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 Video

Updated: Jun 12, 2026

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Learning task-optimal registration cost functions for localizing cytoarchitecture and function in the cerebral

B T Thomas Yeo1, Mert R Sabuncu, Tom Vercauteren

  • 1Computer Science and Artificial Intelligence Laboratory, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, USA. ythomas@csail.mit.edu

IEEE Transactions on Medical Imaging
|June 10, 2010
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

Excessive Censoring Degrades Individual-Specific Cortical Parcellations and Personalized TMS Targets.

bioRxiv : the preprint server for biology·2026
Same author

Atrophy in preclinical Alzheimer's disease maps to a network that predicts longitudinal decline.

Molecular psychiatry·2026
Same author

Individual-specific resting-state networks predict language dominance in drug-resistant epilepsy.

Epilepsia·2026
Same author

Widespread use of invalid statistical tests in biomedical machine learning.

bioRxiv : the preprint server for biology·2026
Same author

Developing a multi-modal neuroimaging-based BrainAge model across childhood.

bioRxiv : the preprint server for biology·2026
Same author

Convergent and divergent brain-cognition development in early adolescence.

Nature communications·2026

This study introduces a machine learning framework to automatically learn parameters for image registration cost functions. This optimizes image alignment for specific applications, improving localization of brain regions in neuroimaging data.

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Machine Learning

Background:

  • Image registration commonly involves manual parameter tuning, limiting its adaptability.
  • Generic registration algorithms require specialization for specific imaging modalities and tasks.
  • Current methods often assume macro-anatomy perfectly predicts cortical function, which is not always true.

Purpose of the Study:

  • To develop a principled machine learning framework for learning image registration cost function parameters.
  • To systematically adapt generic registration algorithms to specific applications by learning cost function parameters.
  • To improve the localization of cytoarchitecture and functional regions in the cerebral cortex.

Main Methods:

  • Formulated image registration as an optimization problem with a machine learning layer for parameter selection.

More Related Videos

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment
09:30

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Published on: May 23, 2025

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET
09:03

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET

Published on: October 22, 2019

Related Experiment Videos

Last Updated: Jun 12, 2026

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment
09:30

Localizing Function-specific Targets for Transcranial Magnetic Stimulation in the Absence of Navigation Equipment

Published on: May 23, 2025

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET
09:03

Radiotracer Administration for High Temporal Resolution Positron Emission Tomography of the Human Brain: Application to FDG-fPET

Published on: October 22, 2019

  • Employed cross-validation error optimization to learn thousands of registration cost function parameters.
  • Learned optimal weights on cortical folds or an optimal cortical folding template for image registration.

    • Main Results:

    • Achieved state-of-the-art results in localizing cortical regions using both histological and functional MRI data.
    • Demonstrated the framework's ability to systematically adapt registration cost functions to specific applications.
    • Showcased improved alignment of cortical function by learning parameters beyond macro-anatomy.

    Conclusions:

    • The proposed framework enables data-driven optimization of image registration for specific neuroimaging applications.
    • This approach enhances the accuracy of localizing functional and structural brain regions.
    • The method offers a systematic way to adapt generic registration techniques, advancing computational neuroscience.