The impact of training data on MRS metabolite quantification with deep learning

Ma, Zien, Karakus, Oktay ORCID: https://orcid.org/0000-0001-8009-9319, Shermer, SM and Langbein, Frank ORCID: https://orcid.org/0000-0002-3379-0323 2025. The impact of training data on MRS metabolite quantification with deep learning. Presented at: ISMRM & ISMRT Annual Meeting & Exhibition 2025, Honolulu, Hawaii, USA, 10-15 May 2025.

Preview

PDF (Abstract) - Accepted Post-Print Version Download (2MB) | Preview

Abstract

We investigate the impact of training data quality on deep learning models for metabolite quantification in MRS. Our focus is on two key aspects of simulated training datasets: the variability of metabolite models and the realism of the noise model. Our results demonstrate that the training dataset, particularly the choice of noise model, impacts quantification performance, highlighting the importance of realistic simulations. Our results are limited to a few cases but clearly indicate potential for investigating the training datasets. Focusing on improving the realism of simulations or obtaining large real datasets may yield substantial improvements in quantifying metabolites in MRS spectra.

Item Type:	Conference or Workshop Item (Poster)
Status:	In Press
Schools:	Schools > Computer Science & Informatics
Date of First Compliant Deposit:	14 February 2025
Date of Acceptance:	31 January 2025
Last Modified:	10 Mar 2025 16:30
URI:	https://orca.cardiff.ac.uk/id/eprint/176200

Actions (repository staff only)

Edit Item