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

The adaptive bases algorithm for intensity-based nonrigid image registration.

Gustavo K Rohde1, Akram Aldroubi, Benoit M Dawant

  • 1STBB/LIMB/NICHD, National Institutes of Health, Bethesda, MD 02872, USA. rohdeg@helix.nih.gov

IEEE Transactions on Medical Imaging
|November 11, 2003
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

Linear Optimal Transport Subspaces for Point Set Classification.

Journal of mathematical imaging and vision·2026
Same author

Insertion Network for Image Sequence Correspondence Building.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

DermIDS: Dermatology imaging data structure for scalable and interoperable AI systems.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

Integrating 2D Dermatological Photography with 3D Anatomical Surfaces.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

Assessing Open-world Foundation Models for Zero-shot Skin Segmentation in Clinical Dermatological Photographs.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

Predictors of motor outcome with pallidal stimulation for Parkinson's disease from the CSP468 cohort.

NPJ Parkinson's disease·2026
Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026
Same journal

Informed-Exploration Reinforcement Learning for Automated Virtual Coronary Intervention Planning.

IEEE transactions on medical imaging·2026
Same journal

4D Reconstruction of Fetal Left Ventricle from Echocardiography via 2.5D Radial Segmentation and Graph-Fourier Reconstruction.

IEEE transactions on medical imaging·2026
Same journal

Generalised Medical Phrase Grounding.

IEEE transactions on medical imaging·2026
Same journal

EndoLRMGS: Combining Large Reconstruction Modelling and Gaussian Splatting for Complete Endoscopic Scene Reconstruction.

IEEE transactions on medical imaging·2026
Same journal

A Neural-Analytical Fusion Scatter Correction Method for Multi-Source CT Using Equivalent High-Order Scatter.

IEEE transactions on medical imaging·2026
See all related articles

This study introduces an adaptive nonrigid medical image registration method that speeds up processing and improves accuracy by spatially adapting transformation compliance. The novel approach uses radially symmetric basis functions and problem partitioning for efficient and topologically correct image alignment.

Area of Science:

  • Medical image analysis
  • Computational anatomy
  • Image registration

Background:

  • Nonrigid medical image registration is crucial for applications like population averaging and atlas-based segmentation.
  • Current mutual information (MI)-based methods using B-splines face computational complexity limitations tied to transformation compliance.
  • Existing methods can be computationally intensive, especially for complex deformations.

Purpose of the Study:

  • To develop a novel nonrigid medical image registration method with spatially adapted transformation compliance.
  • To improve computational efficiency and convergence properties of medical image registration.
  • To enhance the accuracy and topological correctness of image registration algorithms.

Main Methods:

  • Utilized radially symmetric basis functions instead of traditional B-splines for deformation modeling.

Related Experiment Videos

  • Introduced a metric to identify poorly registered regions for targeted improvement.
  • Partitioned the global registration problem into smaller, manageable sub-problems.
  • Implemented a new constraint scheme ensuring topologically correct transformations.

    • Main Results:

    • The proposed method demonstrates improved computational efficiency compared to traditional approaches.
    • Spatial adaptation of transformation compliance leads to faster convergence.
    • The algorithm achieves favorable comparisons against existing medical image registration techniques.
    • The method produces topologically correct transformations.

    Conclusions:

    • The novel registration method offers significant advantages in speed and convergence.
    • Spatially adaptive compliance and novel techniques enhance nonrigid medical image registration.
    • This approach provides a more efficient and accurate solution for medical image alignment tasks.