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 Video

Updated: Jun 23, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Embedding overlap priors in variational left ventricle tracking.

Ismail Ben Ayed1, Shuo Li, Ian Ross

  • 1General Electric Canada (GE Healthcare), London, ON N6A 5P2, Canada. ismail.benayed@ge.com

IEEE Transactions on Medical Imaging
|May 22, 2009
PubMed
Summary

This study introduces overlap priors for variational tracking of the left ventricle (LV) in cardiac MRI. The novel method accurately segments cardiac structures without geometric training, improving clinical flexibility.

Related Concept Videos

Deconvolution01:20

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Economic burden of depressive disorders and HIV for people living with HIV in Uganda.

Health policy and planning·2026
Same author

Cost-effectiveness and benefit-cost analyses of promoting handwashing with soap: A systematic review.

PLoS medicine·2026
Same author

Cost of illness of scrub typhus in South India - a population-based, mixed-methods study.

PLoS neglected tropical diseases·2026
Same author

Effectiveness of domestic food hygiene interventions on the microbiological quality of child food and childhood diarrhoea: a systematic review and meta-analysis.

BMJ global health·2026
Same author

Assessing the effectiveness of a depression-integrated model in adult HIV care in Uganda (the HIV+D trial): a cluster-randomised controlled trial.

The lancet. HIV·2026
Same author

Shining a light on hidden PFAS: Development of a UV-reducible organic fluorine assay for the rapid screening of PFAS in AFFF, water, soils, and commercial products.

Journal of hazardous materials·2025

Area of Science:

  • Medical Imaging
  • Biomedical Engineering
  • Computational Cardiology

Background:

  • Accurate segmentation of the left ventricle (LV) in cardiac magnetic resonance (MR) sequences is crucial for diagnosing cardiovascular diseases.
  • Existing methods often rely on geometric priors or extensive training data, limiting their adaptability.

Purpose of the Study:

  • To develop a novel variational tracking method for LV segmentation using overlap priors.
  • To improve the accuracy and flexibility of cardiac image analysis by reducing reliance on predefined geometric models.

Main Methods:

  • Embedding nonparametric overlap priors, measured by the Bhattacharyya coefficient, into variational curve evolution equations.
  • Minimizing functionals incorporating these priors to guide segmentation of LV endocardium and epicardium boundaries.

Related Experiment Videos

Last Updated: Jun 23, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

  • Learning priors from a single frame's intensity distributions for LV cavity, myocardium, and background.

    • Main Results:

    • The proposed method achieved competitive segmentation accuracy compared to existing techniques, without requiring geometric training or preprocessing.
    • Overlap priors effectively prevented erroneous inclusion of papillary muscles and spilling into the background.
    • Overlap measures were found to be approximately constant across cardiac sequences, enabling single-frame prior learning.

    Conclusions:

    • The developed overlap prior method offers a flexible and accurate approach for LV segmentation in cardiac MR.
    • This technique enhances clinical utility by adapting to current intensity data, independent of training set limitations.
    • The findings support the use of learned overlap priors for robust and efficient cardiac image analysis.