Deep learning can accelerate and quantify simulated localized correlated spectroscopy
Abstract Nuclear magnetic resonance spectroscopy (MRS) allows for the determination of atomic structures and concentrations of different chemicals in a biochemical sample of interest. MRS is used in vivo clinically to aid in the diagnosis of several pathologies that affect metabolic pathways in the...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Nature Portfolio
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/934dd7114c014eccb332bbe5d449288b |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:934dd7114c014eccb332bbe5d449288b |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:934dd7114c014eccb332bbe5d449288b2021-12-02T17:32:57ZDeep learning can accelerate and quantify simulated localized correlated spectroscopy10.1038/s41598-021-88158-y2045-2322https://doaj.org/article/934dd7114c014eccb332bbe5d449288b2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88158-yhttps://doaj.org/toc/2045-2322Abstract Nuclear magnetic resonance spectroscopy (MRS) allows for the determination of atomic structures and concentrations of different chemicals in a biochemical sample of interest. MRS is used in vivo clinically to aid in the diagnosis of several pathologies that affect metabolic pathways in the body. Typically, this experiment produces a one dimensional (1D) 1H spectrum containing several peaks that are well associated with biochemicals, or metabolites. However, since many of these peaks overlap, distinguishing chemicals with similar atomic structures becomes much more challenging. One technique capable of overcoming this issue is the localized correlated spectroscopy (L-COSY) experiment, which acquires a second spectral dimension and spreads overlapping signal across this second dimension. Unfortunately, the acquisition of a two dimensional (2D) spectroscopy experiment is extremely time consuming. Furthermore, quantitation of a 2D spectrum is more complex. Recently, artificial intelligence has emerged in the field of medicine as a powerful force capable of diagnosing disease, aiding in treatment, and even predicting treatment outcome. In this study, we utilize deep learning to: (1) accelerate the L-COSY experiment and (2) quantify L-COSY spectra. All training and testing samples were produced using simulated metabolite spectra for chemicals found in the human body. We demonstrate that our deep learning model greatly outperforms compressed sensing based reconstruction of L-COSY spectra at higher acceleration factors. Specifically, at four-fold acceleration, our method has less than 5% normalized mean squared error, whereas compressed sensing yields 20% normalized mean squared error. We also show that at low SNR (25% noise compared to maximum signal), our deep learning model has less than 8% normalized mean squared error for quantitation of L-COSY spectra. These pilot simulation results appear promising and may help improve the efficiency and accuracy of L-COSY experiments in the future.Zohaib IqbalDan NguyenMichael Albert ThomasSteve JiangNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Medicine R Science Q |
spellingShingle |
Medicine R Science Q Zohaib Iqbal Dan Nguyen Michael Albert Thomas Steve Jiang Deep learning can accelerate and quantify simulated localized correlated spectroscopy |
description |
Abstract Nuclear magnetic resonance spectroscopy (MRS) allows for the determination of atomic structures and concentrations of different chemicals in a biochemical sample of interest. MRS is used in vivo clinically to aid in the diagnosis of several pathologies that affect metabolic pathways in the body. Typically, this experiment produces a one dimensional (1D) 1H spectrum containing several peaks that are well associated with biochemicals, or metabolites. However, since many of these peaks overlap, distinguishing chemicals with similar atomic structures becomes much more challenging. One technique capable of overcoming this issue is the localized correlated spectroscopy (L-COSY) experiment, which acquires a second spectral dimension and spreads overlapping signal across this second dimension. Unfortunately, the acquisition of a two dimensional (2D) spectroscopy experiment is extremely time consuming. Furthermore, quantitation of a 2D spectrum is more complex. Recently, artificial intelligence has emerged in the field of medicine as a powerful force capable of diagnosing disease, aiding in treatment, and even predicting treatment outcome. In this study, we utilize deep learning to: (1) accelerate the L-COSY experiment and (2) quantify L-COSY spectra. All training and testing samples were produced using simulated metabolite spectra for chemicals found in the human body. We demonstrate that our deep learning model greatly outperforms compressed sensing based reconstruction of L-COSY spectra at higher acceleration factors. Specifically, at four-fold acceleration, our method has less than 5% normalized mean squared error, whereas compressed sensing yields 20% normalized mean squared error. We also show that at low SNR (25% noise compared to maximum signal), our deep learning model has less than 8% normalized mean squared error for quantitation of L-COSY spectra. These pilot simulation results appear promising and may help improve the efficiency and accuracy of L-COSY experiments in the future. |
format |
article |
author |
Zohaib Iqbal Dan Nguyen Michael Albert Thomas Steve Jiang |
author_facet |
Zohaib Iqbal Dan Nguyen Michael Albert Thomas Steve Jiang |
author_sort |
Zohaib Iqbal |
title |
Deep learning can accelerate and quantify simulated localized correlated spectroscopy |
title_short |
Deep learning can accelerate and quantify simulated localized correlated spectroscopy |
title_full |
Deep learning can accelerate and quantify simulated localized correlated spectroscopy |
title_fullStr |
Deep learning can accelerate and quantify simulated localized correlated spectroscopy |
title_full_unstemmed |
Deep learning can accelerate and quantify simulated localized correlated spectroscopy |
title_sort |
deep learning can accelerate and quantify simulated localized correlated spectroscopy |
publisher |
Nature Portfolio |
publishDate |
2021 |
url |
https://doaj.org/article/934dd7114c014eccb332bbe5d449288b |
work_keys_str_mv |
AT zohaibiqbal deeplearningcanaccelerateandquantifysimulatedlocalizedcorrelatedspectroscopy AT dannguyen deeplearningcanaccelerateandquantifysimulatedlocalizedcorrelatedspectroscopy AT michaelalbertthomas deeplearningcanaccelerateandquantifysimulatedlocalizedcorrelatedspectroscopy AT stevejiang deeplearningcanaccelerateandquantifysimulatedlocalizedcorrelatedspectroscopy |
_version_ |
1718380135394050048 |