HyperFitS -- Hypernetwork Fitting Spectra for metabolic quantification of ${}^1$H MR spectroscopic imaging

2026-04-03

AI Summary

This study addresses the challenges of time-consuming metabolite quantification in ¹H magnetic resonance spectroscopic imaging (MRSI) and the limited parameter adaptability of existing deep learning approaches. To overcome these issues, the authors propose HyperFitS, a hypernetwork-based spectral fitting method that, for the first time, integrates hypernetworks into MRSI metabolite quantification. HyperFitS flexibly adapts to varying baseline correction strategies, water suppression states, field strengths (3T/7T), and spatial resolutions (2–10 mm) without requiring retraining. Experimental results demonstrate that HyperFitS achieves whole-brain metabolite quantification within seconds, with outputs highly consistent with the LCModel gold standard. The study further reveals that baseline parameterization can influence quantification results by up to 30%, underscoring the method’s enhanced generalizability and computational efficiency.

Abstract

Purpose: Proton magnetic resonance spectroscopic imaging ($^1$H MRSI) enables the mapping of whole-brain metabolites concentrations in-vivo. However, a long-standing problem for its clinical applicability is the metabolic quantification, which can require extensive time for spectral fitting. Recently, deep learning methods have been able to provide whole-brain metabolic quantification in only a few seconds. However, neural network implementations often lack configurability and require retraining to change predefined parameter settings. Methods: We introduce HyperFitS, a hypernetwork for spectral fitting for metabolite quantification in whole-brain $^1$H MRSI that flexibly adapts to a broad range of baseline corrections and water suppression factors. Metabolite maps of human subjects acquired at 3T and 7T with isotropic resolutions of 10 mm, 3.4 mm and 2 mm by water-suppressed and water-unsuppressed MRSI were quantified with HyperFitS and compared to conventional LCModel fitting. Results: Metabolic maps show a substantial agreement between the new and gold-standard methods, with significantly faster fitting times by HyperFitS. Quantitative results further highlight the impact of baseline parametrization on metabolic quantification, which can alter results by up to 30%. Conclusion: HyperFitS shows strong agreement with state-of-the-art conventional methods, while reducing processing times from hours to a few seconds. Compared to prior deep learning based spectral fitting methods, HyperFitS enables a wide range of configurability and can adapt to data quality acquired with multiple protocols and field strengths without retraining.

Problem

• metabolic quantification
• ¹H MRSI
• spectral fitting
• deep learning
• configurability

Innovation

• hypernetwork
• spectral fitting
• metabolic quantification
• MRSI
• configurable deep learning