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

Search for New Physics in Jet Multiplicity Patterns of Multilepton Events at sqrt[s]=13 TeV.

Physical review letters·2025

Same author

Safety evaluation of Lactiplantibacillus plantarum N13: genomic, phenotypic, and toxicological assessment for probiotic applications.

Beneficial microbes·2025

Same author

Search for Fractionally Charged Particles in Proton-Proton Collisions at sqrt[s]=13 TeV.

Physical review letters·2025

Same author

Search for Nuclear Modifications of B^{+} Meson Production in p-Pb Collisions at sqrt[s_{NN}]=8.16 TeV.

Physical review letters·2025

Same author

Search for New Resonances Decaying to Pairs of Merged Diphotons in Proton-Proton Collisions at sqrt[s]=13 TeV.

Physical review letters·2025

Same author

Searches for Pair-Produced Multijet Resonances Using Data Scouting in Proton-Proton Collisions at sqrt[s]=13 TeV.

Physical review letters·2024

Search research articles

Related Experiment Video

Updated: Aug 14, 2025

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

[A multi-channel input convolutional neural network for artifact reduction in quantitative susceptibility mapping].

W Si^1,2, Y Feng^1,2

¹School of Biomedical Engineering, Southern Medical University, Guangzhou 510515, China.

Nan Fang Yi Ke Da Xue Xue Bao = Journal of Southern Medical University

|January 18, 2023

Summary

A new deep learning method, MAR-CNN, significantly reduces artifacts in quantitative susceptibility mapping (QSM) reconstruction. This artifact reduction improves the accuracy of magnetic susceptibility results, outperforming existing deep learning and conventional methods.

Keywords:

convolutional neural networks deep learning image reconstruction quantitative susceptibility mapping

More Related Videos

Using Computer Vision Libraries to Streamline Nuclei Quantification

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

Published on: November 13, 2016

Related Experiment Videos

Last Updated: Aug 14, 2025

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Standardized Data Acquisition for Neuromelanin-Sensitive Magnetic Resonance Imaging of the Substantia Nigra

Published on: September 8, 2021

Using Computer Vision Libraries to Streamline Nuclei Quantification

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

A Multimodal Imaging- and Stimulation-based Method of Evaluating Connectivity-related Brain Excitability in Patients with Epilepsy

Published on: November 13, 2016

Area of Science:

Medical imaging
Artificial intelligence
Biophysics

Context:

Quantitative susceptibility mapping (QSM) is crucial for neuroimaging.
Artifacts in QSM limit the accuracy of magnetic susceptibility quantification.
Existing methods struggle with artifacts from large susceptibility differences.

Purpose:

To develop a deep learning-based QSM reconstruction method for artifact reduction.
To improve the accuracy of magnetic susceptibility results using MAR-CNN.
To address limitations of conventional and existing deep learning QSM methods.

Summary:

A multi-channel input convolutional neural network for artifact reduction (MAR-CNN) was developed.
MAR-CNN utilizes a 3D U-Net architecture with separated tissue field components as input channels.
The method was quantitatively compared against TKD, MEDI, iLSQR, and QSMnet.

Impact:

MAR-CNN demonstrated superior performance in reducing artifacts and improving QSM accuracy.
Results showed significant improvements in peak signal-to-noise ratio and normalized root mean squared error.
MAR-CNN effectively reduced shadow artifacts in simulated hemorrhagic lesions.