Fast quantification of proton magnetic resonance spectroscopic imaging with artificial neural networks

Himanshu Bhat, Balasrinivasa Rao Sajja, Ponnada A. Narayana

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

Accurate quantification of the MRSI-observed regional distribution of metabolites involves relatively long processing times. This is particularly true in dealing with large amount of data that is typically acquired in multi-center clinical studies. To significantly shorten the processing time, an artificial neural network (ANN)-based approach was explored for quantifying the phase corrected (as opposed to magnitude) spectra. Specifically, in these studies radial basis function neural network (RBFNN) was used. This method was tested on simulated and normal human brain data acquired at 3T. The N-acetyl aspartate (NAA)/creatine (Cr), choline (Cho)/Cr, glutamate + glutamine (Glx)/Cr, and myo-inositol (mI)/Cr ratios in normal subjects were compared with the line fitting (LF) technique and jMRUI-AMARES analysis, and published values. The average NAA/Cr, Cho/Cr, Glx/Cr and mI/Cr ratios in normal controls were found to be 1.58 ± 0.13, 0.9 ± 0.08, 0.7 ± 0.17 and 0.42 ± 0.07, respectively. The corresponding ratios using the LF and jMRUI-AMARES methods were 1.6 ± 0.11, 0.95 ± 0.08, 0.78 ± 0.18, 0.49 ± 0.1 and 1.61 ± 0.15, 0.78 ± 0.07, 0.61 ± 0.18, 0.42 ± 0.13, respectively. These results agree with those published in literature. Bland-Altman analysis indicated an excellent agreement and minimal bias between the results obtained with RBFNN and other methods. The computational time for the current method was 15 s compared to approximately 10 min for the LF-based analysis.

Original languageEnglish (US)
Pages (from-to)110-122
Number of pages13
JournalJournal of Magnetic Resonance
Volume183
Issue number1
DOIs
StatePublished - Nov 1 2006

Fingerprint

creatine
proton magnetic resonance
Creatine
Protons
Magnetic Resonance Imaging
Nuclear magnetic resonance
Neural networks
Imaging techniques
inositols
aspartates
choline
Inositol
Choline
glutamine
glutamates
metabolites
Metabolites
Processing
Glutamine
brain

Keywords

  • Artificial neural networks
  • Magnetic resonance spectroscopic imaging
  • Parametric spectral analysis
  • Radial basis function neural network

ASJC Scopus subject areas

  • Biophysics
  • Biochemistry
  • Nuclear and High Energy Physics
  • Condensed Matter Physics

Cite this

Fast quantification of proton magnetic resonance spectroscopic imaging with artificial neural networks. / Bhat, Himanshu; Sajja, Balasrinivasa Rao; Narayana, Ponnada A.

In: Journal of Magnetic Resonance, Vol. 183, No. 1, 01.11.2006, p. 110-122.

Research output: Contribution to journalArticle

@article{a04ec50f68104b0a87478362f445e511,
title = "Fast quantification of proton magnetic resonance spectroscopic imaging with artificial neural networks",
abstract = "Accurate quantification of the MRSI-observed regional distribution of metabolites involves relatively long processing times. This is particularly true in dealing with large amount of data that is typically acquired in multi-center clinical studies. To significantly shorten the processing time, an artificial neural network (ANN)-based approach was explored for quantifying the phase corrected (as opposed to magnitude) spectra. Specifically, in these studies radial basis function neural network (RBFNN) was used. This method was tested on simulated and normal human brain data acquired at 3T. The N-acetyl aspartate (NAA)/creatine (Cr), choline (Cho)/Cr, glutamate + glutamine (Glx)/Cr, and myo-inositol (mI)/Cr ratios in normal subjects were compared with the line fitting (LF) technique and jMRUI-AMARES analysis, and published values. The average NAA/Cr, Cho/Cr, Glx/Cr and mI/Cr ratios in normal controls were found to be 1.58 ± 0.13, 0.9 ± 0.08, 0.7 ± 0.17 and 0.42 ± 0.07, respectively. The corresponding ratios using the LF and jMRUI-AMARES methods were 1.6 ± 0.11, 0.95 ± 0.08, 0.78 ± 0.18, 0.49 ± 0.1 and 1.61 ± 0.15, 0.78 ± 0.07, 0.61 ± 0.18, 0.42 ± 0.13, respectively. These results agree with those published in literature. Bland-Altman analysis indicated an excellent agreement and minimal bias between the results obtained with RBFNN and other methods. The computational time for the current method was 15 s compared to approximately 10 min for the LF-based analysis.",
keywords = "Artificial neural networks, Magnetic resonance spectroscopic imaging, Parametric spectral analysis, Radial basis function neural network",
author = "Himanshu Bhat and Sajja, {Balasrinivasa Rao} and Narayana, {Ponnada A.}",
year = "2006",
month = "11",
day = "1",
doi = "10.1016/j.jmr.2006.08.004",
language = "English (US)",
volume = "183",
pages = "110--122",
journal = "Journal of Magnetic Resonance",
issn = "1090-7807",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - Fast quantification of proton magnetic resonance spectroscopic imaging with artificial neural networks

