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

Expectation maximization strategies for multi-atlas multi-label segmentation.

Torsten Rohlfing1, Daniel B Russakoff, Calvin R Maurer

  • 1Image Guidance Laboratories, Department of Neurosurgery, Stanford University, Stanford, CA, USA. rohlfing@stanford.edu

Information Processing in Medical Imaging : Proceedings of the ... Conference
|September 4, 2004
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

Deep Learning-Based Segmentation of Geographic Atrophy: A Multi-Center, Multi-Device Validation in a Real-World Clinical Cohort.

Diagnostics (Basel, Switzerland)·2025
Same author

Deep Learning Model for Automated Classification of Macular Neovascularization Subtypes in AMD.

Investigative ophthalmology & visual science·2025
Same author

Deep learning model for automatic detection of different types of microaneurysms in diabetic retinopathy.

Eye (London, England)·2025
Same author

Machine Learning Quantification of Fluid Volume in Eyes With Retinal Vein Occlusion Treated With Aflibercept: The REVOLT Study.

Journal of vitreoretinal diseases·2025
Same author

Topographical Quantification of Retinal Fluid in Type 3 MNV and Associations With Short-Term Visual Outcomes.

American journal of ophthalmology·2024
Same author

Deep-learning based automated quantification of critical optical coherence tomography features in neovascular age-related macular degeneration.

Eye (London, England)·2023

Combining multiple segmentations using two novel expectation maximization (EM) algorithms improves accuracy in atlas-based image segmentation. These methods outperform simple label averaging for enhanced ground truth estimation.

Area of Science:

  • Pattern Recognition
  • Medical Image Analysis
  • Computational Biology

Background:

  • Combining decisions from independent classifiers enhances accuracy.
  • Expectation maximization (EM) algorithms are used for ground truth estimation with multiple experts.
  • Atlas-based image segmentation benefits from combining multiple segmentation results.

Purpose of the Study:

  • Introduce two novel extensions to the Warfield algorithm for combining multiple segmentations.
  • Evaluate the effectiveness of these extensions in atlas-based image segmentation.
  • Compare the proposed methods against simple label averaging.

Main Methods:

  • Developed two extensions to an expectation maximization (EM) algorithm for integrating multiple segmentations.

Related Experiment Videos

  • The first method involves repeated application of the Warfield algorithm with integration.
  • The second method is a multi-label extension of the Warfield algorithm.

    • Main Results:

    • Both proposed EM-based methods successfully integrate multiple segmentations.
    • The integrated segmentations are closer to the unknown ground truth than individual segmentations.
    • The two EM methods demonstrated higher accuracy than simple label averaging in validation studies.

    Conclusions:

    • The proposed expectation maximization (EM) algorithm extensions effectively combine multiple segmentations for improved accuracy.
    • These methods offer a superior approach to ground truth estimation in atlas-based image segmentation compared to label averaging.
    • Classifier combination strategies are crucial for advancing atlas-based segmentation accuracy.