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

Leveraging Machine Learning to Advance Alcohol Research: Current Applications, Challenges, and Opportunities.

Alcohol research : current reviews·2026
Same author

Using deep learning to identify brain networks mediating cognitive and motor impairments in alcohol use disorder.

Translational psychiatry·2026
Same author

Developing ICU Clinical Behavioral Atlas Using Ambient Intelligence and Computer Vision.

NEJM AI·2026
Same author

Evaluation of Image-Level Harmonization Methods for Multi-Center MR Neuroimaging.

Journal of magnetic resonance imaging : JMRI·2026
Same author

Both Infarcted and Noninfarcted Brain Regions Contribute to Deep Learning-Based MRI Prediction of Acute Stroke Outcome.

AJNR. American journal of neuroradiology·2025
Same author

The Current Status of AI-accelerated MRI Techniques in Clinical Use.

Radiology·2025
Same journal

Enhancing Alzheimer's Diagnosis: Leveraging Anatomical Landmarks in Graph Convolutional Neural Networks on Tetrahedral Meshes.

Information processing in medical imaging : proceedings of the ... conference·2026
Same journal

Cycle-Consistent Zero-Shot Through-Plane Super-Resolution for Anisotropic Head MRI.

Information processing in medical imaging : proceedings of the ... conference·2026
Same journal

Brightness-Invariant Tracking Estimation in Tagged MRI.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

Multi-View and Multi-Scale Alignment for Contrastive Language-Image Pre-training in Mammography.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

Using Multiple Instance Learning to Build Multimodal Representations.

Information processing in medical imaging : proceedings of the ... conference·2025
Same journal

mSPD-NN: A Geometrically Aware Neural Framework for Biomarker Discovery from Functional Connectomics Manifolds.

Information processing in medical imaging : proceedings of the ... conference·2024
See all related articles

Related Experiment Video

Updated: Oct 3, 2025

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.8K

Representation Disentanglement for Multi-modal Brain MRI Analysis.

Jiahong Ouyang1, Ehsan Adeli1, Kilian M Pohl1,2

  • 1Stanford University, Stanford, CA.

Information Processing in Medical Imaging : Proceedings of the ... Conference
|February 17, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a novel margin loss for multi-modal magnetic resonance imaging (MRI) analysis, improving the disentanglement of anatomical and appearance information for better neuroimaging insights.

More Related Videos

Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

17.0K
Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

26.5K

Related Experiment Videos

Last Updated: Oct 3, 2025

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging
11:28

Concurrent EEG and Functional MRI Recording and Integration Analysis for Dynamic Cortical Activity Imaging

Published on: June 30, 2018

11.8K
Basics of Multivariate Analysis in Neuroimaging Data
06:35

Basics of Multivariate Analysis in Neuroimaging Data

Published on: July 24, 2010

17.0K
Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging
17:06

Co-analysis of Brain Structure and Function using fMRI and Diffusion-weighted Imaging

Published on: November 8, 2012

26.5K

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Deep Learning

Background:

  • Multi-modal magnetic resonance imaging (MRI) leverages complementary information from different sequences for comprehensive brain analysis.
  • Current deep learning approaches aim to disentangle anatomical (shape) and modality (appearance) information, but may not achieve true representation disentanglement.
  • Explicitly separating shape and appearance is crucial for robust multi-modal neuroimaging studies.

Purpose of the Study:

  • To challenge existing multi-modal deep learning strategies that fail to effectively disentangle anatomical and appearance information.
  • To propose a novel method that achieves superior disentangled representations in multi-modal neuroimaging.
  • To demonstrate the utility of disentangled anatomical representations in downstream tasks like zero-dose PET reconstruction and brain tumor segmentation.

Main Methods:

  • Proposed a margin loss to regularize the relationship similarity between representations across subjects and modalities.
  • Developed a conditional convolution for a single model to encode images from all modalities, ensuring robust training.
  • Introduced a fusion function to combine disentangled anatomical representations into modality-invariant features.

Main Results:

  • The proposed method demonstrated superior disentangled representations compared to existing strategies on three multi-modal neuroimaging datasets.
  • The fused anatomical representation showed significant potential in downstream tasks.
  • Achieved promising results in zero-dose Positron Emission Tomography (PET) reconstruction and brain tumor segmentation.

Conclusions:

  • The novel margin loss effectively addresses the limitations of current methods in achieving representation disentanglement for multi-modal MRI.
  • The proposed approach yields modality-invariant anatomical features beneficial for various neuroimaging applications.
  • This work advances multi-modal neuroimaging analysis by providing a more robust and effective method for feature disentanglement and fusion.