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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

8.1K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
8.1K
Imaging Studies III: Computed Tomography01:27

Imaging Studies III: Computed Tomography

89
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
89

You might also read

Related Articles

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

Sort by
Same author

Lecanemab in practice: AI-derived MRI predictors of benefit and Amyloid Related Imaging Abnormalities (ARIA).

Alzheimer's research & therapy·2026
Same author

Spinal cord reserve is associated with multi-dimensional clinical resilience in multiple sclerosis.

Journal of neurology·2026
Same author

The Ischemic Stroke Lesion Segmentation Challenge (ISLES)'24 Dataset: A Multimodal Stroke Imaging Dataset with Hyperacute CT, Acute Postinterventional MRI, and 3-month Clinical Outcomes.

Radiology. Artificial intelligence·2026
Same author

Cross-sectional brain volumetric measures and disability outcomes in relapsing-remitting multiple sclerosis.

Journal of neurology·2026
Same author

Screening for Alzheimer's disease in the community using an AI-driven screening platform: design of the PREDICTOM study.

The journal of prevention of Alzheimer's disease·2026
Same author

Hierarchical uncertainty estimation for learning-based registration in neuroimaging.

... International Conference on Learning Representations·2026

Related Experiment Video

Updated: Oct 20, 2025

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

1.4K

A Contrast Augmentation Approach to Improve Multi-Scanner Generalization in MRI.

Maria Ines Meyer1,2, Ezequiel de la Rosa2,3, Nuno Pedrosa de Barros2

  • 1Department of Health Technology, Technical University of Denmark, Lyngby, Denmark.

Frontiers in Neuroscience
|September 17, 2021
PubMed
Summary

Gaussian Mixture Models Data Augmentation (GMM-DA) enhances Deep Learning (DL) model generalization for brain MRI segmentation. This method improves model robustness across different scanners and increases prediction consistency for multi-center clinical data.

Keywords:
data augmentationgaussian mixture modelsmagnetic resonance imagingmulti-scannersegmentation

More Related Videos

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

742
Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.6K

Related Experiment Videos

Last Updated: Oct 20, 2025

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

1.4K
Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function
02:09

Multi-modal Pulmonary Imaging: Using Complementary Information from CT and Hyperpolarized 129Xe MRI to Evaluate Lung Structure-Function

Published on: April 12, 2024

742
Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues
07:34

Perceptual and Category Processing of the Uncanny Valley Hypothesis' Dimension of Human Likeness: Some Methodological Issues

Published on: June 3, 2013

17.6K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • Deep Learning (DL) models for brain Magnetic Resonance Imaging (MRI) are sensitive to data variability from different acquisition protocols and scanners.
  • Most available brain MRI datasets are homogeneous, hindering the clinical translation of DL techniques due to poor generalization to multi-center data.
  • Robust methods are essential for reliable DL application in clinical practice, addressing variations in MRI data.

Purpose of the Study:

  • To introduce a novel data augmentation technique, Gaussian Mixture Models Data Augmentation (GMM-DA), to increase intensity and contrast variability in brain MRI datasets.
  • To improve the generalization capability of DL models for brain structure segmentation across diverse scanners and centers.
  • To enhance the robustness and consistency of DL models in clinical settings.

Main Methods:

  • Proposed GMM-DA to augment training datasets, simulating real-world clinical data variability while preserving anatomical information.
  • Trained a U-Net model for brain structure segmentation with and without GMM-DA on single- and multi-scanner datasets.
  • Evaluated model performance on generalization to unseen scanners, test-retest consistency on same-patient images, and impact of bias fields.

Main Results:

  • GMM-DA significantly improved the generalization capability of the DL model to scanners not included in the training data, even with multi-scanner training sets.
  • The consistency of segmentation predictions for same-patient images was enhanced, both for same-scanner and different-scanner test-retest scenarios.
  • The GMM-DA approach demonstrated improved robustness against bias field influences.

Conclusions:

  • GMM-DA is an effective data augmentation strategy for improving the generalization and robustness of DL models in brain MRI segmentation.
  • The proposed method enhances the transferability of DL models to diverse clinical environments with multi-center and multi-scanner data.
  • GMM-DA contributes to more reliable and consistent AI-driven medical image analysis in clinical practice.