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

A marginalized MAP approach and EM optimization for pair-wise registration.

Lilla Zöllei1, Mark Jenkinson, Samson Timoner

  • 1A. A. Martinos Center, MGH, USA. lzollei@nmr.mgh.harvard.edu

Information Processing in Medical Imaging : Proceedings of the ... Conference
|July 19, 2007
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

Predicting Knee osteoarthritis progression using explainable machine learning and clinical imaging data.

Osteoarthritis and cartilage open·2026
Same author

Cognitive reserve proxies predict cognition and motor function beyond multimodal MRI brain measures in healthy adults.

Biological psychology·2026
Same author

Fast segmentation with the NextBrain histological atlas.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

Cortical reconstruction and anatomical parcellation of high-resolution multi-modal postmortem <i>ex vivo</i> MRI of the human infant brain.

bioRxiv : the preprint server for biology·2026
Same author

Deep infant brain segmentation from multi-contrast MRI.

Conference record. Asilomar Conference on Signals, Systems & Computers·2026
Same author

Repetitive transcranial magnetic stimulation for post-stroke depression: Associations between neural damage and treatment response.

Journal of affective disorders·2026
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 maximum a posteriori (MAP) framework for pair-wise image registration. The developed Expectation-Maximization (EM) algorithm efficiently solves entropy-based registration problems, demonstrating effectiveness in intra-operative scenarios.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Computational Anatomy

Background:

  • Pair-wise image registration is crucial for aligning medical images.
  • Existing methods often struggle with complex registration tasks, such as intra-operative scenarios.
  • Maximum a posteriori (MAP) frameworks offer a probabilistic approach to registration.

Purpose of the Study:

  • To develop a novel MAP framework for pair-wise image registration.
  • To address the challenge of nuisance parameters in registration by marginalization.
  • To introduce an efficient optimization algorithm for entropy-based registration.

Main Methods:

  • Formalized pair-wise registration within a MAP framework using a multinomial model of joint intensities.
  • Treated multinomial parameters as nuisance parameters and marginalized them out.

Related Experiment Videos

  • Utilized the Expectation-Maximization (EM) algorithm to optimize the marginalized objective function.

    • Main Results:

    • Marginalization leads to joint entropy minimization with uninformative priors and pooled entropy minimization with informative priors.
    • The EM algorithm provides a simple and effective iteration for entropy-based registration.
    • Demonstrated rapid and effective solving of a challenging intra-operative registration problem.

    Conclusions:

    • The proposed MAP framework and EM algorithm offer an effective solution for pair-wise image registration.
    • The method shows particular promise for challenging intra-operative registration tasks.
    • This approach advances the field of medical image analysis and computational anatomy.