Advertisement

Quantification of Metabolites in Magnetic Resonance Spectroscopic Imaging Using Machine Learning

  • Dhritiman DasEmail author
  • Eduardo Coello
  • Rolf F. Schulte
  • Bjoern H. Menze
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10435)

Abstract

Magnetic Resonance Spectroscopic Imaging (MRSI) is a clinical imaging modality for measuring tissue metabolite levels in-vivo. An accurate estimation of spectral parameters allows for better assessment of spectral quality and metabolite concentration levels. The current gold standard quantification method is the LCModel - a commercial fitting tool. However, this fails for spectra having poor signal-to-noise ratio (SNR) or a large number of artifacts. This paper introduces a framework based on random forest regression for accurate estimation of the output parameters of a model based analysis of MR spectroscopy data. The goal of our proposed framework is to learn the spectral features from a training set comprising of different variations of both simulated and in-vivo brain spectra and then use this learning for the subsequent metabolite quantification. Experiments involve training and testing on simulated and in-vivo human brain spectra. We estimate parameters such as concentration of metabolites and compare our results with that from the LCModel.

References

  1. 1.
    Pedrosa de Barros, N., McKinley, R., Wiest, R., Slotboom, J.: Improving labeling efficiency in automatic quality control of MRSI data. Magnetic Resonance in Medicine (2017). http://dx.doi.org/10.1002/mrm.26618
  2. 2.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001). http://dx.doi.org/10.1023/A:1010933404324 CrossRefzbMATHGoogle Scholar
  3. 3.
    Kelm, B.M., Kaster, F.O., Henning, A., Weber, M.A., Bachert, P., Boesiger, P., Hamprecht, F.A., Menze, B.H.: Using spatial prior knowledge in the spectral fitting of MRS images. NMR Biomed. 25(1), 1–13 (2012)CrossRefGoogle Scholar
  4. 4.
    Menze, B.H., Kelm, B.M., Weber, M.A., Bachert, P., Hamprecht, F.A.: Mimicking the human expert: pattern recognition for an automated assessment of data quality in MR spectroscopic images. Magn. Reson. Med. 59(6), 1457–1466 (2008). http://dx.doi.org/10.1002/mrm.21519 CrossRefGoogle Scholar
  5. 5.
    Provencher, S.W.: Estimation of metabolite concentrations from localized in vivo proton NMR spectra. Magn. Reson. Med. 6, 672–679 (1993)CrossRefGoogle Scholar
  6. 6.
    de Graaf, R.A.: In Vivo NMR Spectroscopy: Principles and Techniques, 2nd edn. Wiley, Chichester (2013)Google Scholar
  7. 7.
    Schulte, R.F., Lange, T., Beck, J., Meier, D., Boesiger, P.: Improved two-dimensional J-resolved spectroscopy. NMR Biomed. 19(2), 264–270 (2006)CrossRefGoogle Scholar
  8. 8.
    Vanhamme, L., van den Boogaart, A., Huffel, S.V.: Improved method for accurate and efficient quantification of MRS data with use of prior knowledge. J. Magn. Reson. 129(1), 35–43 (1997). http://www.sciencedirect.com/science/article/pii/S1090780797912441 CrossRefGoogle Scholar
  9. 9.
    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 (2011). https://dx.doi.org/10.1002/mrm.22579 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Dhritiman Das
    • 1
    • 3
    Email author
  • Eduardo Coello
    • 2
    • 3
  • Rolf F. Schulte
    • 3
  • Bjoern H. Menze
    • 1
  1. 1.Department of Computer ScienceTechnical University of MunichMunichGermany
  2. 2.Department of PhysicsTechnical University of MunichMunichGermany
  3. 3.GE Global Research EuropeMunichGermany

Personalised recommendations