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: Jul 16, 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

Improving segmentation of the left ventricle using a two-component statistical model.

Sebastian Zambal1, Jifi Hladůvka, Katja Bühler

  • 1VRVis Research Center for Virtual Reality and Visualization, Donau-City-Strasse 1, 1220 Vienna, Austria.

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|March 16, 2007
PubMed
Summary

This study introduces a novel segmentation method for cardiac MRI, interconnecting 2D Active Appearance Models (AAMs) with a 3D shape model. This approach enhances segmentation accuracy, particularly with imperfect data, outperforming traditional 3D AAMs.

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

Multimodal, quantitative analysis enables process management of productive, mixotrophic biofilms.

Bioresource technology·2026
Same author

Computational reconstruction of evolutionary selection in human brain networks.

Frontiers in neuroinformatics·2026
Same author

Multi-modal brain data exploration software for imaging transcriptomics: A comparative evaluation and future directions.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

Circuit Mining in Transcriptomics Data.

IEEE computer graphics and applications·2025
Same author

Towards net zero land biotechnology: an assessment of biogenic feedstock potential for selected bioprocesses in Germany.

Biotechnology for biofuels and bioproducts·2025
Same author

AI-in-The-Loop: The Future of Biomedical Visual Analytics Applications in the Era of AI.

IEEE computer graphics and applications·2025

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Biomedical Engineering

Background:

  • Segmentation accuracy of 3D Active Appearance Models (AAMs) is limited by noisy, incomplete, and motion-affected cardiac MRI data.
  • Standard AAMs struggle to model local variations effectively.
  • Existing methods often require pristine training data, which is rare in cardiac MRI.

Purpose of the Study:

  • To develop an improved cardiac MRI segmentation technique that addresses data imperfections.
  • To overcome the limitations of pure 3D AAMs in modeling local variations.
  • To enhance segmentation performance using a hybrid 2D/3D modeling approach.

Main Methods:

  • Interconnecting multiple 2D Active Appearance Models (AAMs) using a unified 3D shape model.

More Related Videos

3D Modeling of the Lateral Ventricles and Histological Characterization of Periventricular Tissue in Humans and Mouse
15:26

3D Modeling of the Lateral Ventricles and Histological Characterization of Periventricular Tissue in Humans and Mouse

Published on: May 19, 2015

Related Experiment Videos

Last Updated: Jul 16, 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

3D Modeling of the Lateral Ventricles and Histological Characterization of Periventricular Tissue in Humans and Mouse
15:26

3D Modeling of the Lateral Ventricles and Histological Characterization of Periventricular Tissue in Humans and Mouse

Published on: May 19, 2015

  • Developing a split-model inspired approach for cardiac image segmentation.
  • Utilizing a novel framework to handle noisy and incomplete MRI data.

    • Main Results:

    • The proposed method demonstrates improved robustness in segmenting cardiac MRI with imperfect data.
    • Average segmentation improvement of 11% was achieved compared to traditional 3D AAMs.
    • The hybrid 2D/3D model effectively captures local variations missed by pure 3D AAMs.

    Conclusions:

    • The proposed method of interconnecting 2D AAMs via a 3D shape model offers a significant advancement in cardiac MRI segmentation.
    • This approach provides a viable solution for segmenting challenging cardiac datasets.
    • The findings suggest a promising direction for improving automated medical image analysis.