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

Purpose: ²³Na MRI can be used to quantify in-vivo tissue sodium concentration (TSC), but the inherently low ²³Na 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 ¹H MRI acquisitions; however, this approach typically requires large volumes of high-quality training data, which is not readily available for ²³Na MRI. Here, we propose using ¹H data to train a denoising convolutional neural network (CNN), which we subsequently demonstrate on prospective ²³Na images of the calf.

Methods: 1893 ¹H 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 ¹H k-space data before reconstruction to create paired training data. For prospective testing, ²³Na 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.

Results: CNNs were successfully applied to ²³Na 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 <0.9 mM bias compared to reference values. Estimated SNR was significantly higher in CNN-denoised images compared to NUFFT, CS and reference images. Quantitative edge sharpness was equivalent for all images. For subjective image quality ranking, CNN-denoised images ranked equally best with reference images and significantly better than NUFFT and CS images.

Conclusion: Denoising CNNs trained on ¹H data can be successfully applied to ²³Na images of the calf; thus, allowing scan time to be reduced from ten minutes to two minutes with little impact on image quality or apparent TSC quantification accuracy.