue impact and physical and neurobehavioural factors: An exploration in people with progressive multiple sclerosis.

Multiple sclerosis and related disorders·2024
Same author

Profiling cognitive-motor interference in a large sample of persons with progressive multiple sclerosis and impaired processing speed: results from the CogEx study.

Journal of neurology·2023
Same author

The computer-based Symbol Digit Modalities Test: establishing age-expected performance in healthy controls and evaluation of pediatric MS patients.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2017
Same author

Comparison of Quantitative Cerebral Blood Flow Measurements Performed by Bookend Dynamic Susceptibility Contrast and Arterial Spin-Labeling MRI in Relapsing-Remitting Multiple Sclerosis.

AJNR. American journal of neuroradiology·2016
Same author

Suicidal Ideation After Mild Traumatic Brain Injury: A Consecutive Canadian Sample.

Archives of suicide research : official journal of the International Academy for Suicide Research·2016
Same author

Major psychological complications and decreased health-related quality of life among survivors of Stevens-Johnson syndrome and toxic epidermal necrolysis.

The British journal of dermatology·2016

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Computational Anatomy

Background:

  • Accurate brain extraction and tissue segmentation are crucial for quantitative analysis of neuroimaging data.
  • Existing methods may lack robustness, speed, or accuracy, particularly in diseased states.
  • Developing automated protocols is essential for efficient clinical workflows.

Purpose of the Study:

  • To introduce a new, fully automatic protocol for brain extraction and tissue segmentation of MR images.
  • To evaluate the reproducibility and accuracy of the proposed protocol in healthy and Alzheimer's brains.
  • To assess the algorithm's performance on a digital brain phantom.

Main Methods:

  • Brain extraction using proton density and T2-weighted MR images to create a brain mask.

Related Experiment Videos

  • Automatic tissue segmentation (gray matter, white matter, CSF) on T1-weighted images using a histogram-based Expectation Maximization algorithm.
  • Validation using reproducibility measures (intracranial capacity variation, scan-rescan differences) and accuracy tests on a digital brain phantom.

    • Main Results:

    • Excellent reproducibility for brain extraction (average variation < 0.66% TIC) and segmentation (< 0.30% TIC scan-rescan differences).
    • High accuracy on a digital brain phantom with classification errors < 1% of phantom volume.
    • Robustness demonstrated by insensitivity to parameter initialization and low Type I/II errors (2.2-4.3%).

    Conclusions:

    • The developed protocol offers a robust, fast, and accurate solution for brain extraction and tissue segmentation.
    • Its high reproducibility and accuracy make it suitable for clinical applications involving both normal and diseased brains.
    • This automated approach facilitates quantitative neuroimaging analysis and supports clinical decision-making.