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

Bayesian multimodality non-rigid image registration via conditional density estimation.

Jie Zhang1, Anand Rangarajan

  • 1Department of Computer and Information Science & Engineering, University of Florida, Gainesville, FL, USA.

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

Toward Improving the Generation Quality of Autoregressive Slot VAEs.

Neural computation·2024
Same author

Learning Canonical Embeddings for Unsupervised Shape Correspondence With Locally Linear Transformations.

IEEE transactions on pattern analysis and machine intelligence·2023
Same author

Machine-Learning-Based Real-Time Multi-Camera Vehicle Tracking and Travel-Time Estimation.

Journal of imaging·2022
Same author

Spherical Minimum Description Length.

Entropy (Basel, Switzerland)·2020
Same author

A model of crop diversification under labor shocks.

PloS one·2020
Same author

A Grassmannian Graph Approach to Affine Invariant Feature Matching.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2019
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

This study introduces a novel Bayesian method for multimodality non-rigid image registration, using a density estimator to replace the unknown likelihood. The approach establishes a criterion linking Bayesian maximum a posteriori (MAP) estimation to mutual information maximization.

Area of Science:

  • Medical Imaging
  • Computational Biology
  • Computer Vision

Background:

  • Multimodality image registration is crucial for integrating information from different imaging sources.
  • Mutual information (MI)-based methods are widely used but have limitations in general multimodality settings.
  • Accurate non-rigid registration is essential for detailed anatomical analysis and disease tracking.

Purpose of the Study:

  • To develop a Bayesian framework for non-rigid image registration applicable to multimodality data.
  • To address the challenge of an unknown likelihood function in multimodality registration.
  • To establish a theoretical link between the proposed Bayesian approach and existing MI-based methods.

Main Methods:

  • A Bayesian framework employing a density estimator as a surrogate for the unknown likelihood function.

Related Experiment Videos

  • Incorporation of a small deformation penalty as a prior on the displacement field.
  • Derivation of a criterion that equates Bayesian maximum a posteriori (MAP) optimization with mutual information maximization under specific conditions.

    • Main Results:

    • The proposed Bayesian method provides a robust alternative for multimodality non-rigid image registration.
    • A novel criterion is derived, connecting Bayesian MAP estimation with mutual information maximization.
    • Empirical validation on synthetic and real (T1/T2 2D MR) images demonstrates competitive performance compared to MI, joint entropy, and joint probability methods.

    Conclusions:

    • The Bayesian approach offers a principled and flexible framework for multimodality non-rigid image registration.
    • The derived criterion provides theoretical insights into the relationship between Bayesian inference and information-theoretic measures.
    • The method shows promise for applications requiring accurate alignment of diverse medical imaging data.