Improving Brain Metabolite Detection with a Combined Low-Rank Approximation and Denoising Diffusion Probabilistic Model Approach
Abstract
:1. Introduction
2. Materials and Methods
2.1. Datasets
2.1.1. Baseline MRS Dataset
2.1.2. Functional MRS Dataset
2.2. Denoising Methods
2.2.1. Casorati Singular Value Decomposition (CSVD)
2.2.2. Denoising Diffusion Probabilistic Model (DDPM)
2.2.3. Implementation Details
2.3. Data Analysis
3. Results
3.1. Baseline MRS Dataset
3.2. Functional MRS Dataset
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Appendix A
Appendix A.1. Derivation of the Closed-Form Solution for CSVD Denoising
References
- Wilson, M.; Andronesi, O.; Barker, P.B.; Bartha, R.; Bizzi, A.; Bolan, P.J.; Brindle, K.M.; Choi, I.-Y.; Cudalbu, C.; Dydak, U.; et al. A methodological consensus on clinical proton MR spectroscopy of the brain: Review and recommendations. Magn. Reson. Med. 2019, 82, 527–550. [Google Scholar] [CrossRef] [PubMed]
- Archibald, J.; MacMillan, E.L.; Graf, C.; Kozlowski, P.; Laule, C.; Kramer, J.L.K. Metabolite activity in the anterior cingulate cortex during a painful stimulus using functional MRS. Sci. Rep. 2020, 10, 19218. [Google Scholar] [CrossRef] [PubMed]
- Koolschijn, R.S.; Clarke, W.T.; Ip, B.; Emir, U.E.; Barron, H.C. Event-related functional magnetic resonance spectroscopy. NeuroImage 2023, 276, 120194. [Google Scholar] [CrossRef] [PubMed]
- Mullins, P.G.; Rowland, L.M.; Jung, R.E.; Sibbitt, W.L., Jr. A novel technique to study the brain’s response to pain: Proton magnetic resonance spectroscopy. NeuroImage 2005, 26, 642–646. [Google Scholar] [CrossRef]
- Cleve, M.; Gussew, A.; Reichenbach, J.R. In vivo detection of acute pain-induced changes of GABA+ and Glx in the human brain by using functional 1H MEGA-PRESS MR spectroscopy. NeuroImage 2015, 105, 67–75. [Google Scholar] [CrossRef]
- Provencher, S.W. Estimation of metabolite concentrations from localized in vivo proton NMR spectra. Magn. Reason. Med. 1993, 30, 672–679. [Google Scholar] [CrossRef]
- Nguyen, H.M.; Peng, X.; Do, M.N.; Liang, Z.P. Denoising MR spectroscopic imaging data with low-rank approximations. IEEE Trans. Biomed. Eng. 2013, 60, 78–89. [Google Scholar] [CrossRef]
- Rowland, B.; Merugumala, S.K.; Liao, H.; Creager, M.A.; Balschi, J.; Lin, A.P. Spectral improvement by fourier thresholding of in vivo dynamic spectroscopy data. Magn. Reason. Med. 2016, 76, 978–985. [Google Scholar] [CrossRef]
- Brender, J.R.; Kishimoto, S.; Merkle, H.; Reed, G.; Hurd, R.E.; Chen, A.P.; Ardenkjaer-Larsen, J.H.; Munasinghe, J.; Saito, K.; Seki, T.; et al. Dynamic Imaging of Glucose and Lactate Metabolism by 13C-MRS without Hyperpolarization. Sci. Rep. 2019, 9, 3410. [Google Scholar] [CrossRef]
- Hu, W.; Chen, D.; Qiu, T.; Chen, H.; Chen, X.; Yang, L.; Yan, G.; Guo, D.; Qu, X. Denoising Single Voxel Magnetic Resonance Spectroscopy with Deep Learning on Repeatedly Sampled In Vivo Data. arXiv 2021, arXiv:2101.11442. [Google Scholar]
- Clarke, W.T.; Chiew, M. Uncertainty in denoising of MRSI using low-rank methods. Magn. Reason. Med. 2022, 87, 574–588. [Google Scholar] [CrossRef] [PubMed]
- Shamaei, A.; Starcukova, J.; Starcuk, Z., Jr. EigenMRS: A computationally cheap data-driven approach to MR spectroscopic imaging denoising. In Proceedings of the 2023 ISMRM & ISMRT Annual Meeting & Exhibition, Toronto, ON, Canada, 3–8 June 2023; Available online: https://archive.ismrm.org/2023/3440.html (accessed on 4 June 2024).
