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

3D image segmentation of deformable objects with joint shape-intensity prior models using level sets.

Jing Yang1, James S Duncan

  • 1Departments of Electrical Engineering and Diagnostic Radiology, Yale University, P.O. Box 208042, New Haven, CT 06520-8042, USA. j.yang@yale.edu

Medical Image Analysis
|September 29, 2004
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

STNAGNN: Data-driven Spatio-temporal Brain Connectivity beyond FC.

Proceedings of machine learning research·2026
Same author

Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

Deep learning-based generation of synthetic multiphasic MRI in hepatocellular carcinoma and cirrhosis.

JHEP reports : innovation in hepatology·2026
Same author

MRCKα represses GEF-H1 mediated RhoA activation to promote ovarian cancer spheroid growth and invasion.

bioRxiv : the preprint server for biology·2026
Same author

CAUSAL MODELING OF FMRI TIME-SERIES FOR INTERPRETABLE AUTISM SPECTRUM DISORDER CLASSIFICATION.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

TOWARDS ZERO-SHOT TASK-GENERALIZABLE LEARNING ON FMRI.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026

This study introduces a new Bayesian method for 3D image segmentation using joint shape and gray level priors. The approach is robust to noise and avoids explicit point correspondences for improved segmentation accuracy.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Computational Anatomy

Background:

  • Accurate 3D image segmentation is crucial for medical diagnosis and analysis.
  • Traditional methods often struggle with noise and require explicit point correspondences.
  • Integrating shape and intensity information can improve segmentation robustness.

Purpose of the Study:

  • To develop a novel Bayesian method for 3D image segmentation.
  • To leverage joint prior knowledge of object shape and image gray levels.
  • To formulate a robust segmentation model using level set functions.

Main Methods:

  • A Bayesian formulation employing joint prior knowledge of object shape and image gray levels.
  • Maximum A Posteriori (MAP) estimation model for segmentation.

Related Experiment Videos

  • Shape-intensity model formulated using level set functions, avoiding landmark points.
  • Comparison with the Point Distribution Model (PDM).

    • Main Results:

    • The proposed method demonstrates robustness to noise in 2D and 3D medical images.
    • The algorithm effectively handles multidimensional data.
    • The level set representation proved comparable to PDM.
    • Explicit point correspondences were not required during training.

    Conclusions:

    • The novel Bayesian approach offers an effective and robust solution for 3D image segmentation.
    • The joint shape-intensity model using level sets enhances segmentation accuracy and efficiency.
    • The method's ability to avoid explicit point correspondences simplifies the training process.