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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Diffusing caveolin-1 scaffolds regulate mechanosignalling.

Nature cell biology·2026
Same author

Rural Clinicians Efforts to Maintain Relationship-Centered Care Amidst Conflicting Tensions with Inherited Opioid Prescribing Practices.

Journal of general internal medicine·2026
Same author

HDCluster: High-Degree Graph Clustering for Robust Analysis of Single Molecule Localization Microscopy.

bioRxiv : the preprint server for biology·2025
Same author

nERdy: network analysis of endoplasmic reticulum dynamics.

Communications biology·2025
Same author

Physician-in-the-Loop Active Learning in Radiology Artificial Intelligence Workflows: Opportunities, Challenges, and Future Directions.

AJR. American journal of roentgenology·2025
Same author

BiasPruner: Mitigating bias transfer in continual learning for fair medical image analysis.

Medical image analysis·2025

Related Experiment Video

Updated: Apr 29, 2026

Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

6.6K

The isometric log-ratio transform for probabilistic multi-label anatomical shape representation.

Shawn Andrews, Neda Changizi, Ghassan Hamarneh

    IEEE Transactions on Medical Imaging
    |May 27, 2014
    PubMed
    Summary

    The isometric log-ratio (ILR) transform better captures anatomical shape variability in medical image segmentation than the LogOdds transform. This is crucial for analyzing probabilistic labels with complex boundaries.

    More Related Videos

    A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
    08:12

    A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

    Published on: March 1, 2022

    2.1K
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    6.3K

    Related Experiment Videos

    Last Updated: Apr 29, 2026

    Three-Dimensional Shape Modeling and Analysis of Brain Structures
    05:33

    Three-Dimensional Shape Modeling and Analysis of Brain Structures

    Published on: November 14, 2019

    6.6K
    A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
    08:12

    A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

    Published on: March 1, 2022

    2.1K
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    6.3K

    Area of Science:

    • Medical Image Analysis
    • Computational Anatomy
    • Geometric Deep Learning

    Background:

    • Probabilistic labels are essential for handling uncertainty in medical image segmentation.
    • Standard statistical methods assume unconstrained vector spaces, which conflicts with the simplex geometry of probabilistic labels.
    • Existing transformations like LogOdds can sacrifice relative uncertainty information due to asymmetry.

    Purpose of the Study:

    • To explore the interpretation of Aitchison geometry for probabilistic labels in medical image segmentation.
    • To compare the effectiveness of the isometric log-ratio (ILR) transform versus the LogOdds transform for statistical analysis of probabilistic labels.
    • To demonstrate how ILR transformation better preserves shape variability, especially with complex boundaries.

    Main Methods:

    • Applied statistical techniques to probabilistic labels in medical image segmentation.
    • Utilized the isometric log-ratio (ILR) transform, a symmetrized version of the LogOdds transform, mapping simplex geometry to Euclidean space.
    • Compared statistical analysis results of ILR-transformed data against LogOdds-transformed data.

    Main Results:

    • The LogOdds transform can skew results due to its asymmetry.
    • The ILR transform provides a more symmetric and accurate representation of probabilistic label data.
    • Statistical analysis of ILR-transformed data effectively captures anatomical shape variability, particularly in cases with multiple shared foreground boundaries.

    Conclusions:

    • The ILR transform is a superior method for statistical analysis of probabilistic labels in medical image segmentation compared to the LogOdds transform.
    • ILR transformation preserves crucial relative uncertainty information, leading to more robust shape modeling.
    • This approach enhances the analysis of complex anatomical structures with shared boundaries in medical imaging.