- Lam, F.; Li, Y.; Peng, X. Constrained Magnetic Resonance Spectroscopic Imaging by Learning Nonlinear Low-Dimensional Models. IEEE Trans. Med. Imaging 2020, 39, 545–555. [Google Scholar] [CrossRef] [PubMed]
- Dziadosz, M.; Rizzo, R.; Kyathanahally, S.P.; Kreis, R. Denoising single MR spectra by deep learning: Miracle or mirage? Magn. Reason. Med. 2023, 90, 1749–1761. [Google Scholar] [CrossRef] [PubMed]
- Li, Y.; Wang, Z.; Lam, F. SNR Enhancement for Multi-TE MRSI Using Joint Low-Dimensional Model and Spatial Constraints. IEEE Trans Biomed Eng. 2022, 69, 3087–3097. [Google Scholar] [CrossRef]
- Li, Y.; Ruhm, L.; Wang, Z.; Zhao, R.; Anderson, A.; Arnold, P.; Huesmann, G.; Henning, A.; Lam, F. Joint learning of nonlinear representation and projection for fast constrained MRSI reconstruction. Magn. Reason. Med. 2024, 1–15. [Google Scholar] [CrossRef]
- Ho, J.; Jain, A.; Abbeel, P. Denoising Diffusion Probabilistic Models. Adv. Neural Inf. Process. Syst. 2020, 33, 6840–6851. [Google Scholar]
- Kazerouni, A.; Aghdam, E.K.; Heidari, M.; Azad, R.; Fayyaz, M.; Hacihaliloglu, I.; Merhof, D. Diffusion models in medical imaging: A comprehensive survey. Med. Image Anal. 2023, 88, 102846. [Google Scholar] [CrossRef]
- Hu, D.; Tao, Y.K.; Oguz, I. Unsupervised Denoising of Retinal OCT with Diffusion Probabilistic Model. arXiv 2022, arXiv:2201.11760v1. [Google Scholar]
- Gong, K.; Johnson, K.A.; El Fakhri, G.; Li, Q.; Pan, T. PET image denoising based on denoising diffusion probabilistic model. arXiv 2022, arXiv:2209.06167v2. [Google Scholar]
- Xiang, T.; Yurt, M.; Syed, A.B.; Setsompop, K.; Chaudhari, A. DDM2: Self-supervised MRI denoising with generative diffusion models. arXiv 2023, arXiv:2302.03018v1. [Google Scholar]
- Provencher, S.W. A constrained regularization method for inverting data represented by linear algebraic or integral equations. Comput. Phys. Commun. 1982, 27, 213–227. [Google Scholar] [CrossRef]
- Shamaei, A.; Starcukova, J.; Rizzo, R.; Starcuk, Z., Jr. Water removal in MR spectroscopic imaging with Casorati singular value decomposition. Magn. Reason. Med. 2024, 91, 1694–1706. [Google Scholar] [CrossRef] [PubMed]
- Dong, Z. Proton MRS and MRSI of the brain without water suppression. Prog. Nucl. Magn. Reson. Spectrosc. 2014, 86–87, 65–79. [Google Scholar] [CrossRef] [PubMed]
- Harris, A.D.; Saleh, M.G.; Edden, R.A.E. Edited 1H Magnetic Resonance Spectroscopy In Vivo: Methods and Metabolites. Magn. Reason. Med. 2017, 77, 1377–1389. [Google Scholar] [CrossRef]
- Anton, A.; Mead, R.J.; Shaw, P.J.; Edden, R.A.E.; Bigley, J.; Jenkins, T.M.; Wild, J.M.; Hoggard, N.; Wilkinson, I.D. Assessment of the Precision in Measuring Glutathione at 3 T With a MEGA-PRESS Sequence in Primary Motor Cortex and Occipital Cortex. J. Magn. Reson. Imaging 2022, 55, 435–442. [Google Scholar] [CrossRef]
- Robison, R.K.; Haynes, J.R.; Ganji, S.K.; Nockowski, C.P.; Kovacs, Z.; Pham, W.; Morgan, V.L.; Smith, S.A.; Thompson, R.C.; Omary, R.A.; et al. J-Difference editing (MEGA) of lactate in the human brain at 3T. Magn. Reason. Med. 2023, 90, 852–862. [Google Scholar] [CrossRef]
- Luque, E.L.; Lui, Z.; Sung, D.; Goldberg, R.M.; Agarwal, R.; Bhattacharya, A.; Ahmed, N.S.; Allen, J.W.; Fleischer, C.C. An Update on MR Spectroscopy in Cancer Management: Advances in Instrumentation, Acquisition, and Analysis. Radiol. Imaging Cancer 2024, 6, e230101. [Google Scholar] [CrossRef]
- Spotorno, N.; Najac, C.; Strandberg, O.; Stomrud, E.; van Westen, D.; Nilsson, M.; Ronen, I.; Hansson, O. Diffusion weighted magnetic resonance spectroscopy revealed neuronal specific microstructural alterations in Alzheimer’s disease. Brain Commun. 2024, 6, fcae026. [Google Scholar] [CrossRef]
- Nam, K.M.; Gursan, A.; Bhogal, A.A.; Wijnen, J.P.; Klomp, D.W.; Prompers, J.J.; Hendriks, A.D. Deuterium echo-planar spectroscopic imaging (EPSI) in the human liver in vivo at 7T. Magn. Reason. Med. 2023, 90, 863–874. [Google Scholar] [CrossRef]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Jeon, Y.-J.; Nam, K.M.; Park, S.-E.; Baek, H.-M. Improving Brain Metabolite Detection with a Combined Low-Rank Approximation and Denoising Diffusion Probabilistic Model Approach. Bioengineering 2024, 11, 1170. https://doi.org/10.3390/bioengineering11111170
Jeon Y-J, Nam KM, Park S-E, Baek H-M. Improving Brain Metabolite Detection with a Combined Low-Rank Approximation and Denoising Diffusion Probabilistic Model Approach. Bioengineering. 2024; 11(11):1170. https://doi.org/10.3390/bioengineering11111170
Chicago/Turabian StyleJeon, Yeong-Jae, Kyung Min Nam, Shin-Eui Park, and Hyeon-Man Baek. 2024. "Improving Brain Metabolite Detection with a Combined Low-Rank Approximation and Denoising Diffusion Probabilistic Model Approach" Bioengineering 11, no. 11: 1170. https://doi.org/10.3390/bioengineering11111170
APA StyleJeon, Y.-J., Nam, K. M., Park, S.-E., & Baek, H.-M. (2024). Improving Brain Metabolite Detection with a Combined Low-Rank Approximation and Denoising Diffusion Probabilistic Model Approach. Bioengineering, 11(11), 1170. https://doi.org/10.3390/bioengineering11111170