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

Hierarchical active shape models, using the wavelet transform.

Christos Davatzikos1, Xiaodong Tao, Dinggang Shen

  • 1Section for Biomedical Image Analysis, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA. hristos@rad.jhu.edu

IEEE Transactions on Medical Imaging
|May 23, 2003
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

The genetic architecture of multimodal human brain age.

Nature communications·2024
Same author

Distance-weighted Sinkhorn loss for Alzheimer's disease classification.

iScience·2024
Same author

Integrating imaging and genomic data for the discovery of distinct glioblastoma subtypes: a joint learning approach.

Scientific reports·2024
Same author

Plasma Biomarkers as Predictors of Progression to Dementia in Individuals with Mild Cognitive Impairment.

Journal of Alzheimer's disease : JAD·2024
Same author

Genetic and Clinical Correlates of AI-Based Brain Aging Patterns in Cognitively Unimpaired Individuals.

JAMA psychiatry·2024
Same author

Dimensional Neuroimaging Endophenotypes: Neurobiological Representations of Disease Heterogeneity Through Machine Learning.

ArXiv·2024
Same journal

MUST: Multi-style virtual staining with incomplete pairs.

IEEE transactions on medical imaging·2026
Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026
Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026
Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026
Same journal

The Ritz Adjoint Method for MRI Pulse Design.

IEEE transactions on medical imaging·2026
Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026
See all related articles

This study introduces a hierarchical active shape model (ASM) using wavelet transforms to better capture biological shape variations. This method improves segmentation accuracy, especially with limited training data.

Area of Science:

  • Medical image analysis
  • Computer vision
  • Computational anatomy

Background:

  • Active shape models (ASMs) struggle to represent full biological shape variability with limited eigenvectors.
  • Existing methods often rely on non-biological smoothness constraints.

Purpose of the Study:

  • To develop a novel hierarchical active shape model (ASM) formulation.
  • To improve the representation of biological shape variability and enhance segmentation robustness.

Main Methods:

  • Utilized wavelet transform to analyze deformable contour statistics.
  • Applied principal component analysis (PCA) on wavelet coefficients for shape priors.
  • Incorporated local and global shape characteristics as deformation constraints.

Related Experiment Videos

Main Results:

  • The hierarchical ASM effectively captures both global and local shape variations.
  • Demonstrated robustness with a limited number of training samples (as few as five).
  • Achieved accurate and automated segmentation of corpus callosum and hand contours from MRI data.

Conclusions:

  • The wavelet-based hierarchical ASM overcomes limitations of traditional ASMs.
  • This approach provides biologically relevant smoothness constraints without ad hoc physical models.
  • Enables robust and automated medical image segmentation even with scarce training data.