Data-driven Synthesis of Magnetic Resonance Spectroscopy Data using a Variational Autoencoder

TL;DR

This paper presents a variational autoencoder-based method to synthesize in-vivo magnetic resonance spectroscopy data, aiming to augment limited datasets and improve spectral analysis, while also evaluating the approach's strengths and limitations.

Contribution

It introduces a data-driven VAE framework trained on measured MRS data for realistic synthetic spectrum generation and provides a comprehensive evaluation methodology.

Findings

VAE accurately reconstructs dominant spectral patterns.

Synthetic spectra improve signal quality metrics in applications.

Limitations include under-representation of noise and reduced metabolite quantification accuracy.

Abstract

The development of deep learning methods for magnetic resonance spectroscopy (MRS) is often hindered by limited availability of large, high-quality training datasets. While physics-based simulations are commonly used to mitigate this limitation, accurately modeling all in-vivo signal components remains challenging. In this work, we propose a data-driven framework for synthesizing in-vivo MRS data using a variational autoencoder (VAE) trained exclusively on measured single-voxel spectroscopy data. The model learns a low-dimensional latent representation of complex-valued spectra and enables generation of new samples through latent-space sampling and interpolation. The generative performance of the proposed approach is evaluated using a comprehensive set of complementary analyses, including reconstruction quality, feature-level similarity using low-dimensional embeddings, application-based signal quality metrics, and metabolite quantification agreement. The results demonstrate that the VAE accurately reconstructs dominant spectral patterns and generates synthetic spectra that occupy the same feature space as in-vivo data. In an example application targeting GABA-edited spectroscopy, augmenting limited subsets of transients with synthetic spectra improves signal quality metrics such as signal-to-noise ratio, linewidth, and shape scores. However, the results also reveal limitations of the generative approach, including under-representation of stochastic noise and reduced accuracy in absolute metabolite quantification, particularly for applications sensitive to concentration estimates. These findings highlight both potential and limitations of data-driven MRS synthesis. Beyond the proposed model, this study introduces a structured evaluation framework for generative MRS methods, emphasizing the importance of application-aware validation when synthetic data are used for downstream analysis.