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

A minimum description length approach to statistical shape modeling.

Rhodri H Davies1, Carole J Twining, Tim F Cootes

  • 1Division of Imaging Science and Biomedical Engineering, University of Manchester, UK. rhodri.h.davies@stud.man.ac.uk

IEEE Transactions on Medical Imaging
|June 20, 2002
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

Impact of quantified knee positioning on the measurement of minimal joint space width using statistical shape models: A cross-sectional and longitudinal analysis in the IMI-APPROACH.

Osteoarthritis imaging·2026
Same author

Progression of bone and joint space deformity in patients with mild knee osteoarthritis: Data from the IMI-APPROACH cohort.

Osteoarthritis and cartilage open·2026
Same author

Reproducibility of echocardiographic measurements of left ventricular systolic function: a systematic review and meta-analysis comparing artificial intelligence and clinician estimates.

European heart journal. Digital health·2026
Same author

Incidental findings and duty-of-care protocols in cardiovascular magnetic resonance among older adults: a prospective population-based study from MyoFit46.

The lancet. Healthy longevity·2026
Same author

Reappraising cardiac function with myocardial contraction fraction: normal values, disease detection, and prognostication.

European heart journal. Cardiovascular Imaging·2026
Same author

Biomarkers.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
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 an automated method for building statistical shape models, improving image segmentation and interpretation. The approach eliminates manual landmarking by optimizing shape parameterization for better model compactness and generalization.

Area of Science:

  • Medical Image Analysis
  • Computer Vision
  • Computational Geometry

Background:

  • Statistical shape models (SSMs) are valuable for image segmentation and interpretation.
  • Building SSMs traditionally requires manual landmarking, which is time-consuming and subjective, especially in 3D.
  • Establishing dense correspondences between training shapes is a key challenge in SSM construction.

Purpose of the Study:

  • To develop an automated method for constructing statistical shape models.
  • To overcome the limitations of manual landmarking in establishing shape correspondences.
  • To create more compact, specific, and generalizable shape models.

Main Methods:

  • The correspondence problem is reframed as finding optimal parameterizations for each training shape.

Related Experiment Videos

  • A minimum description length (MDL) principle is used to define and select the 'best' model.
  • Shape parameterizations are represented and manipulated to build the MDL model.

    • Main Results:

    • The automated method successfully builds statistical shape models from training data.
    • The proposed approach outperforms traditional manual landmarking in constructing 2D shape models.
    • The method demonstrates straightforward extensibility to three-dimensional applications.

    Conclusions:

    • Automated statistical shape model construction is feasible and effective.
    • Optimizing shape parameterization via MDL offers a superior alternative to manual landmarking.
    • This technique enhances the efficiency and objectivity of building shape models for image analysis.