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

Coupled shape distribution-based segmentation of multiple objects.

Andrew Litvin1, William C Karl

  • 1Boston University, Boston, Massachusetts, USA. litvin@bu.edu

Information Processing in Medical Imaging : Proceedings of the ... Conference
|March 16, 2007
PubMed
Summary

This study introduces a novel multi-object prior shape model for image segmentation. This model enhances accuracy by capturing inter-object relationships in medical imaging.

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

Localized priors for the precise segmentation of individual vertebras from CT volume data.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2008
Same author

4Pi spectral self-interference microscopy.

Journal of the Optical Society of America. A, Optics, image science, and vision·2007
Same author

Spectral self-interference microscopy for low-signal nanoscale axial imaging.

Journal of the Optical Society of America. A, Optics, image science, and vision·2007
See all related articles

Area of Science:

  • Medical image analysis
  • Computer vision
  • Computational geometry

Background:

  • Image segmentation is crucial for medical diagnosis.
  • Existing methods often struggle with segmenting multiple interacting objects.
  • Prior shape information can improve segmentation accuracy and robustness.

Purpose of the Study:

  • To develop a multi-object prior shape model for curve evolution-based image segmentation.
  • To incorporate inter-object shape interactions into the prior model.
  • To apply the model to medical image segmentation tasks.

Main Methods:

  • Constructing a prior shape model from shape distributions (cumulative distribution functions).
  • Utilizing shape distribution-based object representations for robustness and invariance.
  • Integrating the multi-object prior into a curve evolution framework for shape estimation.

Main Results:

  • The developed prior model effectively captures shape features and inter-object interactions.
  • The curve evolution formulation with the prior model demonstrates improved performance in segmentation.
  • Successful application to challenging medical image segmentation problems.

Conclusions:

  • The proposed multi-object prior shape model enhances curve evolution-based image segmentation.
  • This approach offers a robust and generalizable method for segmenting multiple objects in medical images.
  • The model's ability to capture inter-object relationships is key to its improved performance.

Related Experiment Videos