PURPOSE: A supervised deep learning (DL) approach for frequency and phase correction (FPC) of MRS data recently showed encouraging results, but obtaining transients with labels for supervised learning is challenging. This work investigates the feasibility and efficiency of unsupervised deep learning-based FPC. METHODS: Two novel deep learning-based FPC methods (deep learning-based Cr referencing and deep learning-based spectral registration), which use a priori physics domain knowledge, are presented. The proposed networks were trained, validated, and evaluated using simulated, phantom, and publicly accessible in vivo MEGA-edited MRS data. The performance of our proposed FPC methods was compared with other generally used FPC methods, in terms of precision and time efficiency. A new measure was proposed in this study to evaluate the FPC method performance. The ability of each of our methods to carry out FPC at varying SNR levels was evaluated. A Monte Carlo study was carried out to investigate the performance of our proposed methods. RESULTS: The validation using low-SNR manipulated simulated data demonstrated that the proposed methods could perform FPC comparably with other methods. The evaluation showed that the deep learning-based spectral registration over a limited frequency range method achieved the highest performance in phantom data. The applicability of the proposed method for FPC of GABA-edited in vivo MRS data was demonstrated. Our proposed networks have the potential to reduce computation time significantly. CONCLUSIONS: The proposed physics-informed deep neural networks trained in an unsupervised manner with complex data can offer efficient FPC of large MRS data in a shorter time.

Department of Biomedical Engineering Brno University of Technology Brno Czech Republic

Institute of Scientific Instruments of the Czech Academy of Sciences Brno Czech Republic

Zobrazit více v PubMed

de Graaf RA. In vivo NMR spectroscopy. Vivo NMR Spectrosc. 2019;560:375‐437.

Hui SCN, Mikkelsen M, Zöllner HJ, et al. Frequency drift in MR spectroscopy at 3 T. Neuroimage. 2021;241:118430. PubMed PMC

Near J, Edden R, Evans CJ, Harris A, Jezzard P. Frequency and phase drift correction of magnetic resonance spectroscopy data by spectral registration in the time domain. Magn Reson Med. 2015;50:44‐50. PubMed PMC

Near J, Harris AD, Juchem C, et al. Preprocessing, analysis and quantification in single‐voxel magnetic resonance spectroscopy: experts' consensus recommendations. NMR Biomed. 2021;34:e4257. PubMed PMC

Wiegers EC, Philips BWJ, Heerschap A, van der Graaf M. Automatic frequency and phase alignment of in vivo J‐difference‐edited MR spectra by frequency domain correlation. MAGMA. 2017;30:537‐544. PubMed PMC

Keating B, Deng W, Roddey JC, et al. Prospective motion correction for single‐voxel 1H MR spectroscopy. Magn Reson Med. 2010;64:672‐679. PubMed PMC

Tapper S, Mikkelsen M, Dewey BE, et al. Frequency and phase correction of J‐difference edited MR spectra using deep learning. Magn Reson Med. 2021;85:1755‐1765. PubMed PMC

Helms G, Piringer A. Restoration of motion‐related signal loss and line‐shape deterioration of proton MR spectra using the residual water as intrinsic reference. Magn Reson Med. 2001;46:395‐400. PubMed

Wilson M. Robust retrospective frequency and phase correction for single‐voxel MR spectroscopy. Magn Reson Med. 2019;81:2878‐2886. PubMed

Mikkelsen M, Tapper S, Near J, Mostofsky SH, Edden RAE. Correcting frequency and phase offsets in MRS data using robust spectral registration. NMR Biomed. 2020;33:e4368. PubMed PMC

Ernst T, Li J. A novel phase and frequency navigator for proton magnetic resonance spectroscopy using water‐suppression cycling. Magn Reson Med. 2011;65:13‐17. PubMed PMC

Waddell KW, Avison MJ, Joers JM, Gore JC. A practical guide to robust detection of GABA in human brain by J‐difference spectroscopy at 3 T using a standard volume coil. Magn Reson Imaging. 2007;25:1032‐1038. PubMed PMC

Goodfellow I, Bengio Y. Courville A. Deep Learning. MIT Press; 2016.

Lundervold AS, Lundervold A. An overview of deep learning in medical imaging focusing on MRI. Z Med Phys. 2019;29:102–27. PubMed

Gurbani SS, Sheriff S, Maudsley AA, Shim H, Cooper LAD. Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting. Magn Reson Med. 2019;81:3346‐3357. PubMed PMC

Lee HH. Intact metabolite spectrum mining by deep learning in proton magnetic resonance spectroscopy of the brain. Magn Reson Med. 2019;82:33‐48. PubMed

Kreis R, Kyathanahally SP. Deep learning approaches for detection and removal of ghosting artifacts in MR spectroscopy. Magn Reson Med. 2018;863:851‐863. PubMed

Lee H, Lee HH, Kim H. Reconstruction of spectra from truncated free induction decays by deep learning in proton magnetic resonance spectroscopy. Magn Reson Med. 2020;84:559‐568. PubMed

