Rapid 2D 23 Na MRI of the calf using a denoising convolutional neural network

Na MRI can be used to quantify in-vivo tissue sodium concentration (TSC), but the inherently low Na signal leads to long scan times and/or noisy or low-resolution images. Reconstruction algorithms such as compressed sensing (CS) have been proposed to mitigate low signal-to-noise ratio (SNR); although, these can result in unnatural images, suboptimal denoising and long processing times. Recently, machine learning has been increasingly used to denoise H MRI acquisitions; however, this approach typically requires large volumes of high-quality training data, which is not readily available for Na MRI. Here, we propose using H data to train a denoising convolutional neural network (CNN), which we subsequently demonstrate on prospective Na images of the calf. 1893 H fat-saturated transverse slices of the knee from the open-source fastMRI dataset were used to train denoising CNNs for different levels of noise. Synthetic low SNR images were generated by adding gaussian noise to the high-quality H k-space data before reconstruction to create paired training data. For prospective testing, Na images of the calf were acquired in 10 healthy volunteers with a total of 150 averages over ten minutes, which were used as a reference throughout the study. From this data, images with fewer averages were retrospectively reconstructed using a non-uniform fast Fourier transform (NUFFT) as well as CS, with the NUFFT images subsequently denoised using the trained CNN. CNNs were successfully applied to Na images reconstructed with 50, 40 and 30 averages. Muscle and skin apparent TSC quantification from CNN-denoised images were equivalent to those from CS images, with