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

You might also read

Related Articles

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

Sort by

Same author

ROS-Responsive Nanobubbles for Dual-Enhanced Ultrasound and Magnetic Resonance Imaging of Tumor Oxidative Stress.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026

Same author

Physics-Guided Neural Network for Quantitative Parameter Mapping Using Balanced Steady State Free Precession MRI.

Magnetic resonance in medicine·2026

Same author

Posture-dependent cerebrospinal fluid flow measurement in the optic nerve subarachnoid space using multi-delay 2D interslice saturation MRI.

Brain research bulletin·2025

Same author

Towards fair decentralized benchmarking of healthcare AI algorithms with the Federated Tumor Segmentation (FeTS) challenge.

Nature communications·2025

Same author

Long-term physical exercise facilitates putative glymphatic and meningeal lymphatic vessel flow in humans.

Nature communications·2025

Same author

Simultaneous measurement of cerebral blood flow and cerebrospinal fluid flow using pseudo-continuous arterial spin labeling.

NeuroImage·2025

Search research articles

Related Experiment Video

Updated: Jul 11, 2025

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

SIMPLEX: Multiple phase-cycled bSSFP quantitative magnetization transfer imaging with physic-guided simulation

Huan Minh Luu¹, Sung-Hong Park¹

¹Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology (KAIST), Rm 1002, CMS (E16) Building, 291 Daehak-ro, Yuseong-gu, Daejeon 34141, South Korea.

|November 11, 2023

Summary

SIMPLEX, a novel deep learning method, improves quantitative magnetization transfer (qMT) imaging by accurately extracting qMT parameters from bSSFP data without extra scans. This enhances clinical applicability and reduces processing time.

Keywords:

Artificial neural network Deep learning Magnetization transfer Quantitative imaging SIMPLEX bSSFP

More Related Videos

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

Brain State-dependent Brain Stimulation with Real-time Electroencephalography-Triggered Transcranial Magnetic Stimulation

Brain State-dependent Brain Stimulation with Real-time Electroencephalography-Triggered Transcranial Magnetic Stimulation

Published on: August 20, 2019

Related Experiment Videos

Last Updated: Jul 11, 2025

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Targeting Neuronal Fiber Tracts for Deep Brain Stimulation Therapy Using Interactive, Patient-Specific Models

Published on: August 12, 2018

Brain State-dependent Brain Stimulation with Real-time Electroencephalography-Triggered Transcranial Magnetic Stimulation

Brain State-dependent Brain Stimulation with Real-time Electroencephalography-Triggered Transcranial Magnetic Stimulation

Published on: August 20, 2019

Area of Science:

Medical Imaging
Magnetic Resonance Imaging
Computational Neuroscience

Background:

Quantitative magnetization transfer (qMT) imaging typically requires additional quantitative maps (e.g., T1) for accurate data fitting.
A recent method using multi-phase-cycled bSSFP simplified qMT protocols but yielded suboptimal parameter quantification.
Suboptimal quantification limits the clinical utility of advanced qMT imaging techniques.

Purpose of the Study:

To enhance the accuracy and robustness of qMT parameter quantification from multi-phase-cycled bSSFP data.
To introduce SIMPLEX (SIMulation-based Physics-guided Learning of neural network for qMT parameters EXtraction), a novel deep learning approach for qMT analysis.
To enable simultaneous, high-resolution mapping of qMT parameters, T1, T2, and ΔB0 without additional acquisitions.

Main Methods:

Developed SIMPLEX, a neural network trained exclusively on simulated MR data generated from the signal model.
Leveraged physics-guided learning and simulation data to avoid expensive ground truth data curation.
Applied the trained network directly to in-vivo data without further training or fine-tuning.

Main Results:

SIMPLEX demonstrated a significant reduction in fitting mean squared error compared to existing least-squares fitting methods on simulation data.
The network performed effectively on unseen in-vivo data, validating its generalization capabilities.
SIMPLEX consistently improved qMT parameter quantification quality and exhibited enhanced robustness to noise over the prior technique.

Conclusions:

SIMPLEX offers a more reliable and efficient method for qMT parameter quantification using multi-phase-cycled bSSFP.
The approach facilitates the simultaneous acquisition of multiple quantitative maps, including qMT parameters, T1, T2, and ΔB0.
SIMPLEX has the potential to expedite the routine clinical application of high-resolution 3D qMT imaging.