TensorFit: A torch-based tool for ultrafast metabolite fitting of large MRSI data sets.
3D MRSI
GPU optimization
deep learning frameworks
metabolite fitting
torch auto-differentiation
Journal
Magnetic resonance in medicine
ISSN: 1522-2594
Titre abrégé: Magn Reson Med
Pays: United States
ID NLM: 8505245
Informations de publication
Date de publication:
12 Mar 2024
12 Mar 2024
Historique:
revised:
21
02
2024
received:
29
09
2023
accepted:
26
02
2024
medline:
12
3
2024
pubmed:
12
3
2024
entrez:
12
3
2024
Statut:
aheadofprint
Résumé
To introduce a tool (TensorFit) for ultrafast and robust metabolite fitting of MRSI data based on Torch's auto-differentiation and optimization framework. TensorFit was implemented in Python based on Torch's auto-differentiation to fit individual metabolites in MRS spectra. The underlying time domain and/or frequency domain fitting model is based on a linear combination of metabolite spectroscopic response. The computational time efficiency and accuracy of TensorFit were tested on simulated and in vivo MRS data and compared against TDFDFit and QUEST. TensorFit demonstrates a significant improvement in computation speed, achieving a 165-times acceleration compared with TDFDFit and 115 times against QUEST. TensorFit showed smaller percentual errors on simulated data compared with TDFDFit and QUEST. When tested on in vivo data, it performed similarly to TDFDFit with a 2% better fit in terms of mean squared error while obtaining a 169-fold speedup. TensorFit enables fast and robust metabolite fitting in large MRSI data sets compared with conventional metabolite fitting methods. This tool could boost the clinical applicability of large 3D MRSI by enabling the fitting of large MRSI data sets within computation times acceptable in a clinical environment.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : European Union's Horizon 2020 research and innovation programme
ID : 813120
Organisme : Schweizerische Nationalfonds zur Förderung der wissenschaftlichen Forschung
ID : 182569
Organisme : Schweizerische Nationalfonds zur Förderung der wissenschaftlichen Forschung
ID : 207997
Informations de copyright
© 2024 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals LLC on behalf of International Society for Magnetic Resonance in Medicine.
Références
Lukas L, Devos A, Suykens JAK, et al. Brain tumor classification based on long echo proton MRS signals. Artif Intell Med. 2004;31:73-89.
Tate AR, Griffiths JR, Martínez-Pérez I, et al. Towards a method for automated classification of 1H MRS spectra from brain tumours. NMR Biomed. 1998;11:177-191.
Negendank W. Studies of human tumors by MRS: a review. NMR Biomed. 1992;5:303-324.
Villanueva-Meyer JE, Mabray MC, Cha S. Current clinical brain tumor imaging. Neurosurgery. 2017;81:397-415.
Lichy MP, Plathow C, Schulz-Ertner D, Kauczor HU, Schlemmer HP. Follow-up gliomas after radiotherapy: 1H MR spectroscopic imaging for increasing diagnostic accuracy. Neuroradiology. 2005;47:826-834. doi:10.1007/s00234-005-1434-0
Horská A, Barker PB. Imaging of brain tumors: MR spectroscopy and metabolic imaging. Neuroimaging Clin. 2010;20:293-310.
Thust SC, van den Bent MJ, Smits M. Pseudoprogression of brain tumors. J Magn Reson Imaging. 2018;48:571-589.
van der Graaf M. In vivo magnetic resonance spectroscopy: basic methodology and clinical applications. Eur Biophys J. 2010;39:527-540.
