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

Robust active appearance models and their application to medical image analysis.

Reinhard Beichel1, Horst Bischof, Franz Leberl

  • 1Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16/2, A-8010 Graz, Austria. beichel@icg.tu-graz.ac.at

IEEE Transactions on Medical Imaging
|September 15, 2005
PubMed
Summary

This study introduces a robust active appearance model (RAAM) for medical image segmentation. The novel RAAM algorithm effectively handles significant object disturbances, improving segmentation accuracy in challenging clinical scenarios.

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

MMP9 Genotype and Systemic T-Cell Subsets Correlate With Structural and Functional Outcomes in Neovascular Age-Related Macular Degeneration.

Investigative ophthalmology & visual science·2026
Same author

Loss of Enhancement in Vestibular Schwannomas Post Stereotactic Radiosurgery: Impact on Tumor Control and Serviceable Hearing: Erratum.

Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology·2026
Same author

Comparative Evaluation of Deep Learning Models for 3D Segmentation and Volumetry of Vestibular Schwannomas Using Large Heterogeneous Data Sets with External Validation.

AJNR. American journal of neuroradiology·2025
Same author

Fully automated IVUS image segmentation with efficient deep-learning-assisted annotation.

Computers in biology and medicine·2025
Same author

Loss of Enhancement in Vestibular Schwannomas Post Stereotactic Radiosurgery: Impact on Tumor Control and Serviceable Hearing.

Otology & neurotology : official publication of the American Otological Society, American Neurotology Society [and] European Academy of Otology and Neurotology·2025
Same author

Sli2Vol+: Segmenting 3D Medical Images Based on an Object Estimation Guided Correspondence Flow Network.

IEEE Winter Conference on Applications of Computer Vision. IEEE Winter Conference on Applications of Computer Vision·2025

Area of Science:

  • Medical Image Analysis
  • Computer Vision
  • Biomedical Engineering

Background:

  • Active Appearance Models (AAMs) are widely used for medical image segmentation.
  • Clinical settings often present gross object disturbances due to pathology or interventions.
  • Standard AAMs lack robustness against these significant variations.

Purpose of the Study:

  • To develop a novel robust Active Appearance Model (RAAM) matching algorithm.
  • To enhance the robustness of AAM-based segmentation in the presence of severe image disturbances.
  • To address limitations of existing methods by not assuming disturbance types or magnitudes.

Main Methods:

  • The RAAM algorithm employs a two-stage approach for robust matching.
  • Stage 1: Mean-shift-based mode detection to analyze initial residuals.

Related Experiment Videos

  • Stage 2: Utilization of an objective function to select outlier-free mode combinations.

    • Main Results:

    • The RAAM method demonstrates significant robustness across various noise conditions.
    • Quantitative evaluation in diaphragm segmentation and rheumatoid arthritis assessment shows excellent performance.
    • The RAAM algorithm tolerates up to 50% of the object area being affected by gross gray-level disturbances.

    Conclusions:

    • The proposed robust Active Appearance Model (RAAM) significantly improves segmentation reliability in medical imaging.
    • RAAM offers a powerful solution for segmenting images with substantial pathological or interventional disturbances.
    • This method advances the clinical applicability of AAMs in challenging real-world scenarios.