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.