EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network

Rebecca R Baker, Vivek Muthurangu, Marilena Rega, Stephen B Walsh, Jennifer A Steeden

Magnetic Resonance Imaging · 2024-07 · 110 · 184-194

DOI: 10.1016/j.mri.2024.04.027 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2024-07. Verfasst von Rebecca R Baker und 4 weiteren Autor:innen. Beteiligte Einrichtung: UCL Centre for Medical Imaging, University College London, London, UK; UCL Centre for Translational Cardiovascular Imaging, University College London…. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Neural Networks, Computer, Signal-To-Noise Ratio, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Michael J Fox Foundation for Parkinson's Research, UK Research and Innovation, UKRI Medical Research Council.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: 23Na MRI can be used to quantify in-vivo tissue sodium concentration (TSC), but the inherently low 23Na signal leads to long scan times and/or noisy or low-resolution images. Reconstruction algorithms such as compressed sensing (CS) have been proposed to mitigate low signal-to-noise ratio (SNR); although, these can result in unnatural images, suboptimal denoising and long processing times. Recently, machine learning has been increasingly used to denoise 1H MRI acquisitions; however, this approach typically requires large volumes of high-quality training data, which is not readily available for 23Na MRI. Here, we propose using 1H data to train a denoising convolutional neural network (CNN), which we subsequently demonstrate on prospective 23Na images of the calf. METHODS: 1893 1H fat-saturated transverse slices of the knee from the open-source fastMRI dataset were used to train denoising CNNs for different levels of noise. Synthetic low SNR images were generated by adding gaussian noise to the high-quality 1H k-space data before reconstruction to create paired training data. For prospective testing, 23Na images of the calf were acquired in 10 healthy volunteers with a total of 150 averages over ten minutes, which were used as a reference throughout the study. From this data, images with fewer averages were retrospectively reconstructed using a non-uniform fast Fourier transform (NUFFT) as well as CS, with the NUFFT images subsequently denoised using the trained CNN. RESULTS: CNNs were successfully applied to 23Na images reconstructed with 50, 40 and 30 averages. Muscle and skin apparent TSC quantification from CNN-denoised images were equivalent to those from CS images, with

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingNeural Networks, ComputerSignal-To-Noise RatioImage Processing, Computer-AssistedAlgorithmsHumansLegMaleAdultFemaleSodium IsotopesProspective StudiesSodiumHealthy VolunteersMuscle, Skeletal

Stichwörter der Autor:innen

(23)Na MRIConvolutional neural networkDenoisingMachine learningSodiumX-nuclei

Substanzen

Sodium IsotopesSodium

Autor:innen und Institutionen

  • UCL Centre for Medical Imaging, University College London, London, UK; UCL Centre for Translational Cardiovascular Imaging, University College London, London, UK. Electronic address: r.baker.17@ucl.ac.uk.
  • UCL Centre for Translational Cardiovascular Imaging, University College London, London, UK. Electronic address: v.muthurangu@ucl.ac.uk.
  • Institute of Nuclear Medicine, University College Hospital, London, UK. Electronic address: marilena.rega@nhs.net.
  • Department of Renal Medicine, University College London, London, UK. Electronic address: stephen.walsh@ucl.ac.uk.
  • UCL Centre for Translational Cardiovascular Imaging, University College London, London, UK. Electronic address: jennifer.steeden@ucl.ac.uk.

Förderung

  • Michael J Fox Foundation for Parkinson's Research
  • UK Research and Innovation
  • UKRI Medical Research Council

Zitieren

APA

Baker, R. R., Muthurangu, V., Rega, M., Walsh, S. B., & Steeden, J. A. (2024). Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network. Magnetic Resonance Imaging, 110, 184-194. https://doi.org/10.1016/j.mri.2024.04.027

Vancouver

Baker RR, Muthurangu V, Rega M, Walsh SB, Steeden JA. Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network. Magnetic Resonance Imaging. 2024;110:184-194. doi:10.1016/j.mri.2024.04.027

BibTeX
@article{Baker2024,
  author = {Baker, Rebecca R and Muthurangu, Vivek and Rega, Marilena and Walsh, Stephen B and Steeden, Jennifer A},
  title = {Rapid 2D 23Na MRI of the calf using a denoising convolutional neural network},
  journal = {Magnetic Resonance Imaging},
  year = {2024},
  volume = {110},
  pages = {184--194},
  doi = {10.1016/j.mri.2024.04.027}
}
Kostenlos starten →