A Statistical Diagnostic Decision Support Tool Using Magnetic Resonance Spectroscopy Data

  • Evaggelia Tsolaki
  • Evanthia Kousi
  • Eftychia Kapsalaki
  • Ioannis Dimou
  • Kyriaki Theodorou
  • Georgios C. Manikis
  • Constantin Kappas
  • Ioannis Tsougos
Part of the Springer Optimization and Its Applications book series (SOIA, volume 65)


The aim of this study was to develop a practical postprocessing statistical tool for spectroscopic data analysis to successively create an effective noninvasive tool for spectra evaluation and cerebral disease classification. Spectroscopic data were obtained from a total of 112 patients suffering from several brain lesions. The evaluation was based on histological diagnosis, and/or radiological diagnoses and/or medical physicists’ observation. First, calculation of metabolite ratio (NAA/Cr, Cho/Cr, mI/Cr, LL/Cr) means was conducted for each pathological case, and results were compared with the corresponding published data. A Matlab-based algorithm called FA.S.M.A (Fast Spectroscopic Multiple Analysis) with a Graphical User Interface (GUI) was developed, performing nearest mean classification. It is a fast and user-friendly radiological tool which provides fundamental functionality in estimating mean metabolite ratios values during spectroscopy examination. The user can insert the metabolite ratios and obtain the most probable diagnostic class and the corresponding mean spectrum based on published prior knowledge. In future, FA.S.M.A will be extended to enrich more advanced Pattern Recognition techniques and additional machine learning (ML) methods will be implemented in order to provide a more accurate mapping of the input data to facilitate brain tumor classification according to histological subtype. From a clinical point of view, FA.S.M.A will be extended to incorporate quantitative data from other advanced MR-based techniques such as DWI, DTI, and perfusion measurements not only for supporting primary diagnosis of tumor type but also for determining the extent of glioma infiltration with a high degree of spatial resolution.


