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

Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm.

Maria Lorenzo-Valdés1, Gerardo I Sanchez-Ortiz, Andrew G Elkington

  • 1Visual Information Processing Group, Department of Computing, Imperial College London, 180 Queens' Gate, London SW7 2BZ, UK. maria.d.lorenzo-valdes@imperial.ac.uk

Medical Image Analysis
|September 29, 2004
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

Disparate privacy risks from medical AI.

Nature·2026
Same author

Local and global patterns support medical imaging as a biomarker of ageing.

Communications medicine·2026
Same author

Longitudinal Language-Model Reasoning Enables Automated Labeling of Lung Cancer Recurrence from Unstructured Clinical Records.

Research square·2026
Same author

Multiparametric Free-Breathing 3D Whole-Heart Cardiac MR for Anatomical Bright- and Black-Blood Imaging With Co-Registered <math><semantics><mrow><msub><mrow><mi>T</mi></mrow> <mrow><mn>1</mn></mrow></msub> <mo>/</mo> <msub><mrow><mi>T</mi></mrow> <mrow><mn>2</mn></mrow></msub></mrow> <annotation>$$ {T}_1/{T}_2 $$</annotation></semantics></math> Myocardial Tissue Mapping at <math><semantics><mrow><mn>0</mn> <mo>.</mo> <mn>55</mn></mrow> <annotation>$$ 0.55 $$</annotation></semantics></math> T.

NMR in biomedicine·2026
Same author

A Maturity Model for the Enforcement of PETs in Federated Settings.

Studies in health technology and informatics·2026
Same author

A deep-learning framework reveals whole-body perturbations at cell level.

Nature·2026

This study introduces an automatic segmentation algorithm for 4D cardiac MR images using a probabilistic atlas and expectation-maximization. The method accurately segments cardiac structures, demonstrating its potential for clinical applications.

Area of Science:

  • Medical Imaging
  • Biomedical Engineering
  • Computational Anatomy

Background:

  • Accurate segmentation of cardiac structures in 4D cardiac MR images is crucial for diagnosis and treatment planning.
  • Existing segmentation methods often require manual input, which is time-consuming and prone to inter-observer variability.

Purpose of the Study:

  • To develop and validate an automatic atlas-based segmentation algorithm for 4D cardiac MR images.
  • To assess the algorithm's accuracy in segmenting the left ventricle, right ventricle, and myocardium.

Main Methods:

  • The algorithm utilizes a 4D extension of the expectation-maximization (EM) algorithm combined with a 4D probabilistic cardiac atlas.
  • Spatial and temporal contextual information is integrated using 4D Markov Random Fields.

Related Experiment Videos

  • A global connectivity filter is applied to extract the largest connected component of each segmented structure.

    • Main Results:

    • The algorithm achieved high correlation coefficients for segmenting the left ventricle (LV) (r = 0.96), myocardium (r = 0.92), and right ventricle (r = 0.92) in healthy volunteers.
    • Validation using a 'leave one out' approach confirmed the robustness of the segmentation.
    • Good correlation was observed for LV (r = 0.93) and myocardium (0.94) volumes in patients with hypertrophic cardiomyopathy.

    Conclusions:

    • The proposed automatic atlas-based segmentation algorithm is effective and accurate for 4D cardiac MR images.
    • The method shows promise for clinical applications, particularly in assessing cardiac function and disease, such as hypertrophic cardiomyopathy.
    • Integration of probabilistic atlases and advanced algorithms like EM and MRFs enhances segmentation accuracy and efficiency.