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

A hybrid framework for 3D medical image segmentation.

Ting Chen1, Dimitris Metaxas

  • 1CBIM Center, Rutgers University, Piscataway, NJ 08854, USA. ting.chen@med.nyu.edu

Medical Image Analysis
|May 18, 2005
PubMed
Summary

This study introduces a hybrid 3D segmentation framework combining Gibbs, marching cubes, and deformable models for accurate 3D structure segmentation. The method achieves high-quality, efficient segmentation with minimal user input, demonstrated on brain tumors.

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

Analysis of cardiac dynamic global function.

JRSM cardiovascular disease·2026
Same author

MADCrowner: Margin Aware Dental Crown design with template deformation and refinement.

Medical image analysis·2026
Same author

SODA: Spectral Orthogonal Decomposition Adaptation for Diffusion Models.

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

Editorial for Special Issue on Foundation Models for Medical Image Analysis.

Medical image analysis·2024
Same author

Gloss Prior Guided Visual Feature Learning for Continuous Sign Language Recognition.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2024
Same author

Domain-Adversarial Transformer Network for Multiphase Liver Tumor Segmentation.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2023

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Computational Anatomy

Background:

  • Accurate 3D segmentation of complex structures is crucial for medical image analysis.
  • Existing methods often require significant user intervention or prior information.
  • Integrating region and boundary information can improve segmentation robustness.

Purpose of the Study:

  • To develop a novel hybrid 3D segmentation framework.
  • To improve segmentation accuracy and reduce user intervention.
  • To create a generic framework applicable to various clinical objects.

Main Methods:

  • A novel Gibbs model with a high-order clique system incorporating region and boundary information.
  • An improved marching cubes algorithm for 3D mesh generation from Gibbs model outputs.

Related Experiment Videos

  • Recursive application of Gibbs and deformable models with parameter updates.

    • Main Results:

    • The hybrid framework achieved high-quality 3D segmentations of complex structures, including brain tumors.
    • Segmentation results demonstrated computational efficiency and accuracy comparable to expert manual segmentations.
    • The method showed effectiveness as a generic segmentation framework for various clinical objects.

    Conclusions:

    • The proposed hybrid 3D segmentation framework offers an effective solution for segmenting complex structures.
    • The methodology provides high-quality segmentations with minimal prior information and user interaction.
    • The framework is computationally efficient and demonstrates broad applicability in medical imaging.