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 segmentation of echocardiographic sequences by active appearance motion models.

Johan G Bosch1, Steven C Mitchell, Boudewijn P F Lelieveldt

  • 1Division of Image Processing (LKEB), Department of Radiology, Leiden University Medical Center, PO Box 9600, 2300 RC Leiden, The Netherlands. j.g.bosch@lumc.nl

IEEE Transactions on Medical Imaging
|February 11, 2003
PubMed
Summary

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

Detailed quantification of right ventricular function in tetralogy of Fallot: a 3D echocardiography study.

European heart journal. Imaging methods and practice·2026
Same author

Apical Hypertrophic Cardiomyopathy and Elite-Level Sports: A 12-Year Follow-Up Case.

JACC. Case reports·2026
Same author

Correction: Continuous shear wave measurements for dynamic cardiac stiffness evaluation in pigs.

Scientific reports·2026
Same author

ENDOCOR: a nationwide consortium of endocarditis teams-initiating a registry for infective endocarditis within the Netherlands Heart Registration.

Netherlands heart journal : monthly journal of the Netherlands Society of Cardiology and the Netherlands Heart Foundation·2025
Same author

Pulse-inversion Doppler-based Phase-compensation Reduces Decorrelation in High-frame Rate Contrast-enhanced Ultrasound.

Ultrasound in medicine & biology·2025
Same author

Vortices and Hemodynamic Forces in the Left Ventricle: Comparison between High Frame Rate Echo-Particle Image Velocimetry and 4D Flow MRI.

Ultrasound in medicine & biology·2025

A new active appearance motion model (AAMM) automates left ventricular border detection in echocardiograms. This robust method achieves high accuracy, comparable to human experts, for improved cardiac imaging analysis.

Area of Science:

  • Medical Imaging
  • Cardiology
  • Computer Vision

Background:

  • Accurate delineation of left ventricular (LV) endocardial contours is crucial for echocardiographic analysis.
  • Traditional methods for border detection can be time-consuming and subject to inter-observer variability.

Purpose of the Study:

  • To introduce and evaluate a novel extension of active appearance models (AAMs) for automated border detection in echocardiographic image sequences.
  • To assess the robustness, accuracy, and time-continuity of the proposed active appearance motion model (AAMM) for LV endocardial contour delineation.

Main Methods:

  • Developed and implemented an active appearance motion model (AAMM) for automated delineation of LV endocardial contours.
  • Employed nonlinear intensity normalization to handle ultrasound-specific intensity distributions.

Related Experiment Videos

  • Trained and tested the AAMM on 16-frame transthoracic four-chamber echocardiographic sequences from 129 infarct patients.

    • Main Results:

    • The fully automated AAMM achieved robust and time-continuous delineation of LV endocardial contours across the cardiac cycle.
    • On the test set, the AAMM performed well in 97% of cases, with an average landmark point distance of 3.3 mm, comparable to human inter-observer variability.
    • The AAMM demonstrated significantly higher accuracy than equivalent 2D AAMs, highlighting the value of ultrasound-specific intensity normalization.

    Conclusions:

    • The active appearance motion model (AAMM) provides a highly accurate and automated solution for left ventricular endocardial border detection in echocardiography.
    • The developed nonlinear intensity normalization is essential for achieving good performance with ultrasound images.
    • This technique offers a significant advancement over existing methods, improving the efficiency and reliability of cardiac image analysis.