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

Simultaneous segmentation of multiple closed surfaces using optimal graph searching.

Kang Li1, Steven Millington, Xiaodong Wu

  • 1Dept. of Electrical and Computer Engineering, Carnegie Mellon University, 5000 Forbes Ave, Pittsburgh, PA 15213, USA. kangl@cmu.edu

Information Processing in Medical Imaging : Proceedings of the ... Conference
|March 16, 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

Decouple, Reorganize, and Fuse: A Multimodal Framework for Cancer Survival Prediction.

IEEE transactions on medical imaging·2026
Same author

Cell Instance Segmentation: The Devil Is in the Boundaries.

IEEE transactions on medical imaging·2025
Same author

CONUNETR: A CONDITIONAL TRANSFORMER NETWORK FOR 3D MICRO-CT EMBRYONIC CARTILAGE SEGMENTATION.

Proceedings. IEEE International Symposium on Biomedical Imaging·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
Same author

DeepPhosPPI: a deep learning framework with attention-CNN and transformer for predicting phosphorylation effects on protein-protein interactions.

Briefings in bioinformatics·2025
Same author

Rethinking deep learning in bioimaging through a data centric lens.

Npj imaging..·2025
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 introduces a graph-based method for segmenting multiple surfaces in 3D images. The technique accurately co-segments bone and cartilage in ankle MRIs, demonstrating its utility in biomedical image analysis.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Computational Anatomy

Background:

  • Accurate segmentation of multiple anatomical structures is crucial for quantitative analysis in medical imaging.
  • Existing methods often struggle with complex geometries and simultaneous segmentation of multiple surfaces.

Purpose of the Study:

  • To develop a general graph-theoretic technique for simultaneous segmentation of multiple closed surfaces in volumetric images.
  • To apply and validate this method for co-segmenting bone and cartilage in 3D magnetic resonance (MR) images of human ankles.

Main Methods:

  • A novel graph-construction scheme using triangulated surface meshes from topological presegmentation.
  • An efficient graph-cut algorithm guaranteeing global optimality under specified cost functions and geometric constraints.

Related Experiment Videos

Main Results:

  • Demonstrated applicability to challenging biomedical image analysis tasks.
  • Achieved highly accurate co-segmentation of bone and cartilage surfaces in 3D ankle MR images.
  • Validated against manual tracings, showing minimal signed surface positioning errors (bone: 0.02 ± 0.11mm, cartilage: 0.17 ± 0.12mm).

Conclusions:

  • The proposed graph-theoretic technique offers a robust and accurate solution for simultaneous multi-surface segmentation.
  • This method shows significant potential for advancing quantitative analysis in medical image interpretation, particularly for complex joint structures.