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

Elastic registration of biological images using vector-spline regularization.

Carlos O S Sorzano1, Philippe Thévenaz, Michael Unser

  • 1Biomedical Imaging Group, Swiss Federal Institute of Technology Lausanne (EPFL), Switzerland. cos@cnb.uam.es

IEEE Transactions on Bio-Medical Engineering
|April 14, 2005
PubMed
Summary

This study introduces an advanced elastic registration algorithm for aligning biological images. The method uses B-spline models and vector-spline regularization for accurate deformation handling and landmark constraints, showing favorable expert validation.

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

Revisiting deep information propagation: Fractal frontier and finite-size effects.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

The Inaugural Flatiron Institute Cryo-EM Conformational Heterogeneity Challenge.

bioRxiv : the preprint server for biology·2025
Same author

Revisiting PSF models: Unifying framework and high-performance implementation.

Journal of microscopy·2025
Same author

Perturbative Fourier ptychographic microscopy for fast quantitative phase imaging.

Optics express·2025
Same author

Model-based temporal unmixing towards quantitative photo-switching optoacoustic tomography.

Optics express·2025
Same author

Point-spread-function engineering in MINFLUX: optimality of donut and half-moon excitation patterns.

Optics letters·2024

Area of Science:

  • Biomedical Imaging
  • Computational Biology
  • Image Analysis

Background:

  • Accurate alignment of biological images is crucial for quantitative analysis.
  • Existing elastic registration methods have limitations in handling complex deformations and sparse data.
  • Integration of advanced modeling techniques can improve registration accuracy.

Purpose of the Study:

  • To develop and validate a novel elastic registration algorithm for biological image alignment.
  • To enhance the handling of diverse and complex image deformations.
  • To incorporate soft landmark constraints for improved accuracy in data-scarce regions.

Main Methods:

  • The algorithm employs a B-spline model for the deformation field, allowing for rich deformation representation.

Related Experiment Videos

  • Registration is achieved by minimizing pixelwise mean-square distance between images.
  • Vector-spline regularization is used to control deformation divergence and curl, alongside soft landmark constraints.

    • Main Results:

    • The B-spline model effectively handles a wide range of deformations.
    • Vector-spline regularization provides control over intrinsic deformation properties.
    • The algorithm successfully registered challenging biological images, including electrophoretic gels and fly embryos.
    • Expert validation confirmed the favorable accuracy of the registration results.

    Conclusions:

    • The presented elastic registration algorithm offers a robust and accurate solution for biological image alignment.
    • The combination of B-spline modeling and vector-spline regularization enhances registration performance.
    • The method's ability to handle soft landmarks makes it versatile for various biological imaging applications.