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

Automatic construction of eigenshape models by direct optimization.

A C Kotcheff1, C J Taylor

  • 1Department of Medical Bio-Physics, University of Manchester, UK. acwk@sv1.smb.man.ac.uk

Medical Image Analysis
|March 11, 1999
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

Range-resolved water temperature measurement using Raman LiDAR with multiplexed excitation.

Optics express·2026
Same author

Loop diuretics, heart failure diagnosis and outcome in primary care.

International journal of cardiology·2025
Same author

Depth-resolved water temperature measurements using Raman LiDAR.

Applied optics·2024
Same author

Effectiveness of an online module: climate-change and sustainability in clinical practice.

BMC medical education·2022
Same author

The effect of mental fatigue on the performance of Australian football specific skills amongst amateur athletes.

Journal of science and medicine in sport·2021
Same author

Radiative Double-Electron Capture by Bare and One-Electron Ions on Gas Targets.

Physical review letters·2020

This study introduces an automated method for creating eigenshape models, crucial for medical image analysis. By optimizing shape pose and parametrization using a genetic algorithm, it overcomes manual model-building limitations.

Area of Science:

  • Medical image analysis
  • Computational anatomy
  • Pattern recognition

Background:

  • Eigenshape models are valuable tools in medical image analysis.
  • Manual construction of these models is time-consuming and labor-intensive.
  • Existing methods lack robustness due to sensitivity to pose and parametrization.

Purpose of the Study:

  • To develop an automated approach for constructing accurate eigenshape models.
  • To address the challenge of selecting optimal pose and parametrization for training shapes.
  • To improve the compactness and specificity of eigenshape models.

Main Methods:

  • Proposed an objective function based on the determinant of the covariance matrix.
  • Utilized a genetic algorithm (GA) to optimize pose and parametrization of training shapes.

Related Experiment Videos

  • Demonstrated a practical method for automatic eigenshape model construction.

    • Main Results:

    • The genetic algorithm effectively optimizes the objective function.
    • Automatically generated models were often superior to hand-built counterparts.
    • The GA approach requires no prior assumptions about shape characteristics.

    Conclusions:

    • Automated eigenshape model construction is feasible and effective.
    • The proposed GA-based method offers a robust and efficient alternative to manual model building.
    • This approach enhances the utility of eigenshape models in medical image analysis.