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

Appearance-based segmentation of medial temporal lobe structures.

S Duchesne1, J Pruessner, D L Collins

  • 1McConnell Brain Imaging Centre, Montreal Neurological Institute, McGill University, 3801 University Street, Montreal, Canada. duchesne@bic.mni.mcgill.ca

Neuroimage
|October 16, 2002
PubMed
Summary

A novel method uses MRI data and shape analysis to segment brain structures faster than existing techniques. This approach offers a robust and flexible alternative for medical image analysis.

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

Assessment of cognitive load in the context of neurosurgery.

International journal of computer assisted radiology and surgery·2025
Same author

Root and canal morphology of the permanent teeth in medieval and current French population.

Archives of oral biology·2022
Same author

A voxel-wise assessment of growth differences in infants developing autism spectrum disorder.

NeuroImage. Clinical·2021
Same author

A variation in the infant oxytocin receptor gene modulates infant hippocampal volumes in association with sex and prenatal maternal anxiety.

Psychiatry research. Neuroimaging·2020
Same author

Partial Support for an Interaction Between a Polygenic Risk Score for Major Depressive Disorder and Prenatal Maternal Depressive Symptoms on Infant Right Amygdalar Volumes.

Cerebral cortex (New York, N.Y. : 1991)·2020
Same author

Automatic extraction of vertebral landmarks from ultrasound images: A pilot study.

Computers in biology and medicine·2020

Area of Science:

  • Medical Imaging
  • Neuroimaging
  • Computer Vision

Background:

  • Traditional 2D shape models require manual intervention.
  • 3D shape analysis is complex and computationally intensive.
  • Accurate segmentation of medial temporal lobe structures is crucial for neurological studies.

Purpose of the Study:

  • To propose a new paradigm for structure appearance characterization.
  • To develop an automated method for segmenting medial temporal lobe structures in brain MRI.
  • To evaluate the accuracy and efficiency of the proposed segmentation technique.

Main Methods:

  • Combined gray-level MRI intensity data with a shape descriptor from principal components analysis of 3D deformation vector fields.
  • Developed an appearance model to synthesize a deformation field for mapping new volumes to a reference target.

Related Experiment Videos

  • Tested the method on 80 normal subjects and compared it with manual segmentation and the ANIMAL technique.

    • Main Results:

    • The novel method achieved segmentation accuracy marginally lower (< 2%) than ANIMAL.
    • The proposed method was six times faster than ANIMAL in processing time.
    • Experimental results demonstrated robustness and flexibility.

    Conclusions:

    • The new paradigm offers a robust and flexible approach to structure appearance characterization.
    • The developed segmentation method is efficient and accurate for medial temporal lobe structures.
    • The concept shows applicability for shape deformation analysis in neuroimaging.