Deep learning‐based target metabolite isolation and big data‐driven measurement uncertainty estimation in proton magnetic resonance spectroscopy of the brain

The aim of this study was to develop a method for metabolite quantification with simultaneous measurement uncertainty estimation in deep learning‐based proton magnetic resonance spectroscopy (1H‐MRS).

[1]  Andrew A Maudsley,et al.  Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting , 2019, Magnetic resonance in medicine.

[2]  Hyeonjin Kim,et al.  Intact metabolite spectrum mining by deep learning in proton magnetic resonance spectroscopy of the brain , 2019, Magnetic resonance in medicine.

[3]  Jasper Snoek,et al.  Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[4]  R. Pohmann,et al.  Determination of regional variations and reproducibility in in vivo 1H NMR spectroscopy of the rat brain at 16.4 T , 2011, Magnetic resonance in medicine.

[5]  R Gruetter,et al.  Toward an in vivo neurochemical profile: quantification of 18 metabolites in short-echo-time (1)H NMR spectra of the rat brain. , 1999, Journal of magnetic resonance.

[6]  T. Perry.  Cerebral Amino Acid Pools , 1982 .

[7]  Hyeonjin Kim,et al.  Parameterization of spectral baseline directly from short echo time full spectra in 1H‐MRS , 2017, Magnetic resonance in medicine.

[8]  Anke Henning,et al.  Methodological consensus on clinical proton MRS of the brain: Review and recommendations , 2019, Magnetic resonance in medicine.

[9]  S. Provencher.  Estimation of metabolite concentrations from localized in vivo proton NMR spectra , 1993, Magnetic resonance in medicine.

[10]  E. Hattingen,et al.  Fitting algorithms and baseline correction influence the results of non‐invasive in vivo quantitation of 2‐hydroxyglutarate with 1H‐MRS , 2018, NMR in biomedicine.

[11]  Margarida Julià-Sapé,et al.  Quality of clinical brain tumor MR spectra judged by humans and machine learning tools , 2018, Magnetic resonance in medicine.

[12]  Robin A. de Graaf,et al.  In Vivo NMR Spectroscopy , 2019 .

[13]  Nima Hatami,et al.  Magnetic Resonance Spectroscopy Quantification using Deep Learning , 2018, MICCAI.

[14]  Hamid Dehghani,et al.  Influence of macromolecule baseline on 1H MR spectroscopic imaging reproducibility , 2016, Magnetic resonance in medicine.

[15]  K. Behar,et al.  Analysis of macromolecule resonances in 1H NMR spectra of human brain , 1994, Magnetic resonance in medicine.

[16]  Rolf Gruetter,et al.  Localized short‐echo‐time proton MR spectroscopy with full signal‐intensity acquisition , 2006, Magnetic resonance in medicine.

[17]  Spatially selective RF pulses and the effects of digitization on their performance , 1993, Magnetic resonance in medicine.

[18]  Fawzi Boumezbeur,et al.  Metabolite and macromolecule T1 and T2 relaxation times in the rat brain in vivo at 17.2T , 2016, Magnetic resonance in medicine.

[19]  Roland Kreis,et al.  Deep learning approaches for detection and removal of ghosting artifacts in MR spectroscopy , 2018, Magnetic resonance in medicine.

[20]  Eduard Schreibmann,et al.  A convolutional neural network to filter artifacts in spectroscopic MRI , 2018, Magnetic resonance in medicine.

[21]  Zenon Starčuk,et al.  Quantitation of magnetic resonance spectroscopy signals: the jMRUI software package , 2009 .

[22]  V. Govindaraju,et al.  Proton NMR chemical shifts and coupling constants for brain metabolites , 2000, NMR in biomedicine.

[23]  Hong Wu,et al.  Non-invasive detection of 2-hydroxyglutarate and other metabolites in IDH1 mutant glioma patients using magnetic resonance spectroscopy , 2012, Journal of Neuro-Oncology.

[24]  Roland Kreis,et al.  The trouble with quality filtering based on relative Cramér‐Rao lower bounds , 2016, Magnetic resonance in medicine.

[25]  Bjoern H. Menze,et al.  Quantification of Metabolites in Magnetic Resonance Spectroscopic Imaging Using Machine Learning , 2017, MICCAI.

[26]  Sebastian Raschka,et al.  Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning , 2018, ArXiv.

[27]  R. Gruetter,et al.  In vivo 1H NMR spectroscopy of rat brain at 1 ms echo time , 1999, Magnetic resonance in medicine.

[28]  Steve B. Jiang,et al.  Deep learning can accelerate and quantify simulated localized correlated spectroscopy , 2018, Scientific Reports.

[29]  R. Gruetter,et al.  Methodology of1H NMR spectroscopy of the human brain at very high magnetic fields , 2005, Applied magnetic resonance.

[30]  D. Graveron-Demilly,et al.  Time-domain quantitation of 1H short echo-time signals: background accommodation , 2004, Magnetic Resonance Materials in Physics, Biology and Medicine.

[31]  Dennis W J Klomp,et al.  1H–MRS processing parameters affect metabolite quantification: The urgent need for uniform and transparent standardization , 2017, NMR in biomedicine.

[32]  B. Meier,et al.  Computer Simulations in Magnetic Resonance. An Object-Oriented Programming Approach , 1994 .

[33]  Robin A. de Graaf.  In vivo NMR spectroscopy , 1998 .

[34]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.