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

Non-rigid image registration using a statistical spline deformation model.

Dirk Loeckx1, Frederik Maes, Dirk Vandermeulen

  • 1Medical Image Computing (Radiology-ESAT/PSI), Faculties of Medicine and Engineering, University Hospital Gasthuisberg, Herestraat 49, B-3000 Leuven, Belgium. Dirk.Loeckx@uz.kuleuven.ac.be

Information Processing in Medical Imaging : Proceedings of the ... Conference
|September 4, 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

Real-World Evaluation of AI-Assisted Readout of Skin Prick Automated Test Results.

Allergy·2026
Same author

An autoencoder and vision transformer based interpretability analysis on the performance differences in automated staging of second and third molars.

Scientific reports·2025
Same author

Automated Classification of Neuromuscular Diseases Using Thigh Muscle MRI With Model Interpretations.

Journal of cachexia, sarcopenia and muscle·2025
Same author

Artificial Intelligence (AI)-assisted readout method for the evaluation of skin prick automated test results.

Nature communications·2025
Same author

Automated quantification of lung pathology on micro-CT in diverse disease models using deep learning.

EBioMedicine·2025
Same author

Local response function estimation in spherical deconvolution for comprehensive tissue representation using diffusion MRI.

Imaging neuroscience (Cambridge, Mass.)·2025
Same journal

Enhancing Alzheimer's Diagnosis: Leveraging Anatomical Landmarks in Graph Convolutional Neural Networks on Tetrahedral Meshes.

Information processing in medical imaging : proceedings of the ... conference·2026
Same journal

Cycle-Consistent Zero-Shot Through-Plane Super-Resolution for Anisotropic Head MRI.

Information processing in medical imaging : proceedings of the ... conference·2026
Same journal

Brightness-Invariant Tracking Estimation in Tagged MRI.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

Multi-View and Multi-Scale Alignment for Contrastive Language-Image Pre-training in Mammography.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

Using Multiple Instance Learning to Build Multimodal Representations.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

mSPD-NN: A Geometrically Aware Neural Framework for Biomarker Discovery from Functional Connectomics Manifolds.

Information processing in medical imaging : proceedings of the ... conference·2024
See all related articles

A new statistical spline deformation model (SSDM) reduces computational complexity for non-rigid image registration. This method achieves accurate results with significantly fewer parameters, improving efficiency in medical imaging analysis.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Biomedical Engineering

Background:

  • Non-rigid image registration is crucial for analyzing medical images, but often computationally intensive.
  • Existing methods may require a high number of parameters, leading to increased processing time and memory usage.

Purpose of the Study:

  • To introduce a Statistical Spline Deformation Model (SSDM) for efficient non-rigid image registration.
  • To reduce the degrees of freedom in non-rigid registration while maintaining accuracy.
  • To integrate user-defined transformations within a unified framework.

Main Methods:

  • Developed a Statistical Spline Deformation Model (SSDM) using statistically trained B-spline deformation meshes.
  • Employed Principal Component Analysis (PCA) to train the model and identify significant modes of variation.

Related Experiment Videos

  • Merged user-defined transformation components (e.g., affine modes) with principal components.
  • Applied the SSDM to temporal registration of thorax CR-images using pattern intensity.

    • Main Results:

    • Achieved a 33% reduction in degrees of freedom using 30 training pairs without compromising registration accuracy.
    • Maintained the same accuracy as traditional methods even after reducing degrees of freedom by up to 66%.
    • Demonstrated the model's ability to optimize along transformation components rather than individual spline coefficients.

    Conclusions:

    • The Statistical Spline Deformation Model (SSDM) offers a computationally efficient approach to non-rigid image registration.
    • SSDM effectively reduces the number of parameters required for accurate image registration, particularly in medical applications.
    • This model provides a flexible framework for incorporating various transformation types, enhancing its applicability in complex imaging scenarios.