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

Multiscale 3D shape analysis using spherical wavelets.

Delphine Nain1, Steven Haker, Aaron Bobick

  • 1College of Computing, Georgia Institute of Technology, Atlanta, GA 30332-0280, USA. delfin@cc.gatech.edu

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|May 12, 2006
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

Normal tissue transcriptional signatures for tumor-type-agnostic phenotype prediction.

Scientific reports·2024
Same author

Visualizing Fluid Flows via Regularized Optimal Mass Transport with Applications to Neuroscience.

Journal of scientific computing·2024
Same author

Multi-scale geometric network analysis identifies melanoma immunotherapy response gene modules.

Scientific reports·2024
Same author

Unbalanced regularized optimal mass transport with applications to fluid flows in the brain.

Scientific reports·2024
Same author

Dynamic network curvature analysis of gene expression reveals novel potential therapeutic targets in sarcoma.

Scientific reports·2024
Same author

Multi-Scale Geometric Network Analysis Identifies Melanoma Immunotherapy Response Gene Modules.

bioRxiv : the preprint server for biology·2023
Same journal

LiftReg: Limited Angle 2D/3D Deformable Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Inverse Consistency by Construction for Multistep Deep Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Can Crowdsourced Annotations Improve AI-based Congestion Scoring For Bedside Lung Ultrasound?

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Equivariant Filters for Efficient Tracking in 3D Imaging.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

Lobar Lung Density Embeddings with a Transformer encoder (LobTe) to predict emphysema progression in COPD.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same journal

uniGradICON: A Foundation Model for Medical Image Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
See all related articles

This study introduces a new algorithm for learning shape variations, outperforming Principal Component Analysis (PCA) on small datasets. The method effectively captures local shape differences, avoiding the oversmoothing common with PCA.

Area of Science:

  • Computational anatomy
  • Medical image analysis
  • Statistical shape modeling

Background:

  • Shape priors are crucial for modeling biological variations in populations.
  • Principal Component Analysis (PCA) effectively captures global variations but struggles with local ones, especially with limited data.
  • Existing methods often fail to represent complex local shape variations accurately.

Purpose of the Study:

  • To develop a novel algorithm for learning shape variations at multiple scales and locations.
  • To improve the representation of local shape variations in statistical shape models.
  • To overcome the limitations of PCA in modeling complex biological shapes from small datasets.

Main Methods:

  • Utilized spherical wavelets for multi-scale analysis.

Related Experiment Videos

  • Employed spectral graph partitioning for identifying localized variations.
  • Developed a novel algorithm integrating these techniques to learn shape variations.

    • Main Results:

    • The proposed algorithm significantly improved shape approximation compared to PCA on small training sets.
    • The method demonstrated superior ability in capturing local shape variations.
    • PCA was observed to oversmooth data, leading to less accurate shape representations.

    Conclusions:

    • The novel algorithm effectively learns shape variations from data at multiple scales and locations.
    • This approach offers a significant improvement over PCA for modeling complex biological shapes with limited data.
    • The findings have implications for statistical shape modeling in fields like medical imaging and computational anatomy.