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

Semi-automatic segmentation and tracking of CVH data.

Yingge Qu1, Pheng Ann Heng, Tien-Tsin Wong

  • 1Dept. of Computer Science & Enginering, The Chinese University of Hong Kong. ygqu@cse.cuhk.edu.hk

Studies in Health Technology and Informatics
|January 13, 2006
PubMed
Summary

This study introduces a unified variational framework for medical image segmentation and tracking using the Chinese Visible Human dataset. The method enhances accuracy and reduces user intervention for segmenting and tracking organs in high-resolution medical images.

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

HiVLR: Hierarchical Vision-Language Reasoning for interpretable zero-shot radiography image understanding.

Medical image analysis·2026
Same author

Learning the PTM code through a coarse-to-fine mechanism-aware framework.

Nature communications·2026
Same author

Advancing radiograph representation learning via cascading graph alignment for vision-language clinical concepts.

Medical image analysis·2026
Same author

Consistent and Controllable Image Animation With Linear Motion Diffusion Transformers.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Unified and explainable molecular representation learning for imperfectly annotated data from the hypergraph view.

Nature communications·2025
Same author

ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis.

IEEE transactions on pattern analysis and machine intelligence·2025

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Biomedical Engineering

Background:

  • Level set methods are vital for medical image segmentation.
  • Accurate segmentation and tracking of anatomical structures are essential for diagnosis and treatment planning.
  • High-resolution data, like the Chinese Visible Human (CVH) dataset, presents unique challenges.

Purpose of the Study:

  • To develop a unified variational framework for segmenting and tracking medical image data.
  • To construct an effective speed function for the level set method in medical imaging.
  • To reduce user intervention in the segmentation and tracking of anatomical structures.

Main Methods:

  • A variational framework was developed to unify segmentation and tracking.
  • The framework focuses on constructing a robust speed function for the level set evolution.

Related Experiment Videos

  • The method was applied to segment the initial slice and track subsequent slices of the CVH data.

    • Main Results:

    • The proposed method achieved promising segmentation results on the CVH dataset.
    • The tracking procedure demonstrated a significant reduction in user intervention.
    • The unified approach effectively segments initial data and tracks structures in serial images.

    Conclusions:

    • The developed variational framework offers a unified approach for medical image segmentation and tracking.
    • The method is effective for high-resolution data and reduces the need for manual input.
    • This approach advances the application of level set methods in medical image analysis.