Klukowski P, Augoff M, ZieRba M, Drwal M, Gonczarek A, Walczak MJ. NMRNet: a deep learning approach to automated peak picking of protein NMR spectra. Bioinformatics. 2018;34:2590‐2597. PubMed

Iqbal Z, Nguyen D, Hangel G, Motyka S, Bogner W, Jiang S. Super‐resolution 1H magnetic resonance spectroscopic imaging utilizing deep learning. Front Oncol. 2019;9:1‐13. PubMed PMC

Gurbani SS, Schreibmann E, Maudsley AA, et al. A convolutional neural network to filter artifacts in spectroscopic MRI. Magn Reson Med. 2018;80:1765‐1775. PubMed PMC

Ma DJ, Le HAM, Ye Y, et al. MR spectroscopy frequency and phase correction using convolutional neural networks. Magn Reson Med. 2022;87:1700‐1710. PubMed

Zhang Z, Zha H. Linear low‐rank approximation and nonlinear dimensionality reduction. Sci China, Ser A Math. 2004;47:908‐920.

Melas‐Kyriazi L. The Mathematical Foundations of Manifold Learning. arXiv:2011.01307. 2020.

Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science. 2006;313:504‐507. PubMed

Mikkelsen M, Barker PB, Bhattacharyya PK, et al. Big GABA: edited MR spectroscopy at 24 research sites. Neuroimage. 2017;159:32‐45. PubMed PMC

Mikkelsen M, Rimbault DL, Barker PB, et al. Big GABA II: water‐referenced edited MR spectroscopy at 25 research sites. Neuroimage. 2019;191:537‐548. PubMed PMC

Edden RAE, Puts NAJ, Harris AD, Barker PB, Evans CJ. Gannet: a batch‐processing tool for the quantitative analysis of gamma‐aminobutyric acid‐edited MR spectroscopy spectra. J Magn Reson Imaging. 2014;40:1445‐1452. PubMed PMC

Kreis R, Cudalbu C, De GRA, et al. Terminology and concepts for the characterization of in vivo MR spectroscopy methods and MR spectra: background and experts' consensus recommendations. NMR Biomed. 2021;34:e4347. PubMed PMC

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. PubMed

Tkáč I, Starčuk Z, Choi I‐Y, Gruetter R. In vivo 1 H NMR spectroscopy of rat brain at 1 ms echo time. Magn Reson Med. 1999;41:649‐656. PubMed

Srivastava N, Hinton G, Krizhevsky A, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15:1929‐1958.

Fukushima K. Neocognitron: a self‐organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern. 1980;36:193–202. PubMed

Schmidhuber, J. (2014). Deep learning in neural networks: An overview. Neural Networks, 61, 85–117. 10.1016/j.neunet.2014.09.003 PubMed DOI

Sokolenko S, Jézéquel T, Hajjar G, Farjon J, Akoka S, Giraudeau P. Robust 1D NMR lineshape fitting using real and imaginary data in the frequency domain. J Magn Reson. 2019;298:91‐100. PubMed

Brunton SL, Kutz JN. Data‐driven science and engineering: Cambridge University Press; 2019.

Bisong E. Google Colaboratory. New York: Cambridge University Press; 2019.

Paszke A, Gross S, Massa F, et al. PyTorch: an imperative style, high‐performance deep learning library. Adv Neural Inf Process Syst. 2019;32:1‐12.

Falcon W. PyTorch lightning. GitHub. https://github.com/PyTorchLightning/pytorch‐lightning.

Falkner S, Klein A, Hutter F. BOHB: Robust and Efficient Hyperparameter Optimization at Scale. In: 35th International Conference on Machine Learning, PMLR; 2018:1437‐1446. Accessed March 30, 2019.

Liaw R, Liang E, Nishihara R, Moritz P, Gonzalez JE, Tune Stoica I.: a research platform for distributed model selection and training. 2018. https://arxiv.org/abs/1807.05118v1. Accessed January 25, 2022.

Kingma DP, Ba JL. Adam: a method for stochastic optimization. In: Proceedings of the Third International Conference on Learning, San Diego, California, 2015.

Simpson R, Devenyi GA, Jezzard P, Hennessy TJ, Near J. Advanced processing and simulation of MRS data using the FID appliance (FID‐A)—an open source MATLAB‐based toolkit. Magn Reson Med. 2017;77:23‐33. PubMed

Sun Q, Liu Y, Chua T‐S, Schiele B. Meta‐transfer learning for few‐shot learning. https://github.com/y2l/meta‐transfer‐learning‐tensorflow. Accessed August 15, 2022. PubMed

Grøvik E, Yi D, Iv M, et al. Handling missing MRI sequences in deep learning segmentation of brain metastases: a multicenter study. npj Digit Med. 2021;41:1‐7. PubMed PMC

Liu Z, Mao H, Wu C‐Y, et al. A ConvNet for the 2020s. 2022. https://arxiv.org/abs/2201.03545v1. Accessed February 11, 2022.

Evans CJ, Puts NAJ, Robson SE, et al. Subtraction artifacts and frequency (Mis‐)alignment in J‐difference GABA editing. J Magn Reson Imaging. 2013;38:970‐975. PubMed