Physics-informed deep learning approach to quantification of human brain metabolites from magnetic resonance spectroscopy data

0570880 - ÚPT 2024 RIV GB eng J - Journal Article
Shamaei, Amirmohammad - Starčuková, Jana - Starčuk jr., Zenon
Physics-informed deep learning approach to quantification of human brain metabolites from magnetic resonance spectroscopy data.
Computers in Biology Medicine. Roč. 158, May (2023), č. článku 106837. ISSN 0010-4825. E-ISSN 1879-0534
R&D Projects: GA MŠMT(CZ) EF18_046/0016045; GA MŠMT(CZ) LM2018129; GA MŠMT(CZ) LM2023050
EU Projects: European Commission(XE) 813120 - INSPiRE-MED
Institutional support: RVO:68081731
Keywords : MR spectroscopy * Inverse problem * Deep learning * Machine learning * Convolutional neural network * Metabolite quantification
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 7.7, year: 2022
Method of publishing: Open access
https://www.sciencedirect.com/science/article/pii/S0010482523003025

Purpose: While the recommended analysis method for magnetic resonance spectroscopy data is linear combination model (LCM) fitting, the supervised deep learning (DL) approach for quantification of MR spectroscopy (MRS) and MR spectroscopic imaging (MRSI) data recently showed encouraging results, however, supervised learning requires ground truth fitted spectra, which is not practical. Moreover, this work investigates the feasibility and efficiency of the LCM-based self-supervised DL method for the analysis of MRS data. Method: We present a novel DL-based method for the quantification of relative metabolite concentrations, using quantum-mechanics simulated metabolite responses and neural networks. We trained, validated, and evaluated the proposed networks with simulated and publicly accessible in-vivo human brain MRS data and compared the performance with traditional methods. A novel adaptive macromolecule fitting algorithm is included. We investigated the performance of the proposed methods in a Monte Carlo (MC) study. Result: The validation using low-SNR simulated data demonstrated that the proposed methods could perform quantification comparably to other methods. The applicability of the proposed method for the quantification of in-vivo MRS data was demonstrated. Our proposed networks have the potential to reduce computation time significantly. Conclusion: The proposed model-constrained deep neural networks trained in a self-supervised manner can offer fast and efficient quantification of MRS and MRSI data. Our proposed method has the potential to facilitate clinical practice by enabling faster processing of large datasets such as high-resolution MRSI datasets, which may have thousands of spectra.
Permanent Link: https://hdl.handle.net/11104/0342210


Research data: Zenodo