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

Deep Learning for Analysis of Bone Marrow Adiposity: Breakthroughs from Recent Large-Scale Analyses in the UK Biobank.

Current osteoporosis reports·2026
Same author

Clinical implications of bone marrow adiposity identified by phenome-wide association and Mendelian randomization in the UK Biobank.

Nature communications·2025
Same author

Author Correction: Deep learning and genome-wide association meta-analyses of bone marrow adiposity in the UK Biobank.

Nature communications·2025
Same author

Deep learning and genome-wide association meta-analyses of bone marrow adiposity in the UK Biobank.

Nature communications·2025
Same author

Automated Echocardiographic Detection of Heart Failure With Preserved Ejection Fraction Using Artificial Intelligence.

JACC. Advances·2024
Same author

A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data.

Computational and structural biotechnology journal·2024

Related Experiment Video

Updated: Dec 1, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

666

Disentangle, Align and Fuse for Multimodal and Semi-Supervised Image Segmentation.

Agisilaos Chartsias, Giorgos Papanastasiou, Chengjia Wang

    IEEE Transactions on Medical Imaging
    |November 6, 2020
    PubMed
    Summary

    This study introduces a novel method for medical image segmentation that leverages information from multiple magnetic resonance (MR) sequences. This approach improves segmentation accuracy, even with limited or no annotations for the target sequence.

    More Related Videos

    Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
    07:13

    Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

    Published on: October 27, 2023

    1.5K
    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    24.9K

    Related Experiment Videos

    Last Updated: Dec 1, 2025

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

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    666
    Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
    07:13

    Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

    Published on: October 27, 2023

    1.5K
    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
    12:08

    From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

    Published on: August 13, 2014

    24.9K

    Area of Science:

    • Medical Imaging
    • Machine Learning
    • Computer Vision

    Background:

    • Magnetic resonance (MR) imaging protocols utilize diverse sequences (modalities) for comprehensive pathology assessment.
    • Current image analysis often treats individual MR modalities in isolation, neglecting shared anatomical information.
    • Anatomical misregistrations and signal intensity variations across modalities hinder effective multi-modality processing.

    Purpose of the Study:

    • To develop a method for improved segmentation accuracy by integrating information from multiple MR modalities.
    • To enable effective multi-modality learning even with limited (semi-supervised) or no (unsupervised) annotations for the target modality.
    • To overcome challenges of anatomical misalignment and signal intensity differences inherent in multi-modal MR data.

    Main Methods:

    • A novel method employing disentangled decomposition into anatomical and imaging factors.
    • Joint processing and fusion of shared anatomical factors for enhanced segmentation masks.
    • Spatial Transformer Network for non-linear alignment to correct image misregistrations.
    • Image reconstruction using the imaging factor to enable semi-supervised learning.
    • Dynamic learning of temporal and slice pairing between input modalities.

    Main Results:

    • Demonstrated improved segmentation accuracy compared to single-input models.
    • Successfully leveraged information from auxiliary modalities for segmentation, even with minimal annotations.
    • Validated the method across diverse applications including cardiac (Late Gadolinium Enhanced, Blood Oxygenation Level Dependent) and abdominal (T2) segmentation.
    • The approach effectively corrects misregistrations and handles signal intensity variations.

    Conclusions:

    • The proposed method effectively integrates multi-modal MR data for improved segmentation.
    • It offers a robust framework for semi-supervised and unsupervised learning in medical image segmentation.
    • The technique shows significant potential for clinical applications requiring accurate organ and pathology segmentation.