EUVIMEDEUVIMED entdecken
Open Access

Accelerated EPR imaging using deep learning denoising

Irene Canavesi, Navin Viswakarma, Boris Epel iD, Alan McMillan iD, Mrignayani Kotecha iD

Magnetic Resonance in Medicine · 2025-07 · 94 (1) · 436-446

DOI: 10.1002/mrm.30473 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, online erschienen am 17.03.2025. Verfasst von Irene Canavesi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Oxygen Measurement Core, O2M Technologies, LLC, Chicago, Illinois, USA. Hauptthemen laut MEDLINE: Deep Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NCI NIH HHS, National Cancer Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Trityl OXO71‐based pulse electron paramagnetic resonance imaging (EPRI) is an excellent technique to obtain partial pressure of oxygen (pO 2 ) maps in tissues. In this study, we used deep learning techniques to denoise 3D EPR amplitude and pO 2 maps.

Methods

All experiments were performed using a 25 mT EPR imager, JIVA‐25®. The MONAI implementation of four neural networks (autoencoder, Attention UNet, UNETR, and UNet) was tested, and the best model (UNet) was then enhanced with joint bilateral filters (JBF). The training dataset was comprised of 227 3D images (56 in vivo and 171 in vitro), 159 images for training, 45 for validation, and 23 for testing. UNet with 1, 2, and 3 JBF layers was tested to improve image SNR, focusing on multiscale structural similarity index measure and edge sensitivity preservation. The trained algorithm was tested using acquisitions with 15, 30, and 150 averages in vitro with a sealed deoxygenated OXO71 phantom and in vivo with fibrosarcoma tumors grown in a hind leg of C3H mice.

Results

We demonstrate that UNet with 2 JBF layers (UNet+JBF2) provides the best outcome. We demonstrate that using the UNet+JBF2 model, the SNR of 15‐shot amplitude maps provides higher SNR compared to 150‐shot pre‐filter maps, both in phantoms and in tumors, therefore, allowing 10‐fold accelerated imaging. We demonstrate that the trained algorithm improves SNR in pO 2 maps.

Conclusions

We demonstrate the application of deep learning techniques to EPRI denoising. Higher SNR will bring the EPRI technique one step closer to clinics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningImage Processing, Computer-AssistedAnimalsElectron Spin Resonance SpectroscopyPhantoms, ImagingMiceAlgorithmsSignal-To-Noise RatioImaging, Three-DimensionalOxygenFibrosarcomaHumans

Stichwörter der Autor:innen

deep learning denoisingelectron paramagnetic resonance imaginghypoxia imagingoxygen imaging

Substanzen

Oxygen

Autor:innen und Institutionen

  • Oxygen Measurement Core, O2M Technologies, LLC, Chicago, Illinois, USA.
  • Department of Radiation and Cellular Oncology, University of Chicago, Chicago, Illinois, USA.
  • Department of Radiology, University of Wisconsin-Madison, Madison, Wisconsin, USA.

ORCID-Profile: Boris Epel, Alan McMillan, Mrignayani Kotecha

Förderung

  • NCI NIH HHS
  • National Cancer Institute

Zitieren

APA

Canavesi, I., Viswakarma, N., Epel, B., McMillan, A., & Kotecha, M. (2025). Accelerated EPR imaging using deep learning denoising. Magnetic Resonance in Medicine, 94(1), 436-446. https://doi.org/10.1002/mrm.30473

Vancouver

Canavesi I, Viswakarma N, Epel B, McMillan A, Kotecha M. Accelerated EPR imaging using deep learning denoising. Magnetic Resonance in Medicine. 2025;94(1):436-446. doi:10.1002/mrm.30473

BibTeX
@article{Canavesi2025,
  author = {Canavesi, Irene and Viswakarma, Navin and Epel, Boris and McMillan, Alan and Kotecha, Mrignayani},
  title = {Accelerated EPR imaging using deep learning denoising},
  journal = {Magnetic Resonance in Medicine},
  year = {2025},
  volume = {94},
  number = {1},
  pages = {436--446},
  doi = {10.1002/mrm.30473}
}
Kostenlos starten →