Comparative evaluation of supervised and unsupervised deep learning strategies for denoising hyperpolarized 129 Xe lung MRI
Open Access
- 14 August 2025
- journal article
- Published by Wiley in Magnetic Resonance in Medicine
- Vol. 95 (1) , 138-156
Abstract
Purpose: Reduced signal‐to‐noise ratio (SNR) in hyperpolarized 129 Xe MR images can affect accurate quantification for research and diagnostic evaluations. Thus, this study explores the application of supervised deep learning (DL) denoising, traditional (Trad) and Noise2Noise (N2N) and unsupervised Noise2void (N2V) approaches for 129 Xe MR imaging. Methods: The DL denoising frameworks were trained and tested on 952 129 Xe MRI data sets (421 ventilation, 125 diffusion‐weighted, and 406 gas‐exchange acquisitions) from healthy subjects and participants with cardiopulmonary conditions and compared with the block matching 3D denoising technique. Evaluation involved mean signal, noise standard deviation (SD), SNR, and sharpness. Ventilation defect percentage (VDP), apparent diffusion coefficient (ADC), membrane uptake, red blood cell (RBC) transfer, and RBC:Membrane were also evaluated for ventilation, diffusion, and gas‐exchange images, respectively. Results: Denoising methods significantly reduced noise SDs and enhanced SNR ( p < 0.05) across all imaging types. Traditional ventilation model (Trad vent ) improved sharpness in ventilation images but underestimated VDP (bias = −1.37%) relative to raw images, whereas N2N vent overestimated VDP (bias = +1.88%). Block matching 3D and N2V vent showed minimal VDP bias (≤ 0.35%). Denoising significantly reduced ADC mean and SD ( p < 0.05, bias ≤ − 0.63 × 10 −2 ). The values of Trad vent and N2N vent increased mean membrane and RBC ( p < 0.001) with no change in RBC:Membrane. Denoising also reduced SDs of all gas‐exchange metrics ( p < 0.01). Conclusions: Low SNR may impair the potential of 129 Xe MRI for clinical diagnosis and lung function assessment. The evaluation of supervised and unsupervised DL denoising methods enhanced 129 Xe imaging quality, offering promise for improved clinical interpretation and diagnosis.Keywords
Funding Information
- Cystic Fibrosis Foundation (CLEVEL16A0)
- National Institutes of Health (2R01HL126771, R00HL111217, R01HL131012, R01HL143011, R01HL151588, R01HL166335, R44HL123299)
- National Organization for Rare Disorders (20003)
This publication has 47 references indexed in Scilit:
- Quantifying Spatial Distribution of Ventilation Defects in Multiple Pulmonary Diseases With Hyperpolarized 129Xenon MRIJournal of Magnetic Resonance Imaging, 2024
- Childhood to adulthood: Accounting for age dependence in healthy‐reference distributions in 129Xe gas‐exchange MRIMagnetic Resonance in Medicine, 2022
- Diffusion weighted hyperpolarized 129Xe MRI of the lung with 2D and 3D (FLORET) spiralMagnetic Resonance in Medicine, 2022
- Pediatric 129Xe Gas‐Transfer MRI—Feasibility and ApplicabilityJournal of Magnetic Resonance Imaging, 2022
- Denoising of hyperpolarized 13C MR images of the human brain using patch‐based higher‐order singular value decompositionMagnetic Resonance in Medicine, 2021
- Enabling Clinical Technologies for Hyperpolarized 129Xenon Magnetic Resonance Imaging and SpectroscopyAngewandte Chemie International Edition, 2021
- Removal of off‐resonance xenon gas artifacts in pulmonary gas‐transfer MRIMagnetic Resonance in Medicine, 2021
- Hyperpolarized 129Xe gas transfer MRI: the transition from 1.5T to 3TMagnetic Resonance in Medicine, 2018
- Quantitative analysis of hyperpolarized129Xe gas transfer MRIMedical Physics, 2017
- Single‐breath clinical imaging of hyperpolarized 129xe in the airspaces, barrier, and red blood cells using an interleaved 3D radial 1‐point Dixon acquisitionMagnetic Resonance in Medicine, 2015