Deep Learning Reconstruction for 129 Xe Diffusion‐Weighted MRI Enables Use of Natural Abundant Xenon and Improved Image Acceleration
Magnetic Resonance in Medicine · 2026
DOI: 10.1002/mrm.70194 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2026. Verfasst von Rajagopalan Sundaresan und 6 weiteren Autor:innen. Beteiligte Einrichtung: POLARIS, Division of Clinical Medicine, School of Medicine & Population Health, Faculty of Health, The University of Sheffield, Sheffield, UK. Hauptthemen laut MEDLINE: Diffusion Magnetic Resonance Imaging, Deep Learning, Xenon Isotopes, Image Processing, Computer-Assisted. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EPSRC and MRC Prosperity Partnership, EPSRC Centre for Doctoral Training in Medical Imaging.
Abstract (Originalsprache)
Purpose
(i) To assess whether 129 Xe apparent diffusion coefficient (ADC) and diffusive length scale (Lm D ) metrics are quantitatively preserved with deep learning (DL) accelerated acquisition and reconstruction and (ii) to evaluate the feasibility of 129 Xe diffusion weighted imaging with natural‐abundance xenon at increased acceleration factors.
Methods
Twenty three‐dimensional compressed sensing (CS) accelerated 129 Xe DW MRI datasets were gathered from a cohort of patients with asthma, chronic obstructive pulmonary disease (COPD) and idiopathic pulmonary fibrosis (IPF). Images were retrospectively reconstructed with DL based CS, denoising and de‐ringing reconstruction, and compared to conventional CS. ADC and diffusive length scales (Lm D ) were assessed and compared between conventional CS and DL reconstructions. Prospectively acquired DL reconstruction was then assessed in three healthy volunteers who underwent 129 Xe DW MRI with both natural‐abundance and enriched xenon mixes.
Results
DL reconstruction qualitatively improved the sharpness, SNR and image quality of 129 Xe DW images. In the retrospective study, DL reconstruction produced a slight bias in ADC (5.4%) and Lm D (0.8%) values when compared with conventional CS reconstruction. In the prospective study, DL reconstruction significantly improved the SNR of natural‐abundance xenon images and produced ADC and Lm D values comparable to those achieved with 129‐enriched xenon.
Conclusion
DL‐based CS, denoising and de‐ringing significantly improves SNR and image sharpness in 3D 129 Xe diffusion‐weighted MRI while exhibiting a slight bias in ADC and Lm D . This approach enables the use of natural‐abundance xenon and higher acceleration factors, offering substantial cost reduction and improved clinical feasibility for hyperpolarized 129 Xe lung morphometry.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- POLARIS, Division of Clinical Medicine, School of Medicine & Population Health, Faculty of Health, The University of Sheffield, Sheffield, UK.
- GE HealthCare, Bengaluru, India.
- Insigneo Institute, The University of Sheffield, Sheffield, UK.
- GE HealthCare, Chalfont St Giles, UK.
ORCID-Profile: Rajagopalan Sundaresan, Guilhem J Collier, Neil J Stewart
Förderung
- EPSRC and MRC Prosperity Partnership
- EPSRC Centre for Doctoral Training in Medical Imaging
Zitieren
APA
Sundaresan, R., Collier, G. J., Stewart, N. J., Chatterjee, S., Venkatesan, R., Wolber, J., & Wild, J. M. (2026). Deep Learning Reconstruction for 129 Xe Diffusion‐Weighted MRI Enables Use of Natural Abundant Xenon and Improved Image Acceleration. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.70194
Vancouver
Sundaresan R, Collier GJ, Stewart NJ, Chatterjee S, Venkatesan R, Wolber J, et al. Deep Learning Reconstruction for 129 Xe Diffusion‐Weighted MRI Enables Use of Natural Abundant Xenon and Improved Image Acceleration. Magnetic Resonance in Medicine. 2026. doi:10.1002/mrm.70194
BibTeX
@article{Sundaresan2026,
author = {Sundaresan, Rajagopalan and Collier, Guilhem J and Stewart, Neil J and Chatterjee, Sudhanya and Venkatesan, Ramesh and Wolber, Jan and Wild, Jim M},
title = {Deep Learning Reconstruction for 129 Xe Diffusion‐Weighted MRI Enables Use of Natural Abundant Xenon and Improved Image Acceleration},
journal = {Magnetic Resonance in Medicine},
year = {2026},
doi = {10.1002/mrm.70194}
}
EUVIMED