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

Morphological classification of brains via high-dimensional shape transformations and machine learning methods.

Zhiqiang Lao1, Dinggang Shen, Zhong Xue

  • 1Section for Biomedical Image Analysis, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.

Neuroimage
|January 27, 2004
PubMed
Summary
This summary is machine-generated.

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

Accelerated Brain Aging Mediates the Association Between Psychological Profiles and Clinical Pain in Knee Osteoarthritis.

The journal of pain·2023
Same author

Shared and Distinct Associations of Manual Dexterity and Gross Motor Function With Brain Atrophy.

The journals of gerontology. Series A, Biological sciences and medical sciences·2023
Same author

Identification of Clinically Relevant Brain Endothelial Cell Biomarkers in Plasma.

Stroke·2023
Same author

Physics-Informed Discretization for Reproducible and Robust Radiomic Feature Extraction Using Quantitative MRI.

Investigative radiology·2023
Same author

Proteomic Indicators of Health Predict Alzheimer's Disease Biomarker Levels and Dementia Risk.

Annals of neurology·2023
Same author

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises.

Proceedings of the IEEE. Institute of Electrical and Electronics Engineers·2023

This study introduces a novel brain imaging analysis method using morphological signatures and support vector machines (SVM). The technique effectively detects subtle brain changes and classifies demographics like sex and age with high accuracy.

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Biostatistics

Background:

  • Traditional voxel-based morphometry (VBM) methods analyze brain images voxel-by-voxel, potentially missing complex, spatially distributed morphological differences.
  • Detecting subtle population variations in brain morphology requires advanced analytical techniques that consider the data holistically.

Purpose of the Study:

  • To develop and validate a novel high-dimensional shape transformation method for brain image analysis.
  • To apply multivariate pattern classification to morphological signatures for detecting subtle group differences.
  • To assess the method's efficacy in identifying simulated atrophy and classifying demographic groups.

Main Methods:

  • A mass-preserving framework generates high-dimensional morphological signatures from brain images.

Related Experiment Videos

  • Wavelet decomposition and feature reduction techniques significantly reduce signature dimensionality.
  • Nonlinear support vector machine (SVM) pattern classification is applied to morphological signatures.

    • Main Results:

    • The method accurately detects subtle, spatially complex simulated atrophy (5% variation).
    • Brains are classified as male or female with 97% accuracy using leave-one-out cross-validation.
    • High classification rates are achieved for age groups, even in challenging scenarios.

    Conclusions:

    • This multivariate pattern classification approach surpasses voxel-based methods in detecting subtle, complex morphological group differences.
    • The method offers a powerful tool for neuroimaging research, enhancing the ability to identify population-specific brain variations.
    • High classification accuracy for sex and age demonstrates the method's potential in clinical and research applications.