Kreis R. Issues of spectral quality in clinical 1H-magnetic resonance spectroscopy and a gallery of artifacts. NMR Biomed. 2004;17:361-381. doi:10.1002/NBM.891
Gruetter R, Boesch C. Fast, noniterative shimming of spatially localized signals. In vivo analysis of the magnetic field along axes. J Magn Reson. 1992;96:323-334. doi:10.1016/0022-2364(92)90085-L
Juchem C, Nixon TW, Diduch P, Rothman DL, Starewicz P, de Graaf RA. Dynamic shimming of the human brain at 7 tesla. Concepts Magn Reson Part B Magn Reson Eng. 2010;37B:116-128. doi:10.1002/CMR.B.20169
Van Vaals JJ, Bergman AH. Optimization of eddy-current compensation. J Magn Reson. 1990;90:52-70. doi:10.1016/0022-2364(90)90365-G
Ebel A, Soher BJ, Maudsley AA. Assessment of 3D proton MR echo-planar spectroscopic imaging using automated spectral analysis. Magn Reson Med. 2001;46:1072-1078.
Ebel A, Maudsley AA. Improved spectral quality for 3D MR spectroscopic imaging using a high spatial resolution acquisition strategy. Magn Reson Imaging. 2003;21:113-120.
Weng G, Radojewski P, Sheriff S, et al. SLOW: a novel spectral editing method for whole-brain MRSI at ultra high magnetic field. Magn Reson Med. 2022;88:53-70.
Klauser A, Strasser B, Bogner W, et al. ECCENTRIC: a fast and unrestrained approach for high-resolution in vivo metabolic imaging at ultra-high field MR. arXiv Prepr arXiv230513822 2023.
Provencher SW. Estimation of metabolite concentrations from localized in vivo proton NMR spectra. Magn Reson Med. 1993;30:672-679.
Wilson M, Reynolds G, Kauppinen RA, Arvanitis TN, Peet AC. A constrained least-squares approach to the automated quantitation of in vivo 1H magnetic resonance spectroscopy data. Magn Reson Med. 2011;65:1-12.
Ratiney H, Sdika M, Coenradie Y, Cavassila S, van Ormondt D, Graveron-Demilly D. Time-domain semi-parametric estimation based on a metabolite basis set. NMR Biomed. 2005;18:1-13.
Slotboom J, Boesch C, Kreis R. Versatile frequency domain fitting using time domain models and prior knowledge. Magn Reson Med. 1998;39:899-911. doi:10.1002/MRM.1910390607
Binczyk F, Marczyk M, Polanska J. Mixture model based efficient method for magnetic resonance spectra quantification. Proceedings of the Bioinformatics and Biomedical Engineering Third International Conference, 2015. Springer International Publishing; 2015:406-417.
Das D, Coello E, Schulte RF, Menze BH. Quantification of metabolites in magnetic resonance spectroscopic imaging using machine learning. Proceedings of the 20th International Conference of Medical Image Computing and Computer Assisted Intervention. Springer International Publishing; 2017:462-470.
Hatami N, Sdika M, Ratiney H. Magnetic resonance spectroscopy quantification using deep learning. Proceedings of the 21st International Conference of Medical Image Computing and Computer Assisted Intervention - MICCAI 2018. Vol 2018. Springer International Publishing; 2018:467-475.
Rizzo R, Dziadosz M, Kyathanahally SP, Shamaei A, Kreis R. Quantification of MR spectra by deep learning in an idealized setting: investigation of forms of input, network architectures, optimization by ensembles of networks, and training bias. Magn Reson Med. 2023;89:1707-1727.
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.
Shamaei A, Starcukova J, Starcuk Z Jr. Physics-informed deep learning approach to quantification of human brain metabolites from magnetic resonance spectroscopy data. Comput Biol Med. 2023;158:106837.
Rizzo R, Dziadosz M, Kyathanahally SP, Reyes M, Kreis R. Reliability of quantification estimates in MR spectroscopy: CNNs vs traditional model fitting. Proceedings of the 25th International Conference on Medical Image Computing and Computer-Assisted Intervention - MICCAI 2022. Springer International Publishing; 2022:715-724.
Paszke A, Gross S, Massa F, et al. PyTorch: an imperative style, high-performance deep learning library. In: Wallach H, Larochelle H, Beygelzimer A, d'Alché-Buc F, Fox E, Garnett R, eds. Advances in Neural Information Processing Systems 32. Curran Associates, Inc; 2019:8024-8035 http://papers.neurips.cc/paper/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf
Bruckner F, Koraltan S, Abert C, Suess D. Magnum.np-a PyTorch based GPU enhanced finite difference micromagnetic simulation framework for high level development and inverse design. Sci Rep. 2023;13:12054.
