Comparison of Black Box Implementations of Two Algorithms of Processing of NMR Spectra, Gaussian Mixture Model and Singular Value Decomposition

M. Staniszewski, F. Binczyk, A. Skorupa, L. Boguszewicz, M. Sokol, J. Polanska, A. Polanski

2015

Abstract

Analysis of NMR spectra is a multi-stage computational process performed with the use of appropriately chosen sequence of algorithms. Initial stages of this process, called pre-processing, including filtering, baseline correction, phase correction and removal of unwanted components, are aimed at improving the quality of NMR spectral signal by rejection of noise, removing unnecessary spectral components and irregularities. After pre-processing the basic operations on NMR spectra are aimed at estimation of levels of certain metabolites by analysis of appropriate structural properties of NMR spectral signals. In this paper authors present design and implementation of two signals modelling methods. The first one is based on singular value decomposition of the induction decay signal. The second is done with use of mixture model constructed for frequency spectrum. Authors present all assumption that need to be satisfied and processing steps that must be performed before final analysis. The methods studied in the paper are implemented under the black - box assumption; i.e., prior knowledge of parameters of metabolites in the spectra is not used. As a second part of the project authors present a comparison of obtained result with popular modelling techniques and software LCmodel and Tarquin, based on experimental phantom dataset. Comparisons between different methods are based on the commonly used quality indexes, mean squared errors corresponding to levels of detected metabolites and specificities and sensitivities of the process of detection of metabolites. Using the presented comparisons we authors are able to characterize advantages and drawbacks of the studied approaches.

References

  1. Beer R., Ormondt D., Pijnappel W.: Quantification of 1-D and 2-D magnetic resonance time domain signals, Pure &Appl. Chem., Vol. 64, No. 6, pp: 815-823, (1992).
  2. Behar, K. L., Rothman, D. L., Spencer, D. D., Petroff, O.A.:. Analysis of macromolecule resonances in 1H NMR spectra of human brain. Magn. Reson. Med. 32 (3), 294-302, (1994).
  3. Binczyk F. Tarnawski R. Polanska J: Mixture model of NMR and its application to diagnosis and treatment of brain cancer. Archives of Control Science 2010, 20(4), pp:457-472, (2010).
  4. Dempster A.: Maximum likelihood from in- complete data via the EM algorithm. Journal of the Royal Statistical Society B, 39(1), pp: 1-22 (1977).
  5. McLachlan G., Peel D: Finite Mixture Models, ISBN: 047165406X, 9780471654063 Wiley & Sons (2000).
  6. Graff R: In vivo NMR spectroscopy. Principles and Techniques, Wiley & Sons, ISBN: 978-0-470-02670-0 (2007).
  7. Gunther H.: NMR SPECTROSCOPY Basic Principles, Concepts, and Applications in Chemistry, XIII-XIV, 241-243, ISBN: 978-0-471-95201- (1992).
  8. Hofmann, L., Slotboom, J., Boesch, C., Kreis, R.,: Characterization of the macromolecule baseline in localized (1)H-MR spectra of human brain. Magn. Reson. Med. 46 (5), 855-863 (2001).
  9. Jacobsen N: NMR SPECTROSCOPY EXPLAINED Simplified Theory, Applications and Examples for Organic Chemistry and Structural Biology, 4-8, 118- 134, ISBN: 978-0-471-73096-5 (2007).
  10. Krone M., Klawonn F., Luhrs T., Ritter C.: Identification of Nuclear Magnetic Resonance Signals via Gaussian Mixture Decomposition, Advances in Intelligent Data Analysis X, Lecture Notes in Computer Science Volume 7014, 2011, pp 234-245, (2011).
  11. Lupu D., Todor D: A singular value decomposition based algorithm for multicomponent exponential fitting of NMR relaxation signals, Chemometrics and Intelligent Laboratory Systems 29, pp: 11-17 (1995).
  12. Millar P.: Using the Bayesian Information Criterion to judge models and statistical significance”, North American Stata Users' Group Meetings (2006).
  13. Müller N.; Jerschow A. Nuclear Spin Noise Imaging. Proc. Natl. Acad. Sci. U.S.A. 103, 6790-6792 (2006).
  14. Savitzky A., Golay M.: Smoothing and differentiation of data by Simplified least squares procedures. Analytical Chemistry, 36(8), 1627-1639 (1964).
  15. Polanski A., Kimmel M.: Bioinformatics. Springer-Verlag New York, Inc., Secaucus, NJ, USA, ISBN: 978- 3540241669 pp: 43-45 (2007).
  16. Provencher S.: Automated quantitation of localized 1HNMR spectra in vivo: Capabilities and limitations., Proc SMR, 1952 (1995).
  17. Provencher S.: Estimation of metabolite concentrations from localized in vivo proton NMR spectra. Magn. Reson. Med.; 30: 672-679, (1993).
  18. Weinreb, J. C., Brateman, L., Babcock, E. E., Maravilla, K.R., Cohen, J.M., Horner, S.D.,: Chemical shift artifact in clinical magnetic resonance images at 0.35 T. AJR Am. J. Roentgenol. 145 (1), 183-185, (1985).
  19. Wilson, M., Reynolds, G., Kauppinen R. A., Arvanitis T. N., Peet A. C.: A constrained least-squares approach to the automated quantitation of in vivo 1H magnetic resonance spectroscopy data. Magn. Reson. Med. 65 (1), 1-12, (2010).
Download


Paper Citation


in Harvard Style

Staniszewski M., Binczyk F., Skorupa A., Boguszewicz L., Sokol M., Polanska J. and Polanski A. (2015). Comparison of Black Box Implementations of Two Algorithms of Processing of NMR Spectra, Gaussian Mixture Model and Singular Value Decomposition . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015) ISBN 978-989-758-069-7, pages 57-65. DOI: 10.5220/0005210300570065


in Bibtex Style

@conference{biosignals15,
author={M. Staniszewski and F. Binczyk and A. Skorupa and L. Boguszewicz and M. Sokol and J. Polanska and A. Polanski},
title={Comparison of Black Box Implementations of Two Algorithms of Processing of NMR Spectra, Gaussian Mixture Model and Singular Value Decomposition},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015)},
year={2015},
pages={57-65},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005210300570065},
isbn={978-989-758-069-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015)
TI - Comparison of Black Box Implementations of Two Algorithms of Processing of NMR Spectra, Gaussian Mixture Model and Singular Value Decomposition
SN - 978-989-758-069-7
AU - Staniszewski M.
AU - Binczyk F.
AU - Skorupa A.
AU - Boguszewicz L.
AU - Sokol M.
AU - Polanska J.
AU - Polanski A.
PY - 2015
SP - 57
EP - 65
DO - 10.5220/0005210300570065