Magnetic Resonance Spectroscopy Deep Learning Denoising Using Few In Vivo Data

TL;DR

This paper introduces ReLSTM, a deep learning model that denoises in vivo Magnetic Resonance Spectroscopy data using only a small subset of repeated samples, enabling faster scans with high accuracy.

Contribution

The study presents a novel ReLSTM model trained solely on realistic in vivo data, reducing the need for extensive data and improving denoising performance in clinical MRS applications.

Findings

ReLSTM achieves comparable metabolite concentration estimates with only 20% of the repeated samples.

ReLSTM outperforms low-rank denoising methods in error metrics and biomarker quantification.

Fast acquisition spectra can be effectively denoised, facilitating quicker clinical MRS scans.

Abstract

Magnetic Resonance Spectroscopy (MRS) is a noninvasive tool to reveal metabolic information. One challenge of 1H-MRS is the low Signal-Noise Ratio (SNR). To improve the SNR, a typical approach is to perform Signal Averaging (SA) with M repeated samples. The data acquisition time, however, is increased by M times accordingly, and a complete clinical MRS scan takes approximately 10 minutes at a common setting M=128. Recently, deep learning has been introduced to improve the SNR but most of them use the simulated data as the training set. This may hinder the MRS applications since some potential differences, such as acquisition system imperfections, and physiological and psychologic conditions may exist between the simulated and in vivo data. Here, we proposed a new scheme that purely used the repeated samples of realistic data. A deep learning model, Refusion Long Short-Term Memory (ReLSTM), was designed to learn the mapping from the low SNR time-domain data (24 SA) to the high SNR one (128 SA). Experiments on the in vivo brain spectra of 7 healthy subjects, 2 brain tumor patients and 1 cerebral infarction patient showed that only using 20% repeated samples, the denoised spectra by ReLSTM could provide comparable estimated concentrations of metabolites to 128 SA. Compared with the state-of-the-art low-rank denoising method, the ReLSTM achieved the lower relative error and the Cram\'er-Rao lower bounds in quantifying some important biomarkers. In summary, ReLSTM can perform high-fidelity denoising of the spectra under fast acquisition (24 SA), which would be valuable to MRS clinical studies.