Spatially Adaptive Spectral Denoising for MR Spectroscopic Imaging using Frequency-Phase Non-local Means

Magnetic resonance spectroscopic imaging (MRSI) is an imaging modality used for generating metabolic maps of the tissue in-vivo. These maps show the concentration of metabolites in the sample being investigated and their accurate quantification is important to diagnose diseases. However, the major roadblocks in accurate metabolite quantification are: low spatial resolution, long scanning times, poor signal-tonoise ratio (SNR) and the subsequent noise-sensitive non-linear model fitting. In this work, we propose a frequency-phase spectral denoising method based on the concept of non-local means (NLM) that improves the robustness of data analysis and scanning times while potentially increasing spatial resolution. We evaluate our method on simulated data sets as well as on human in-vivo MRSI data. Our denoising method improves the SNR while maintaining the spatial resolution of the spectra.