WAND: Wavelet Analysis-based Neural Decomposition of MRS Signals for Artifact Removal

TL;DR

WAND is a novel wavelet analysis-based neural method that decomposes MRS signals into metabolites, baseline, and artifacts, improving artifact removal and metabolite quantification accuracy.

Contribution

This paper introduces WAND, a neural decomposition approach utilizing wavelet transforms and masks to effectively separate MRS signal components, including unpredictable artifacts.

Findings

WAND improves artifact removal in simulated MRS data.

The method enhances metabolite quantification accuracy.

Validated on MRS Challenge data and in-vivo experiments.

Abstract

Accurate quantification of metabolites in magnetic resonance spectroscopy (MRS) is challenged by low signal-to-noise ratio (SNR), overlapping metabolites, and various artifacts. Particularly, unknown and unparameterized baseline effects obscure the quantification of low-concentration metabolites, limiting MRS reliability. This paper introduces wavelet analysis-based neural decomposition (WAND), a novel data-driven method designed to decompose MRS signals into their constituent components: metabolite-specific signals, baseline, and artifacts. WAND takes advantage of the enhanced separability of these components within the wavelet domain. The method employs a neural network, specifically a U-Net architecture, trained to predict masks for wavelet coefficients obtained through the continuous wavelet transform. These masks effectively isolate desired signal components in the wavelet domain, which are then inverse-transformed to obtain separated signals. Notably, an artifact mask is created by inverting the sum of all known signal masks, enabling WAND to capture and remove even unpredictable artifacts. The effectiveness of WAND in achieving accurate decomposition is demonstrated through numerical evaluations using simulated spectra. Furthermore, WAND's artifact removal capabilities significantly enhance the quantification accuracy of linear combination model fitting. The method's robustness is further validated using data from the 2016 MRS Fitting Challenge and in-vivo experiments.