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

Optimum template selection for atlas-based segmentation.

Minjie Wu1, Caterina Rosano, Pilar Lopez-Garcia

  • 1Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA 15213, USA.

Neuroimage
|December 26, 2006
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

Distinct Attentional Control Profiles during Language Comprehension in Major Mental Health Disorders.

Biological psychiatry. Cognitive neuroscience and neuroimaging·2026
Same author

Exploring the Relationship Between Inflammatory Biomarkers and Negative Symptoms Subtypes in Individuals at Ultra-High Risk for Psychosis.

Early intervention in psychiatry·2026
Same author

Bipolar Disorder Psychosis Risk Predicts Cue Discrimination on the AX-Continuous Performance Task Paradigm.

Bipolar disorders·2026
Same author

Impacted and preserved sub-domains of cognitive control in schizophrenia.

Neuropsychologia·2026
Same author

The Biological Psychiatry Family of Journals Is Rewarding Its Reviewers.

Biological psychiatry·2026
Same author

Prior Trial Effects on Working Memory in Schizophrenia, Bipolar Disorder, and Healthy Control Individuals.

JAMA psychiatry·2026

Selecting the best brain atlas template improves MR brain image segmentation accuracy. This novel method enhances region classification and volume estimation, approaching manual tracing reliability for automated analysis.

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Computational Neuroscience

Background:

  • Atlas-based segmentation of MR brain images commonly uses a single template, which struggles with individual anatomical variations.
  • Existing research often focuses on creating population-specific templates rather than optimizing atlas selection for individual subjects.

Purpose of the Study:

  • To introduce and evaluate a novel template selection method for atlas-based segmentation of MR brain images.
  • To improve the accuracy and reliability of automated brain region identification by using a family of templates.

Main Methods:

  • Developed a template selection method that automatically identifies the best-fitting template for each subject and region based on normalized mutual information and registration accuracy.
  • Quantified segmentation performance using overlap ratios (ORs) and intraclass correlation coefficients (ICCs) by comparing automated results with manual tracings.

Related Experiment Videos

  • Tested the method on two groups of brain images, analyzing multiple regions of interest (ROIs) including the right anterior cingulate cortex (ACC) and subcortical structures.

    • Main Results:

    • The template selection method significantly outperformed the single template method, achieving higher overlap ratios across all 13 analyzed ROIs.
    • Improved accuracy was observed for the right anterior cingulate cortex (p=0.0024) and right amygdala (p<0.013), among other regions.
    • The template selection approach yielded more reliable volume estimates, indicated by increased intraclass correlation coefficients (ICCs).

    Conclusions:

    • Automated atlas-based segmentation using an optimal template selection strategy significantly enhances accuracy and reliability compared to single-template methods.
    • This approach approaches the accuracy of manual tracing, validating its utility for automated brain imaging analyses.
    • The method effectively addresses the challenge of individual anatomical variations in brain structures for improved segmentation outcomes.