Bosch D, Scheffler K. FastPtx: a versatile toolbox for rapid, joint design of pTx RF and gradient pulses using Pytorch's autodifferentiation. MAGMA; 2024;37(1):127-138.
Feinman R. Pytorch-Minimize: a Library for Numerical Optimization with Autograd. URL: https://github.com/rfeinman/pytorch-minimize. 2021.
Cavassila S, Deval S, Huegen C, Van Ormondt D, Graveron-Demilly D. Cramer-Rao bound expressions for parametric estimation of overlapping peaks: influence of prior knowledge. J Magn Reson. 2000;143:311-320.
Cavassila S, Deval S, Huegen C, Van Ormondt D, Graveron-Demilly D. Cramér-Rao bounds: an evaluation tool for quantitation. NMR Biomed. 2001;14:278-283.
Chong DGQ, Kreis R, Bolliger CS, Boesch C, Slotboom J. Two-dimensional linear-combination model fitting of magnetic resonance spectra to define the macromolecule baseline using FiTAID, a fitting tool for arrays of interrelated datasets. Magn Reson Mater Phys Biol Med. 2011;24:147-164.
Borbath T, Murali-Manohar S, Dorst J, Wright AM, Henning A. ProFit-1D-a 1D fitting software and open-source validation data sets. Magn Reson Med. 2021;86:2910-2929.
de Barros N, McKinley R, Knecht U, Wiest R, Slotboom J. Automatic quality control in clinical 1H MRSI of brain cancer. NMR Biomed. 2016;29:563-575.
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.
Levenberg K. A method for the solution of certain non-linear problems in least squares. Q Appl Math. 1944;2:164-168.
Golub GH, Pereyra V. The differentiation of pseudo-inverses and nonlinear least squares problems whose variables separate. SIAM J Numer Anal. 1973;10:413-432.
Hestenes MR, Stiefel E. Methods of conjugate gradients for solving linear systems. J Res Natl Bur Stand. 1934;49:409-436.
Marjańska M, Deelchand DK, Kreis R, 2016 ISMRM MRS Study Group Fitting Challenge Team. Results and interpretation of a fitting challenge for MR spectroscopy set up by the MRS study group of ISMRM. Magn Reson Med. 2022;87:11-32.
Riedmiller M, Braun H. A direct adaptive method for faster backpropagation learning: the RPROP algorithm. Proceedings of the IEEE International Conference on Neural Networks. IEEE; 1993:586-591.
Kingma DP, Ba J. Adam: a method for stochastic optimization. arXiv 14126980 2014.
Yao Z, Gholami A, Shen S, Mustafa M, Keutzer K, Mahoney M. Adahessian: an adaptive second order optimizer for machine learning. Proc AAAI Conf Artif Intell. 2021;35:10665-10673.
Liu DC, Nocedal J. On the limited memory BFGS method for large scale optimization. Math Program. 1989;45:503-528.
Starčuk Z, Starčuková J, Štrbák O, Graveron-Demilly D. Simulation of coupled-spin systems in the steady-state free-precession acquisition mode for fast magnetic resonance (MR) spectroscopic imaging. Meas Sci Technol. 2009;20:104033.
Naressi A, Couturier C, Castang I, De Beer R, Graveron-Demilly D. Java-based graphical user interface for MRUI, a software package for quantitation of in vivo/medical magnetic resonance spectroscopy signals. Comput Biol Med. 2001;31:269-286.
Abadi M, Agarwal A, Barham P, et al. Tensorflow: large-scale machine learning on heterogeneous distributed systems. arXiv 160304467 2016.
Bradbury J, Frostig R, Hawkins P, et al. JAX: composable transformations of Python+ NumPy programs. URL: http://github.com/google/jax. 2018.