Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Magnetic Resonance Imaging

Magnetic Resonance Imaging

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...

You might also read

Related Articles

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

Sort by

Same author

Optical Coherence Tomography Harmonization with Anatomy-Guided Latent Metric Schrödinger Bridges.

Advances in neural information processing systems·2026

Same authorSame journal

Optical Coherence Tomography Harmonization via Dual Diffusion Implicit Bridges.

Proceedings of SPIE--the International Society for Optical Engineering·2026

Same author

Unsupervised OCT Image Interpolation Using Deformable Registration and generative models.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026

Same author

An Unsupervised Approach for Artifact Severity Scoring in Multi-Contrast MR Images.

Proceedings of machine learning research·2026

Same author

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026

Same author

Metabolomic Signatures of Brain Atrophy and Ibudilast Response in Progressive Multiple Sclerosis.

medRxiv : the preprint server for health sciences·2026

Search research articles

Related Experiment Video

Updated: Jun 5, 2025

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

A deep generative prior for high-resolution isotropic MR head slices.

Samuel W Remedios^1,2, Blake E Dewey³, Aaron Carass⁴

¹Department of Computer Science, Johns Hopkins University, Baltimore, MD 21286, USA.

Proceedings of Spie--The International Society for Optical Engineering

|December 4, 2024

Summary

Researchers developed a StyleGAN3-T model to generate high-resolution 2D magnetic resonance (MR) head slices. This open-source generative model, trained on T1- and T2-weighted contrasts, aids diverse medical image analysis tasks.

Keywords:

GAN MRI StyleGAN3 T1 T2 brain generative prior high-resolution isotropic

More Related Videos

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis

Published on: July 19, 2019

Related Experiment Videos

Last Updated: Jun 5, 2025

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Author Spotlight: Optimized Lung MRI Protocol with Computationally Efficient Reconstruction Methods

Published on: September 6, 2024

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis

Comprehensive Autopsy Program for Individuals with Multiple Sclerosis

Published on: July 19, 2019

Area of Science:

Medical Imaging
Artificial Intelligence
Deep Learning

Background:

Generative models are crucial for medical image analysis.
A need exists for generators trained on diverse, high-resolution 2D MR head slices across multiple orientations and contrasts.
Existing deep learning methods often focus on 2D images, necessitating comprehensive 2D data generators.

Purpose of the Study:

To train a StyleGAN3-T model for generating high-resolution 2D head MR slices.
To provide a versatile tool for various downstream medical image analysis applications.
To make the trained model weights publicly available.

Main Methods:

Trained a StyleGAN3-T model using public data of head MR slices.
Focused on T1- and T2-weighted contrasts.
Utilized 1mm isotropic volumes across three standard radiological views, without skull-stripping.
Performed qualitative sampling, latent code interpolation, and style mixing for network analysis.

Main Results:

The StyleGAN3-T model successfully generated high-quality, high-resolution 2D head MR slices.
Network analyses confirmed the model's expressivity and generative capabilities.
The generated images are suitable for various downstream applications.

Conclusions:

The developed StyleGAN3-T model provides a powerful generative prior for 2D head MR imaging.
Open-sourcing the model weights facilitates broader research and application in medical image analysis.
This work addresses the need for comprehensive, high-resolution 2D MR slice generation.