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

Submillimeter postmortem and in vivo diffusion and susceptibility magnetic resonance imaging to characterize cortical micro- and meso-structures.

Research square·2026

Same author

A Multimodal Strategy for Enhancing Minimally Invasive Ablation of Lung Tumor.

Annals of biomedical engineering·2026

Same author

CSF turnover dysfunction: a hidden early biomarker in iRBD?

NPJ Parkinson's disease·2026

Same author

The Caspase-1/GSDMD/PXN/VCAM-1 Cascade Mediates Cerebral Ischemia-Reperfusion Injury.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026

Same author

CAND1 drives intestinal ischemia/reperfusion injury via SCF<sup>FBXO6</sup>-PKM2-mediated mitochondrial fission and apoptosis.

Free radical biology & medicine·2026

Same author

Automatic and Optimal Trajectory Planning for Laser Interstitial Thermal Therapy in Malignant Glioma.

IEEE journal of biomedical and health informatics·2026

Search research articles

Related Experiment Video

Updated: Aug 8, 2025

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

Diffusion MRI data analysis assisted by deep learning synthesized anatomical images (DeepAnat).

Ziyu Li¹, Qiuyun Fan², Berkin Bilgic²

¹Department of Biomedical Engineering, Tsinghua University, Beijing, China; Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom.

Medical Image Analysis

|March 3, 2023

Summary

This study introduces DeepAnat, a novel method using convolutional neural networks to synthesize T1-weighted anatomical MRI images from diffusion MRI data, improving brain segmentation and co-registration for neuroimaging analysis.

Keywords:

Brain segmentation Convolutional neural network Cortical surface reconstruction Diffusion tractography Generative adversarial network Image co-registration

More Related Videos

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

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

Published on: November 8, 2012

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury

Published on: August 14, 2019

Related Experiment Videos

Last Updated: Aug 8, 2025

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Diffusion Tensor Magnetic Resonance Imaging in the Analysis of Neurodegenerative Diseases

Published on: July 28, 2013

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

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

Published on: November 8, 2012

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury

Advanced Diffusion Imaging in The Hippocampus of Rats with Mild Traumatic Brain Injury

Published on: August 14, 2019

Area of Science:

Neuroimaging
Medical Image Analysis
Artificial Intelligence in Medicine

Background:

Diffusion MRI is crucial for mapping brain microstructure and connections.
Analysis often requires T1-weighted (T1w) MRI data for segmentation, which can be unavailable or misaligned.
Susceptibility-induced geometric distortion in diffusion data complicates co-registration with T1w images.

Purpose of the Study:

To develop a method (DeepAnat) to synthesize high-quality T1w anatomical images directly from diffusion MRI data.
To utilize synthesized T1w images for improved brain segmentation and co-registration in diffusion MRI analysis.
To assess the performance and generalizability of the proposed method across different datasets and hardware.

Main Methods:

Convolutional neural networks (CNNs), including U-Net and Generative Adversarial Networks (GANs), were employed to synthesize T1w images from diffusion MRI.
Brain segmentation and co-registration tasks were performed using the synthesized T1w images.
Quantitative evaluations were conducted on datasets from the Human Connectome Project (HCP), UK Biobank, and Massachusetts General Hospital Connectome Diffusion Microstructure Dataset (MGH CDMD).

Main Results:

Synthesized T1w images demonstrated high similarity to native T1w data, yielding comparable results for segmentation and diffusion analysis.
U-Net architecture showed slightly higher brain segmentation accuracy than the GAN.
The method proved generalizable across different datasets and hardware, with significant improvements in co-registration accuracy when assisting alignment of undistorted diffusion and T1w images.

Conclusions:

DeepAnat offers a practical and beneficial solution for overcoming challenges in diffusion MRI analysis caused by missing or misaligned T1w data.
The synthesized T1w images facilitate accurate brain segmentation and enhance the co-registration process.
DeepAnat shows strong potential for broad application in neuroscientific research and clinical practice.