AU - Bhat, Himanshu

AU - Sajja, Balasrinivasa Rao

AU - Narayana, Ponnada A.

PY - 2006/11/1

Y1 - 2006/11/1

N2 - Accurate quantification of the MRSI-observed regional distribution of metabolites involves relatively long processing times. This is particularly true in dealing with large amount of data that is typically acquired in multi-center clinical studies. To significantly shorten the processing time, an artificial neural network (ANN)-based approach was explored for quantifying the phase corrected (as opposed to magnitude) spectra. Specifically, in these studies radial basis function neural network (RBFNN) was used. This method was tested on simulated and normal human brain data acquired at 3T. The N-acetyl aspartate (NAA)/creatine (Cr), choline (Cho)/Cr, glutamate + glutamine (Glx)/Cr, and myo-inositol (mI)/Cr ratios in normal subjects were compared with the line fitting (LF) technique and jMRUI-AMARES analysis, and published values. The average NAA/Cr, Cho/Cr, Glx/Cr and mI/Cr ratios in normal controls were found to be 1.58 ± 0.13, 0.9 ± 0.08, 0.7 ± 0.17 and 0.42 ± 0.07, respectively. The corresponding ratios using the LF and jMRUI-AMARES methods were 1.6 ± 0.11, 0.95 ± 0.08, 0.78 ± 0.18, 0.49 ± 0.1 and 1.61 ± 0.15, 0.78 ± 0.07, 0.61 ± 0.18, 0.42 ± 0.13, respectively. These results agree with those published in literature. Bland-Altman analysis indicated an excellent agreement and minimal bias between the results obtained with RBFNN and other methods. The computational time for the current method was 15 s compared to approximately 10 min for the LF-based analysis.

AB - Accurate quantification of the MRSI-observed regional distribution of metabolites involves relatively long processing times. This is particularly true in dealing with large amount of data that is typically acquired in multi-center clinical studies. To significantly shorten the processing time, an artificial neural network (ANN)-based approach was explored for quantifying the phase corrected (as opposed to magnitude) spectra. Specifically, in these studies radial basis function neural network (RBFNN) was used. This method was tested on simulated and normal human brain data acquired at 3T. The N-acetyl aspartate (NAA)/creatine (Cr), choline (Cho)/Cr, glutamate + glutamine (Glx)/Cr, and myo-inositol (mI)/Cr ratios in normal subjects were compared with the line fitting (LF) technique and jMRUI-AMARES analysis, and published values. The average NAA/Cr, Cho/Cr, Glx/Cr and mI/Cr ratios in normal controls were found to be 1.58 ± 0.13, 0.9 ± 0.08, 0.7 ± 0.17 and 0.42 ± 0.07, respectively. The corresponding ratios using the LF and jMRUI-AMARES methods were 1.6 ± 0.11, 0.95 ± 0.08, 0.78 ± 0.18, 0.49 ± 0.1 and 1.61 ± 0.15, 0.78 ± 0.07, 0.61 ± 0.18, 0.42 ± 0.13, respectively. These results agree with those published in literature. Bland-Altman analysis indicated an excellent agreement and minimal bias between the results obtained with RBFNN and other methods. The computational time for the current method was 15 s compared to approximately 10 min for the LF-based analysis.

KW - Artificial neural networks

KW - Magnetic resonance spectroscopic imaging

KW - Parametric spectral analysis

KW - Radial basis function neural network

UR - http://www.scopus.com/inward/record.url?scp=33750633616&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750633616&partnerID=8YFLogxK

U2 - 10.1016/j.jmr.2006.08.004

DO - 10.1016/j.jmr.2006.08.004

M3 - Article

C2 - 16949319

AN - SCOPUS:33750633616

VL - 183

SP - 110

EP - 122

JO - Journal of Magnetic Resonance

JF - Journal of Magnetic Resonance

SN - 1090-7807

IS - 1

ER -