Accelerated water residual removal in MRS : Exploring deep learning versus fitting‐based approaches
Magnetic Resonance in Medicine · 2026
DOI: 10.1002/mrm.70031 ↗Kurz gefasst
Fachartikel in der Zeitschrift Magnetic Resonance in Medicine, 2026. Verfasst von Federico Turco und 2 weiteren Autor:innen. Beteiligte Einrichtung: Support Center for Advanced Neuroimaging (SCAN), Institute for Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland. Hauptthemen laut MEDLINE: Deep Learning, Water, Brain, Image Processing, Computer-Assisted. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: H2020 Marie Skłodowska-Curie Actions, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung.
Abstract (Originalsprache)
Purpose
Removing water residual signals from MRS spectra is crucial for accurate metabolite quantification. However, currently available algorithms are computationally intensive and time‐consuming, limiting their clinical applicability. This work aims to propose and validate two novel pipelines for fast water residual removal in MRS.
Methods
Two methods for water residual removal are proposed and evaluated: DeepWatR and WaterFit. DeepWatR uses a U‐Net‐like architecture with an attention mechanism for skip connections. WaterFit uses Torch auto‐differentiation to estimate parameters for a 7‐pool Lorentzian model. The accuracy and time‐efficiency of these methods were assessed using simulated and in vivo 1H brain datasets and compared with the gold standard, Hankel Lanczos singular value decomposition method (HLSVD)Pro.
Results
In the simulated dataset, the average percentage quantification error was % for DeepWatR and % for WaterFit, both comparable to % for HLSVDPro in the main metabolites (Cr, Cho, and NAA). DeepWatR was 51 times faster and WaterFit was 22.7 times faster than HLSVDPro for a dataset of 10 000 voxels when using a low‐end graphics processing unit. For 100 voxels, the speed‐up is 6.5 and 7.5 times faster for DeepWatR and WaterFit, respectively. WaterFit showed higher metabolite fitting accuracy after water removal compared to DeepWatR.
Conclusion
WaterFit showed a superior balance of accuracy and processing speed in removing water residual from MRS data compared to DeepWatR. The proposed WaterFit implementation significantly reduces preprocessing time while maintaining metabolite fitting accuracy comparable to gold standard methods. This advancement addresses the need for efficient processing methods that can facilitate analysis and enhance the clinical utility of MRS.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Support Center for Advanced Neuroimaging (SCAN), Institute for Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland.
- Graduate School for Cellular and Biomedical Sciences (GCB), University of Bern, Bern, Switzerland.
ORCID-Profile: Federico Turco, Johannes Slotboom, Milena Capiglioni
Förderung
- H2020 Marie Skłodowska-Curie Actions
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Zitieren
APA
Turco, F., Slotboom, J., & Capiglioni, M. (2026). Accelerated water residual removal in MRS : Exploring deep learning versus fitting‐based approaches. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.70031
Vancouver
Turco F, Slotboom J, Capiglioni M. Accelerated water residual removal in MRS : Exploring deep learning versus fitting‐based approaches. Magnetic Resonance in Medicine. 2026. doi:10.1002/mrm.70031
BibTeX
@article{Turco2026,
author = {Turco, Federico and Slotboom, Johannes and Capiglioni, Milena},
title = {Accelerated water residual removal in MRS : Exploring deep learning versus fitting‐based approaches},
journal = {Magnetic Resonance in Medicine},
year = {2026},
doi = {10.1002/mrm.70031}
}
EUVIMED