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

Denoising Diffusion-Weighted Images Using Grouped Iterative Hard Thresholding of Multi-Channel Framelets.

Computational diffusion MRI : MICCAI Workshop·2017
Same author

Robust Construction of Diffusion MRI Atlases with Correction for Inter-Subject Fiber Dispersion.

Computational diffusion MRI : MICCAI Workshop·2017
Same author

Robust Fusion of Diffusion MRI Data for Template Construction.

Scientific reports·2017
Same author

Learning-Based Multimodal Image Registration for Prostate Cancer Radiation Therapy.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2017
Same author

Segmenting hippocampal subfields from 3T MRI with multi-modality images.

Medical image analysis·2017
Same author

Joint Discriminative and Representative Feature Selection for Alzheimer's Disease Diagnosis.

Machine learning in medical imaging. MLMI (Workshop)·2017

Related Experiment Video

Updated: Apr 28, 2026

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
09:06

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

11.0K

Learning to rank atlases for multiple-atlas segmentation.

Gerard Sanroma, Guorong Wu, Yaozong Gao

    IEEE Transactions on Medical Imaging
    |June 4, 2014
    PubMed
    Summary

    This study introduces a novel learning-based method for selecting the best atlases in multiple-atlas segmentation (MAS). This approach improves segmentation accuracy by predicting atlas performance, outperforming traditional similarity metrics.

    More Related Videos

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.6K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    995

    Related Experiment Videos

    Last Updated: Apr 28, 2026

    Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
    09:06

    Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

    Published on: June 9, 2018

    11.0K
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.6K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    995

    Area of Science:

    • Medical Imaging
    • Computer Vision
    • Machine Learning

    Background:

    • Multiple-atlas segmentation (MAS) in medical imaging relies on combining information from several reference images (atlases) to segment a target image.
    • Current MAS methods often use image similarity for atlas selection, which doesn't always correlate with final segmentation accuracy.
    • The critical problem of selecting the optimal set of atlases for MAS remains largely unexplored.

    Purpose of the Study:

    • To develop a learning-based atlas selection method for multiple-atlas segmentation (MAS).
    • To improve segmentation accuracy by selecting atlases based on their predicted labeling performance.
    • To provide a generalizable atlas selection approach compatible with existing MAS techniques.

    Main Methods:

    • Proposed a learning-based framework to predict the labeling performance of atlas-target image pairs.
    • Learned the relationship between image appearance and segmentation accuracy (Dice ratio).
    • Integrated the proposed atlas selection method with three widely used MAS techniques.

    Main Results:

    • The learning-based atlas selection method significantly improved segmentation performance across multiple datasets (ADNI, SATA, IXI, LONI LPBA40).
    • Outperformed traditional image-similarity-based atlas selection methods.
    • Demonstrated superior results compared to other learning-based atlas selection approaches.

    Conclusions:

    • The proposed learning-based atlas selection method effectively enhances MAS performance.
    • Predicting atlas labeling accuracy is a more reliable criterion than image similarity for atlas selection.
    • This method offers a general and effective solution for optimizing atlas selection in medical image segmentation.