WALINET: A water and lipid identification convolutional neural network for nuisance signal removal in 1H MR spectroscopic imaging
Year: 2024
Type: article
Abstract: Purpose Proton magnetic resonance spectroscopic imaging (‐MRSI) provides noninvasive spectral‐spatial mapping of metabolism. However, long‐standing problems in whole‐brain ‐MRSI are spectral overlap of metabolite peaks with large lipid signal from scalp, and overwhelming water signal that distorts spectra. Fast and effective methods are needed for high‐resolution ‐MRSI to accurately remove lipid and water signals while preserving the metabolite signal. The potential of supervised neural networks for this task remains unexplored, despite their success for other MRSI processing. Methods We introduce a deep learning method based on a modified Y‐NET network for water and lipid removal in whole‐brain ‐MRSI. The WALINET (WAter and LIpid neural NETwork) was compared with conventional methods such as the state‐of‐the‐art lipid L2 regularization and Hankel–Lanczos singular value decomposition (HLSVD) water suppression. Methods were evaluated on simulated models and in vivo whole‐brain MRSI using NMRSE, SNR, CRLB, and FWHM metrics. Results WALINET is significantly faster and needs 8s for high‐resolution whole‐brain MRSI, compared with 42min for conventional HLSVD+L2. WALINET suppresses lipid and water in the brain by 25–45 and 34–53‐fold, respectively. WALINET has better performance than HLSVD+L2, providing: (1) more lipid removal with 41% lower NRMSE; (2) better metabolite signal preservation with 71% lower NRMSE in simulated data; 155% higher SNR and 50% lower CRLB in in vivo data. Metabolic maps obtained by WALINET in healthy subjects and patients show better gray‐/white‐matter contrast with more visible structural details. Conclusions WALINET has superior performance for nuisance signal removal and metabolite quantification on whole‐brain ‐MRSI compared with conventional state‐of‐the‐art techniques. This represents a new application of deep learning for MRSI processing, with potential for automated high‐throughput workflow.
Source: Magnetic Resonance in Medicine
DOI: 10.1002/mrm.30402
Authors: Paul J. Weiser, Georg Langs, Stanislav Motyka, Wolfgang Bogner, Sébastien Courvoisier, Malte Hoffmann, Antoine Klauser, Ovidiu C. Andronesi
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Estimated APC paid: $3,500
Funders: Austrian Science Fund, Centre d'Imagerie BioMédicale, Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, National Cancer Institute, National Institute of Biomedical Imaging and Bioengineering, Eunice Kennedy Shriver National Institute of Child Health and Human Development
Awards: G1360098495, G3717522969, G3870137688, Deep learning in MR Spectroscopic Imaging, Center for Functional Imaging Technologies, Fast motion-robust fetal neuroimaging with MRI, Development of multinuclear MRI for image guided therapy of glioma patients, Development of next generation 2HG and metabolic MR imaging for precision oncology of mutant IDH and wildtype glioma patients, Targeted Therapies for Glioma
OpenAlex ID: W4405930541