Jove
Visualize
Contact Us

Related Experiment Videos

A variational framework for integrating segmentation and registration through active contours.

A Yezzi1, L Zöllei, T Kapur

  • 1School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA.

Medical Image Analysis
|July 19, 2003
PubMed
Summary

This study presents a novel geometric framework using active contours for simultaneous image segmentation and registration. This approach integrates these traditionally separate tasks, improving feature analysis across multiple images.

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

Optimizing registration uncertainty visualization to support intraoperative decision-making during brain tumor resection.

International journal of computer assisted radiology and surgery·2025
Same author

Integrated 3D Anatomical Model for Automatic Myocardial Segmentation in Cardiac CT Imagery.

Computer methods in biomechanics and biomedical engineering. Imaging & visualization·2020
Same author

A geometric snake model for segmentation of medical imagery.

IEEE transactions on medical imaging·1997
Same author

Segmentation of brain tissue from magnetic resonance images.

Medical image analysis·1996
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

Area of Science:

  • Medical image analysis
  • Computer vision
  • Computational geometry

Background:

  • Image segmentation and registration are typically treated as independent problems.
  • Interdependence between segmentation and registration can affect solution accuracy.
  • Existing methods often fail to leverage the relationship between these tasks.

Purpose of the Study:

  • To introduce a unified geometric, variational framework for simultaneous segmentation and registration.
  • To address the limitations of solving segmentation and registration as separate problems.
  • To enable more accurate feature analysis from multiple images.

Main Methods:

  • Utilizes active contours within a geometric, variational framework.
  • Employs a single evolving contour to segment features across multiple images.

Related Experiment Videos

  • Simultaneously optimizes segmentation and registration through contour evolution and mapping.

    • Main Results:

    • Demonstrates the feasibility of joint segmentation and registration using active contours.
    • Shows that a single contour's evolution can drive segmentation in multiple images.
    • Provides a unified approach to a previously decoupled problem.

    Conclusions:

    • The proposed framework offers an integrated solution for segmentation and registration.
    • Simultaneous optimization enhances the analysis of features in multi-image datasets.
    • This approach advances the field of medical image analysis and computer vision.