Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Aliasing01:18

Aliasing

305
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
305
Upsampling01:22

Upsampling

370
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
370

You might also read

Related Articles

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

Sort by
Same author

Effect of Medicaid coverage of tobacco-dependence treatments on smoking cessation.

International journal of environmental research and public health·2010
Same author

Cytokine and autoantibody patterns in acute liver failure.

Journal of immunotoxicology·2009
Same author

A novel scoring system for prognostic prediction in d-galactosamine/lipopolysaccharide-induced fulminant hepatic failure BALB/c mice.

BMC gastroenterology·2009
Same author

Mammalian target of rapamycin signaling pathway contributes to glioma progression and patients' prognosis.

The Journal of surgical research·2009
Same author

Estrogen receptor neurobiology and its potential for translation into broad spectrum therapeutics for CNS disorders.

Current molecular pharmacology·2009
Same author

Transcriptional and post-translational regulation of adiponectin.

The Biochemical journal·2009

Related Experiment Video

Updated: Oct 27, 2025

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
08:51

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

9.3K

Accelerating quantitative susceptibility and R2* mapping using incoherent undersampling and deep neural network

Yang Gao1, Martijn Cloos2, Feng Liu1

  • 1School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, Australia.

Neuroimage
|July 19, 2021
PubMed
Summary

A new Deep Complex Residual Network (DCRNet) accelerates MRI quantitative susceptibility mapping (QSM) and R2* mapping. This deep learning method recovers phase signals, significantly reducing artifacts and reconstruction time for faster, more accurate brain imaging.

Keywords:
Compressed sensingDeep complex residual network (DCRNet)MRI phase accelerationQSM accelerationQuantitative susceptibility mapping (QSM)

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.4K
Dual Raster-Scanning Photoacoustic Small-Animal Imager for Vascular Visualization
07:14

Dual Raster-Scanning Photoacoustic Small-Animal Imager for Vascular Visualization

Published on: July 15, 2020

4.3K

Related Experiment Videos

Last Updated: Oct 27, 2025

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
08:51

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

9.3K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.4K
Dual Raster-Scanning Photoacoustic Small-Animal Imager for Vascular Visualization
07:14

Dual Raster-Scanning Photoacoustic Small-Animal Imager for Vascular Visualization

Published on: July 15, 2020

4.3K

Area of Science:

  • Magnetic Resonance Imaging (MRI)
  • Medical Image Analysis
  • Deep Learning in Radiology

Background:

  • Quantitative susceptibility mapping (QSM) and R2* mapping are crucial MRI techniques for assessing tissue properties.
  • Traditional QSM and R2* acquisitions are time-consuming, limiting clinical application.
  • Existing acceleration methods often fail to recover the full phase signal essential for QSM.

Purpose of the Study:

  • To develop and validate a deep learning-based method for accelerating QSM and R2* MRI acquisition.
  • To enable recovery of both magnitude and phase information from undersampled MRI data.
  • To compare the proposed method against existing iterative and deep learning techniques.

Main Methods:

  • A Deep Complex Residual Network (DCRNet) was developed to reconstruct magnitude and phase images from incoherently undersampled data.
  • The DCRNet was evaluated on retrospective and prospective undersampled datasets from healthy subjects and patients (intracranial hemorrhage, multiple sclerosis) using a 7T scanner.
  • Performance was assessed using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Root-Mean-Squared Error (RMSE), and region-of-interest measurements.

Main Results:

  • DCRNet significantly reduced artifacts and blurring compared to iterative and other deep learning methods.
  • The method achieved superior PSNR, SSIM, and RMSE for magnitude, R2*, local field, and susceptibility maps.
  • A 3.2% to 9.1% accuracy improvement in deep grey matter susceptibility was observed at 4x acceleration.
  • Reconstruction time was drastically reduced from 36-140 seconds to 15-70 milliseconds per 2D image.

Conclusions:

  • The proposed DCRNet enables highly accelerated QSM and R2* MRI acquisition with improved image quality.
  • DCRNet offers a promising solution for faster and more accurate quantitative MRI in clinical settings.
  • This deep learning approach overcomes limitations of previous acceleration techniques for phase-sensitive MRI.