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

Atlas stratification.

Daniel J Blezek1, James V Miller

  • 1GE Research, 1 Research Circle, Niskayuna, NY 12309, USA. blezek@research.ge.com

Medical Image Analysis
|September 4, 2007
PubMed
Summary
This summary is machine-generated.

This study introduces atlas stratification, a method to create multiple brain atlases from data subsets. This approach avoids bias from single-reference atlases and better represents multi-modal populations.

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

State of the AI: Post-Deployment Monitoring of Radiology-Focused Internally Developed AI.

Mayo Clinic proceedings. Digital health·2026
Same author

Comparative Evaluation of Deep Learning Models for 3D Segmentation and Volumetry of Vestibular Schwannomas Using Large Heterogeneous Data Sets with External Validation.

AJNR. American journal of neuroradiology·2025
Same author

7T MRI Automated Software Segmentation of the Hippocampus for Epilepsy: Prospective Performance Evaluation.

AJNR. American journal of neuroradiology·2025
Same author

3D printing of an optic pathway model from 7T MRI for education.

3D printing in medicine·2025
Same author

Strategic Considerations for Selecting Artificial Intelligence Solutions for Institutional Integration: A Single-Center Experience.

Mayo Clinic proceedings. Digital health·2025
Same author

Simultaneous liver transplant and sleeve gastrectomy provides durable weight loss, improves metabolic syndrome and reduces allograft steatosis.

Journal of hepatology·2025
Same journal

Embracing intra-class heterogeneity for semi-supervised medical image segmentation: From diversity to precision.

Medical image analysis·2026
Same journal

Real-time patient-specific microwave ablation zone prediction via a unified bioheat solver and MRI-informed perturbation learning.

Medical image analysis·2026
Same journal

Generative morphodynamic forecasting enables robust zero-shot volumetric medical segmentation.

Medical image analysis·2026
Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026
Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026
Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026
See all related articles

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Computational Anatomy

Background:

  • Standard brain atlas construction relies on a single reference individual, potentially introducing bias if this individual deviates from the population mean.
  • Biased atlases can lead to inaccurate inferences in subsequent analyses.
  • Unbiased methods exist, such as using the sample median or iterative convergence to the population mean.

Purpose of the Study:

  • To investigate whether a single brain atlas is sufficient for a given dataset or if multiple atlases, derived from data subsets, are more appropriate.
  • To explore the concept of 'atlas stratification' for representing multi-modal populations.
  • To determine if clinical MRI neurological image datasets exhibit multi-modal characteristics best described by multiple atlases.

Main Methods:

Related Experiment Videos

  • Utilized the mean shift algorithm to identify distinct modes (clusters) within the sample data.
  • Employed multidimensional scaling (MDS) for visualizing the clustering process.
  • Applied these methods to clinical MRI neurological image datasets.

Main Results:

  • Preliminary results suggest the potential for identifying distinct modes within neurological image datasets.
  • Visualization through MDS aids in understanding the data's clustering behavior.
  • The study lays the groundwork for developing multi-atlas strategies.

Conclusions:

  • A single atlas may not adequately represent all populations, especially those with multi-modal characteristics.
  • Atlas stratification offers a promising approach to improve the accuracy and reduce bias in neuroimaging analyses.
  • Further research is warranted to refine multi-atlas construction and validation techniques.