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

Physical model-based non-rigid registration incorporating statistical shape information.

Y Wang1, L H Staib

  • 1Department of Diagnostic Radiology, Yale University, School of Medicine, New Haven, CT 06520-8042, USA. wang@noodle.med.yale.edu

Medical Image Analysis
|September 6, 2000
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

Machine Learning in Differentiating Gliomas from Primary CNS Lymphomas: A Systematic Review, Reporting Quality, and Risk of Bias Assessment.

AJNR. American journal of neuroradiology·2022
Same author

Scientific Collaboration across Time and Space: Bibliometric Analysis of the <i>American Journal of Neuroradiology</i>, 1980-2018.

AJNR. American journal of neuroradiology·2020
Same author

AUGMENTED INLINE-BASED NAVIGATION FOR STEREOTACTIC IMAGE GUIDED NEUROSURGERY.

Proceedings. IEEE International Symposium on Biomedical Imaging·2013
Same author

TRACKING ORGAN OVERLAP FOR A CONSTRAINED NON-RIGID REGISTRATION ALGORITHM.

Proceedings. IEEE International Symposium on Biomedical Imaging·2011
Same author

Improving the Reliability of Shape Comparison by Perturbation.

Proceedings. IEEE International Symposium on Biomedical Imaging·2011
Same author

LIGHT-SENSITIVE VISUALIZATION OF MULTIMODAL DATA FOR NEUROSURGICAL APPLICATIONS.

Proceedings. IEEE International Symposium on Biomedical Imaging·2011

This study introduces two novel non-rigid registration methods for medical images, combining physical and statistical shape models. These advanced techniques improve accuracy and robustness in anatomical detail mapping.

Area of Science:

  • Medical imaging
  • Computational anatomy
  • Biomedical engineering

Background:

  • Non-rigid registration is crucial for analyzing medical images, enabling detailed anatomical comparisons.
  • Existing methods often struggle with complex deformations and maintaining anatomical consistency.

Purpose of the Study:

  • To develop and evaluate two novel atlas-based, 2D single modality non-rigid registration methods.
  • To enhance registration accuracy and robustness by integrating physical and statistical shape models.

Main Methods:

  • Developed two methods using physical models (elastic solids, viscous fluids) for transformation constraints.
  • Employed a Bayesian formulation integrating physical models, intensity similarity, and statistical shape information.
  • Utilized dense forces for anatomical detail and sparse forces for shape model consistency.

Related Experiment Videos

Main Results:

  • Statistical shape information significantly improves physical model-based non-rigid registration.
  • Both methods demonstrated improved accuracy and robustness in experiments on synthetic and real medical images (brain, heart).
  • Each method showed advantages under different experimental conditions.

Conclusions:

  • The proposed atlas-based methods offer accurate and robust non-rigid registration for medical imaging.
  • Combining physical and statistical shape models provides a powerful framework for deformable image registration.
  • These methods advance the analysis of anatomical structures in medical imaging applications.