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

Least biased target selection in probabilistic atlas construction.

Hyunjin Park1, Peyton H Bland, Alfred O Hero

  • 1Department of Radiology, University of Michigan, Ann Arbor, MI, USA. hyunjinp@umich.edu

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

This study introduces a novel method for selecting the optimal target image in probabilistic atlas construction. By minimizing bending energy, the approach enhances medical image segmentation and registration accuracy.

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

A deep learning architecture for metabolic pathway prediction.

Bioinformatics (Oxford, England)·2026
Same author

A Practical Approach to Disease Risk Prediction: Focus on High-Risk Patients via Highest-<i>k</i> Loss.

Proceedings. IEEE International Conference on Bioinformatics and Biomedicine·2025
Same author

Evolution of Bipartite and Segmented Viruses from Monopartite Viruses.

Viruses·2023
Same author

Synergistic effect of serum uric acid and body mass index trajectories during middle to late childhood on elevation of liver enzymes in early adolescence: Findings from the Ewha Birth and Growth Study.

PloS one·2023
Same author

The association between urinary cotinine level and metabolic syndrome profiles among adolescents: findings from the Ewha Birth and growth study.

BMC public health·2023
Same author

An Integrated Digital Health Care Platform for Diabetes Management With AI-Based Dietary Management: 48-Week Results From a Randomized Controlled Trial.

Diabetes care·2023

Area of Science:

  • Medical imaging
  • Computational anatomy
  • Image analysis

Background:

  • Probabilistic atlases are crucial for medical image segmentation and registration.
  • A key challenge is selecting an appropriate target image for mapping population data.
  • Existing methods lack a robust strategy for target image selection.

Purpose of the Study:

  • To develop and validate a method for selecting the optimal target image in probabilistic atlas construction.
  • To improve the accuracy and efficiency of medical image analysis workflows.
  • To establish a data-driven approach for defining population mean geometry.

Main Methods:

  • Calculated pairwise registration distances using bending energy.
  • Constructed a distance matrix from all pairwise registrations.

Related Experiment Videos

  • Applied Multidimensional Scaling (MDS) to identify the target image closest to the population's mean geometry.

    • Main Results:

    • Successfully identified a target image that best represents the mean geometry of the dataset.
    • Demonstrated that the chosen target image minimizes geometric distortion.
    • The method provides a quantitative basis for target image selection.

    Conclusions:

    • The proposed bending energy-based method offers an objective approach to selecting target images for probabilistic atlases.
    • This technique can enhance the quality of medical image segmentation and registration.
    • The method contributes to more accurate computational anatomy and population-based image analysis.