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

Gaussian distributions on Lie groups and their application to statistical shape analysis.

P Thomas Fletcher1, Sarang Joshi, Conglin Lu

  • 1Medical Image Display and Analysis Group, University of North Carolina at Chapel Hill, USA. fletcher@cs.unc.edu

Information Processing in Medical Imaging : Proceedings of the ... Conference
|September 4, 2004
PubMed
Summary

This study introduces principal geodesic analysis for shape analysis of anatomical objects using medial representations (m-reps). This novel method extends Gaussian distribution concepts to Lie groups, enabling robust statistical modeling of complex anatomical variability.

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

Mesial temporal shape asymmetry as a neuro-imaging correlate of epilepsy in mild cognitive impairment and dementia.

Brain communications·2026
Same author

Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model.

Proceedings of machine learning research·2026
Same author

LEARNING SPATIALLY-CONTINUOUS FIBER ORIENTATION FUNCTIONS.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

Deep Learning Driven Evaluation of MR-guided Focused Ultrasound Ablation.

IEEE transactions on bio-medical engineering·2026
Same author

ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoders.

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision·2025
Same author

RealDeal: Enhancing Realism and Details in Brain Image Generation via Image-to-Image Diffusion Models.

Deep generative models : 5th MICCAI workshop, DGM4MICCAI 2025, held in conjunction with MICCAI 2025, Daejeon, South Korea, September 23, 2025, Proceedings. DGM4MICCAI (Workshop) (5th : 2025 : Taejon-si, Korea)·2025

Area of Science:

  • Computational anatomy
  • Statistical shape analysis
  • Differential geometry

Background:

  • Gaussian distributions and principal component analysis (PCA) are foundational in statistical shape analysis for Euclidean data.
  • Medial representations (m-reps) model anatomical object geometry but their parameters are not Euclidean, precluding standard PCA.
  • Previous work established m-rep parameters as elements of a Lie group.

Purpose of the Study:

  • To develop a Gaussian distribution framework for Lie groups applicable to m-rep parameters.
  • To derive maximum likelihood estimates for the mean and covariance of this Lie group Gaussian distribution.
  • To introduce principal geodesic analysis (PGA) for studying anatomical variability in medially-defined objects.

Main Methods:

  • Development of a Gaussian distribution on Lie groups.

Related Experiment Videos

  • Derivation of maximum likelihood estimates for mean and covariance.
  • Definition of principal geodesic analysis analogous to PCA on Lie groups.

    • Main Results:

    • Successful development of a Gaussian distribution on Lie groups for m-rep parameters.
    • Established maximum likelihood estimation for the distribution's parameters.
    • Demonstrated application of principal geodesic analysis on a population of hippocampi in a schizophrenia study.

    Conclusions:

    • Principal geodesic analysis provides a powerful framework for statistical shape analysis of medially-represented anatomical objects.
    • This method extends traditional PCA to non-Euclidean spaces like Lie groups, crucial for complex anatomical data.
    • The framework is effective for analyzing anatomical variability, as shown in the hippocampus schizophrenia study.