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

Search research articles

Related Experiment Videos

EPRI sparse reconstruction method based on deep learning.

Congcong Du¹, Zhiwei Qiao¹

¹School of Computer and Information Technology, Shanxi University, Taiyuan, Shanxi 030006, China.

Magnetic Resonance Imaging

|December 9, 2022

Summary

This summary is machine-generated.

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

SUMO-specific protease 2 governs cardiac function through the regulation of β-catenin SUMOylation.

International journal of biological macromolecules·2026

Same author

Multigene germline testing for epithelial ovarian cancer in China.

Cancer·2026

Same author

Preventive effect of PC-SOD on oxaliplatin-induced peripheral neuropathy in rats.

BMC neuroscience·2026

Same author

Room-Temperature Transformation of Bulk Materials into Single Atoms for Advancing CO<sub>2</sub> Electroreduction Efficiency.

ACS nano·2026

Same author

Polymeric particle-based antigen delivery system: From immunological engineering to clinical translation.

International journal of pharmaceutics: X·2026

Same author

Assessing sustainability effects of tobacco use and control in global supply chains.

Nature communications·2025

Same journal

Incremental diagnostic value of microstructural time-dependent diffusion MRI in differentiating PCNSL from glioblastoma over conventional MRI.

Magnetic resonance imaging·2026

Same journal

Enhanced motion compensation for free-breathing dynamic contrast-enhanced MRI with GROG-facilitated bunch phase encoding and Golden angle radial sampling.

Magnetic resonance imaging·2026

Same journal

The allegory of the cave: 10 years of AI shadows in radiology.

Magnetic resonance imaging·2026

Same journal

Conversion of 3 T liver, spleen, pancreas, and kidney R2* measurements to 1.5 T R2* equivalents: Validation of a theoretical framework.

Magnetic resonance imaging·2026

Same journal

Cine-derived mitral annular relaxation velocity for detection of preclinical left ventricular diastolic dysfunction.

Magnetic resonance imaging·2026

Same journal

Bone marrow fat fraction and R2* in sickle cell disease: Associations with hemolysis, iron metabolism, and disease severity.

Magnetic resonance imaging·2026

See all related articles

Electron paramagnetic resonance imaging (EPRI) faces long scan times. A new deep learning network, FRD-Net, effectively reduces artifacts in sparse-reconstructed EPRI images, improving accuracy.

Area of Science:

Medical imaging
Biomedical engineering
Radiology

Background:

Electron paramagnetic resonance imaging (EPRI) is crucial for tumor oxygenation assessment.
Current EPRI methods suffer from long scanning times, limiting clinical utility.
Sparse reconstruction accelerates EPRI but introduces artifacts, hindering image analysis.

Purpose of the Study:

To develop an advanced deep learning model for artifact suppression in sparse-reconstructed EPRI images.
To improve the accuracy and quality of EPRI images obtained through sparse reconstruction.

Main Methods:

A novel deep convolutional network, FRD-Net, incorporating feature pyramid attention, residual connections, and dense connections was developed.
The network was trained using EPRI images with artifacts as input and high-quality, densely reconstructed images as output labels.

Keywords:

Convolutional neural network Deep learning EPRI Sparse reconstruction Streak artifacts

Related Experiment Videos

Perceptual loss was integrated into the training process to enhance image quality.

Main Results:

FRD-Net effectively suppressed streak artifacts in EPRI images reconstructed from sparse-view projections.
Experimental results demonstrated superior performance of FRD-Net compared to three existing deep network models.
The proposed method significantly improved sparse reconstruction accuracy in real EPRI data.

Conclusions:

FRD-Net offers a powerful solution for artifact reduction in sparse-reconstructed EPRI.
This advancement has the potential to accelerate EPRI acquisition and improve diagnostic capabilities for tumor oxygenation.
The developed deep learning approach enhances the clinical applicability of EPRI by overcoming reconstruction limitations.