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

Regional appearance in deformable model segmentation.

Joshua V Stough1, Robert E Broadhurst, Stephen M Pizer

  • 1Medical Image Display & Analysis Group (MIDAG), University of North Carolina, Chapel Hill NC 27599, USA. stough@cs.unc.edu

Information Processing in Medical Imaging : Proceedings of the ... Conference
|July 19, 2007
PubMed
Summary
This summary is machine-generated.

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

Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos.

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision·2026
Same author

A Large-scale Multimodal Study for Predicting Mortality Risk Using Minimal and Low Parameter Models and Separable Risk Assessment.

IEEE journal of biomedical and health informatics·2025
Same author

Skeletons, Object Shape, Statistics.

Frontiers in computer science·2023
Same author

Generalizability and quality control of deep learning-based 2D echocardiography segmentation models in a large clinical dataset.

The international journal of cardiovascular imaging·2022
Same author

Fitting unbranching skeletal structures to objects.

Medical image analysis·2021
Same author

A Novel Method for High-Dimensional Anatomical Mapping of Extra-Axial Cerebrospinal Fluid: Application to the Infant Brain.

Frontiers in neuroscience·2020
Same journal

Enhancing Alzheimer's Diagnosis: Leveraging Anatomical Landmarks in Graph Convolutional Neural Networks on Tetrahedral Meshes.

Information processing in medical imaging : proceedings of the ... conference·2026
Same journal

Cycle-Consistent Zero-Shot Through-Plane Super-Resolution for Anisotropic Head MRI.

Information processing in medical imaging : proceedings of the ... conference·2026
Same journal

Brightness-Invariant Tracking Estimation in Tagged MRI.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

Multi-View and Multi-Scale Alignment for Contrastive Language-Image Pre-training in Mammography.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

Using Multiple Instance Learning to Build Multimodal Representations.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

mSPD-NN: A Geometrically Aware Neural Framework for Biomarker Discovery from Functional Connectomics Manifolds.

Information processing in medical imaging : proceedings of the ... conference·2024
See all related articles

This study compares three image appearance models for medical image segmentation. More localized models improved segmentation accuracy by better capturing intensity variations near organ boundaries.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Radiotherapy

Background:

  • Automated medical image segmentation is crucial for clinical applications.
  • Effective image appearance models are needed to characterize image intensity near object boundaries.
  • Deformable models are commonly used for segmentation tasks.

Purpose of the Study:

  • To compare three regional scale appearance models for statistical characterization of image intensity near object boundaries.
  • To evaluate the performance of these models in the context of segmentation using deformable models.
  • To assess the impact of regional scale on segmentation accuracy.

Main Methods:

  • Developed three appearance models based on regional intensity quantile functions.
  • Utilized principal component analysis to build statistical appearance models.

Related Experiment Videos

  • Evaluated models on bladder and prostate segmentation in CT images for adaptive radiotherapy.

    • Main Results:

    • Segmentation results showed improved accuracy with more localized regional models.
    • Smaller regions better represented local intensity inhomogeneity near organ boundaries.
    • The third model, analyzing descriptors per geometrically defined local region, yielded the best results.

    Conclusions:

    • Localized image appearance models enhance the accuracy of automated medical image segmentation.
    • Characterizing intensity distributions at finer scales improves the representation of complex anatomical structures.
    • The findings support the use of detailed regional analysis for deformable model-based segmentation in radiotherapy.