Strategies to Minimize Out-of-Distribution Effects in Data-Driven MRS Quantification

TL;DR

This paper compares data-driven and model-based methods for MRS metabolite quantification, highlighting the importance of test-time adaptation for robustness against out-of-distribution effects in both simulated and in-vivo data.

Contribution

It introduces and evaluates three training strategies for neural network-based MRS quantification, emphasizing test-time adaptation as a robust approach against OoD effects.

Findings

Supervised learning performs well within training distribution but degrades out-of-distribution.

Test-time adaptation offers greater resilience to OoD effects.

Domain shift causes variability in in-vivo results across methods.

Abstract

This study systematically compared data-driven and model-based strategies for metabolite quantification in magnetic resonance spectroscopy (MRS), focusing on resilience to out-of-distribution (OoD) effects and the balance between accuracy, robustness, and generalizability. A neural network designed for MRS quantification was trained using three distinct strategies: supervised regression, self-supervised learning, and test-time adaptation. These were compared against model-based fitting tools. Experiments combined large-scale simulated data, designed to probe metabolite concentration extrapolation and signal variability, with 1H single-voxel 7T in-vivo human brain spectra. In simulations, supervised learning achieved high accuracy for spectra similar to those in the training distribution, but showed marked degradation when extrapolated beyond the training distribution. Test-time adaptation proved more resilient to OoD effects, while self-supervised learning achieved intermediate performance. In-vivo experiments showed larger variance across the methods (data-driven and model-based) due to domain shift. Across all strategies, overlapping metabolites and baseline variability remained persistent challenges. While strong performance can be achieved by data-driven methods for MRS metabolite quantification, their reliability is contingent on careful consideration of the training distribution and potential OoD effects. When such conditions in the target distribution cannot be anticipated, test-time adaptation strategies ensure consistency between the quantification, the data, and the model, enabling reliable data-driven MRS pipelines.