Fast and accurate reconstruction of human lung gas MRI with deep learning

Abstract

Purpose To fast and accurately reconstruct human lung gas MRI from highly undersampled k‐space using deep learning. Methods The scheme was comprised of coarse‐to‐fine nets (C‐net and F‐net). Zero‐filling images from retrospectively undersampled k‐space at an acceleration factor of 4 were used as input for C‐net, and then output intermediate results which were fed into F‐net. During training, a L2 loss function was adopted in C‐net, while a function that united L2 loss with proton prior knowledge was used in F‐net. The 871 hyperpolarized 129Xe pulmonary ventilation images from 72 volunteers were randomly arranged as training (90%) and testing (10%) data. Ventilation defect percentage comparisons were implemented using a paired 2‐tailed Student's t‐test and correlation analysis. Furthermore, prospective acquisitions were demonstrated in 5 healthy subjects and 5 asymptomatic smokers. Results Each image with size of 96 × 84 could be reconstructed within 31 ms (mean absolute error was 4.35% and structural similarity was 0.7558). Compared with conventional compressed sensing MRI, the mean absolute error decreased by 17.92%, but the structural similarity increased by 6.33%. For ventilation defect percentage, there were no significant differences between the fully sampled and reconstructed images through the proposed algorithm (P = 0.932), but had significant correlations (r = 0.975; P < 0.001). The prospectively undersampled results validated a good agreement with fully sampled images, with no significant differences in ventilation defect percentage but significantly higher signal‐to‐noise ratio values. Conclusion The proposed algorithm outperformed classical undersampling methods, paving the way for future use of deep learning in real‐time and accurate reconstruction of gas MRI.

Damaged lung gas exchange function of discharged COVID-19 patients detected by hyperpolarized 129 Xe MRI

“…As an emerging technique for quantifying pulmonary function in pulmonary diseases, the feasibility of hyperpolarized xenon gas MRI in evaluating gas-exchange function and microstructural parameters of the lung has been demonstrated in multiple clinical studies (18)(19)(20)(21)(22)(23). However, none of them have dealt with COVID-19 patients.…”

Sample size estimation: Current practice and considerations for original investigations in MRI technical development studies

“…Some of the included articles with N ≥ 20 were not on MR method developments, but on subjects such as test–retest reliability of phase contrast MRI (N = 27) 22 or the determination of relaxation times of the spinal cord at 3T (N = 30) 23 . Moreover, image‐based deep learning approaches often place certain demands on minimal sampling size, for example, Duan et al 24 selected N = 30 (plus 42 volunteers with disease) for an undersampled deep learning‐based reconstruction of 129 Xe ventilation images.…”

No‐reference image quality assessment of magnetic resonance images with high‐boost filtering and local features

“…Consequently, methods that better correlate with human ratings are preferred. Considering typical usage of NR methods, limited to 2D images, NORMIQA can be applied to select best performing denoising techniques, approaches for correcting artifacts, or image reconstruction solutions . Also, the method can be used to support subjective tests with human observers since such an assessment is often unrepeatable.…”