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 unifying approach to registration, segmentation, and intensity correction.

Kilian M Pohl1, John Fisher, James J Levitt

  • 1Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, USA. pohl@csail.mit.edu

Medical Image Computing and Computer-Assisted Intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
|May 12, 2006
PubMed
Summary

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

Leveraging Machine Learning to Advance Alcohol Research: Current Applications, Challenges, and Opportunities.

Alcohol research : current reviews·2026
Same author

Mapping Individualized Developmental Imbalance in Youth and Its Association with Psychopathology.

bioRxiv : the preprint server for biology·2026
Same author

Using deep learning to identify brain networks mediating cognitive and motor impairments in alcohol use disorder.

Translational psychiatry·2026
Same author

A generalized synthetic control algorithm for sparse functional data.

bioRxiv : the preprint server for biology·2026
Same author

Advancing In-Context Learning for Efficient and Stable Medical Report Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Integrating Anatomical Priors Into a Causal Diffusion Model.

IEEE transactions on medical imaging·2026

This study introduces a new statistical framework for magnetic resonance image analysis. The integrated approach improves the accuracy of brain tissue segmentation and anatomical mapping compared to separate methods.

Area of Science:

  • Medical Imaging
  • Computational Anatomy
  • Statistical Modeling

Background:

  • Accurate segmentation of anatomical structures in magnetic resonance images (MRIs) is crucial for neurological studies.
  • Existing methods often separate image registration and segmentation, potentially leading to suboptimal results.
  • Simultaneous estimation of image properties and anatomical labels can improve segmentation quality.

Purpose of the Study:

  • To develop a unified statistical framework for simultaneous atlas registration and MRI segmentation.
  • To estimate image inhomogeneities, anatomical labelmaps, and atlas-to-image spatial mappings concurrently.
  • To evaluate the performance of the integrated approach for brain tissue segmentation.

Main Methods:

  • An Expectation Maximization (EM)-based algorithm was developed to solve the integrated model.

Related Experiment Videos

  • The framework simultaneously estimates image inhomogeneities, anatomical labelmaps, and atlas-to-image mappings.
  • A brain structure-dependent affine mapping was used as an example application.

    • Main Results:

    • The algorithm achieved high-quality segmentation of brain tissues and substructures.
    • The integrated approach demonstrated superior performance compared to methods that separate registration and segmentation.
    • Validation was performed on a dataset of 22 magnetic resonance images.

    Conclusions:

    • The proposed statistical framework offers an effective method for simultaneous MRI segmentation and atlas registration.
    • Integrating registration and segmentation within a single model enhances segmentation accuracy for brain structures.
    • This unified approach outperforms conventional, stepwise methods in MRI analysis.