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

Recycling lithium-ion batteries to regenerate graphite, silicon, and Si/C composite anodes: Review of advances between 2015 and 2025.

Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA·2026

Same author

Combined, Back-to-Back Endovascular Thrombectomy for Extensive Deep Vein Thrombosis: A Case Report.

Journal of the Society for Cardiovascular Angiography & Interventions·2026

Same author

Early recognition and multidisciplinary care in a pediatric patient with acute infectious purpura fulminans due to MRSA: A rare case report.

IDCases·2026

Same author

Global malnutrition crisis: assessing the fallout of US Agency for International Development (USAID) withdrawal and pathways forward.

Journal of epidemiology and community health·2026

Same author

A review of deep learning techniques in Alzheimer's disease with emphasis on data tools and transfer learning.

Neuroscience·2025

Same author

Comment on "The usefulness of previous urine culture and antibiogram results".

Irish journal of medical science·2025

Search research articles

Related Experiment Video

Updated: Jun 7, 2025

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

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

Published on: October 27, 2023

GraFMRI: A graph-based fusion framework for robust multi-modal MRI reconstruction.

Shahzad Ahmed¹, Feng Jinchao¹, Javed Ferzund²

¹Beijing Key Laboratory of Computational Intelligence and Intelligent System, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.

Magnetic Resonance Imaging

|November 19, 2024

Summary

GraFMRI, a novel framework using Graph Neural Networks (GNNs), enhances multi-modal MRI reconstruction from undersampled data. It significantly improves image quality by reducing noise and artifacts, boosting diagnostic accuracy.

Keywords:

Generative adversarial network Graph neural network MRI reconstruction Medical imaging Zero-shot learning

More Related Videos

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Published on: April 9, 2019

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Related Experiment Videos

Last Updated: Jun 7, 2025

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

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

Published on: October 27, 2023

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Published on: April 9, 2019

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Area of Science:

Medical Imaging
Artificial Intelligence
Graph Neural Networks

Background:

Undersampled k-space data in MRI reconstruction leads to noise and loss of detail.
Existing methods struggle with noise amplification and artifact reduction.
Multi-modal MRI data (T1, T2, PD) offers rich diagnostic information but requires sophisticated fusion techniques.

Purpose of the Study:

Introduce GraFMRI, a novel framework for high-quality MRI reconstruction from undersampled k-space data.
Leverage Graph Neural Networks (GNNs) to represent and fuse multi-modal MRI data.
Address challenges of noise, artifacts, and inter-modality dependency in reconstruction.

Main Methods:

Transforming multi-modal MRI data into a graph-based representation using GNNs.
Integrating Graph-Based Non-Local Means (NLM) Filtering for noise suppression.
Employing Adversarial Training for artifact reduction and a dynamic attention mechanism for focused reconstruction.

Main Results:

GraFMRI demonstrated superior performance compared to traditional and self-supervised methods.
Achieved significant improvements in multi-modal fusion and information preservation.
Reported higher Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) scores due to effective noise and artifact control.

Conclusions:

GraFMRI offers a scalable and robust solution for multi-modal MRI reconstruction.
Effectively mitigates noise and artifacts, enhancing diagnostic accuracy.
Adaptable to various clinical applications, improving image quality and reliability.