Magnetic Resonance Spectroscopy Decision Support System Proton Magnetic Resonance Spectroscopy Decision Support Tool Metabolite Ratio 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
  2. 2.
    P.B. Barker, J.D. Glickson, and R.N. Bryan. In vivo magnetic resonance spectroscopy of human brain tumors. Topics in Magnetic Resonance Imaging, 5(2):32, 1993.Google Scholar
  3. 3.
    I.C. Chiang, Y.T. Kuo, C.Y. Lu, K.W. Yeung, W.C. Lin, F.O. Sheu, and G.C. Liu. Distinction between high-grade gliomas and solitary metastases using peritumoral 3-t magnetic resonance spectroscopy, diffusion, and perfusion imagings. Neuroradiology, 46(8):619–627, 2004.CrossRefGoogle Scholar
  4. 4.
    P. Davanzo, K. Yue, M.A. Thomas, T. Belin, J. Mintz, TN Venkatraman, E. Santoro, S. Barnett, and J. McCracken. Proton magnetic resonance spectroscopy of bipolar disorder versus intermittent explosive disorder in children and adolescents. American Journal of Psychiatry, 160(8):1442, 2003.Google Scholar
  5. 5.
    N. De Stefano and M. Filippi. Mr spectroscopy in multiple sclerosis. Journal of Neuroimaging, 17:31S–35S, 2007.CrossRefGoogle Scholar
  6. 6.
    M.K. Demir, A.C. Iplikcioglu, A. Dincer, M. Arslan, and A. Sav. Single voxel proton mr spectroscopy findings of typical and atypical intracranial meningiomas. European journal of radiology, 60(1):48–55, 2006.CrossRefGoogle Scholar
  7. 7.
    M. Dezortova and M. Hajek. 1H MR spectroscopy in pediatrics. European Journal of Radiology, 67(2):240–249, 2008.CrossRefGoogle Scholar
  8. 8.
    A. Di Costanzo, T. Scarabino, F. Trojsi, T. Popolizio, D. Catapano, G.M. Giannatempo, S. Bonavita, M. Portaluri, M. Tosetti, V.A. dAngelo, et al. Proton mr spectroscopy of cerebral gliomas at 3 t: spatial heterogeneity, and tumour grade and extent. European Radiology, 18(8):1727–1735, 2008.Google Scholar
  9. 9.
    G. Fan, B. Sun, Z. Wu, Q. Guo, and Y. Guo. In vivo single-voxel proton mr spectroscopy in the differentiation of high-grade gliomas and solitary metastases. Clinical radiology, 59(1):77–85, 2004.CrossRefGoogle Scholar
  10. 10.
    K.N. Fountas, E.Z. Kapsalaki, S.D. Gotsis, J.Z. Kapsalakis, H.F. Smisson III, K.W. Johnston, J.S. Robinson Jr, and N. Papadakis. In vivo proton magnetic resonance spectroscopy of brain tumors. Stereotactic and functional neurosurgery, 74(2):83–94, 2000.CrossRefGoogle Scholar
  11. 11.
    J.M. García-Gómez, J. Luts, M. Julià-Sapé, P. Krooshof, S. Tortajada, J.V. Robledo, W. Melssen, E. Fuster-García, I. Olier, G. Postma, et al. Multiproject–multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy. Magnetic Resonance Materials in Physics, Biology and Medicine, 22(1):5–18, 2009.CrossRefGoogle Scholar
  12. 12.
    J.H. Gillard, A.D. Waldman, and P.B. Barker. Clinical MR neuroimaging: diffusion, perfusion, and spectroscopy. Cambridge, UK: Cambridge University Press, 2005.Google Scholar
  13. 13.
    H. González-Vélez, M. Mier, M. Julià-Sapé, T.N. Arvanitis, J.M. García-Gómez, M. Robles, P.H. Lewis, S. Dasmahapatra, D. Dupplaw, A. Peet, et al. Healthagents: distributed multi-agent brain tumor diagnosis and prognosis. Applied Intelligence, 30(3):191–202, 2009.CrossRefGoogle Scholar
  14. 14.
    W. Hollingworth, LS Medina, RE Lenkinski, DK Shibata, B. Bernal, D. Zurakowski, B. Comstock, and JG Jarvik. A systematic literature review of magnetic resonance spectroscopy for the characterization of brain tumors. American journal of neuroradiology, 27(7):1404, 2006.Google Scholar
  15. 15.
    H. Järnum, E.G. Steffensen, L. Knutsson, E.T. Fründ, C.W. Simonsen, S. Lundbye-Christensen, A. Shankaranarayanan, D.C. Alsop, F.T. Jensen, and E.M. Larsson. Perfusion mri of brain tumours: a comparative study of pseudo-continuous arterial spin labelling and dynamic susceptibility contrast imaging. Neuroradiology, 52(4):307–317, 2010.CrossRefGoogle Scholar
  16. 16.
    P. Jissendi Tchofo and D. Balériaux. Brain 1H-MR spectroscopy in clinical neuroimaging at 3 T. Journal of Neuroradiology, 36(1):24–40, 2009.CrossRefGoogle Scholar
  17. 17.
    J. Kim, K.H. Chang, DG Na, IC Song, BJ Kwon, MH Han, and K. Kim. 3 T 1H-MR spectroscopy in grading of cerebral gliomas: comparison of short and intermediate echo time sequences. American journal of neuroradiology, 27(7):1412, 2006.Google Scholar
  18. 18.
    HG Krouwer, T.A. Kim, S.D. Rand, R.W. Prost, V.M. Haughton, K.C. Ho, S.S. Jaradeh, G.A. Meyer, K.A. Blindauer, J.F. Cusick, et al. Single-voxel proton mr spectroscopy of nonneoplastic brain lesions suggestive of a neoplasm. American journal of neuroradiology, 19(9):1695, 1998.Google Scholar
  19. 19.
    A. Kumar, S. Kaushik, RP Tripathi, P. Kaur, and S. Khushu. Role of in vivo proton mr spectroscopy in the evaluation of adult brain lesions: Our preliminary experience. Neurology India, 51(4):474, 2003.Google Scholar
  20. 20.
    M. Law, S. Yang, H. Wang, J.S. Babb, G. Johnson, S. Cha, E.A. Knopp, and D. Zagzag. Glioma grading: sensitivity, specificity, and predictive values of perfusion mr imaging and proton mr spectroscopic imaging compared with conventional mr imaging. American journal of neuroradiology, 24(10):1989, 2003.Google Scholar
  21. 21.
    Y. Li, A.P. Chen, J.C. Crane, S.M. Chang, D.B. Vigneron, and S.J. Nelson. Three-dimensional j-resolved h-1 magnetic resonance spectroscopic imaging of volunteers and patients with brain tumors at 3t. Magnetic Resonance in Medicine, 58(5):886–892, 2007.CrossRefGoogle Scholar
  22. 22.
    M.K. Lim, C.H. Suh, H.J. Kim, Y.K. Cho, S.H. Choi, J.H. Kang, W. Park, and J.H. Lee. Systemic lupus erythematosus: Brain mr imaging and single-voxel hydrogen 1 mr spectroscopy. Radiology, 217(1):43, 2000.Google Scholar
  23. 23.
    A. Lin, B.D. Ross, K. Harris, and W. Wong. Efficacy of proton magnetic resonance spectroscopy in neurological diagnosis and neurotherapeutic decision making. NeuroRx, 2(2):197–214, 2005.CrossRefGoogle Scholar
  24. 24.
    D.N. Louis, H. Ohgaki, O.D. Wiestler, W.K. Cavenee, P.C. Burger, A. Jouvet, B.W. Scheithauer, and P. Kleihues. The 2007 who classification of tumours of the central nervous system. Acta neuropathologica, 114(2):97–109, 2007.CrossRefGoogle Scholar
  25. 25.
    J. Machann, N. Stefan, and F. Schick. 1H MR spectroscopy of skeletal muscle, liver and bone marrow. European Journal of Radiology, 67(2):275–284, 2008.CrossRefGoogle Scholar
  26. 26.
    G. Marquardt, H. Lanfermann, U. Pilatus, and FE Zanella. Clinical application of proton magnetic resonance spectroscopy in the diagnosis of intracranial mass lesions. Neuroradiology, 44:371–381, 2002.Google Scholar
  27. 27.
    D.W. McRobbie, E.A. Moore, M.J. Graves, and M.R. Prince. MRI from picture to proton. Cambridge, UK: Cambridge University Press, 2007.Google Scholar
  28. 28.
    T. Moritani, S. Ekholm, and P.L. Westesson. Diffusion-weighted MR imaging of the brain. Springer Berlin Heidelberg, 2009.Google Scholar
  29. 29.
    Z.G. QI, Y.X. LI, Y. WANG, D.Y. GENG, K.C. LI, T.Z. SHEN, and X.R. CHEN. Lipid signal in evaluation of intracranial meningiomas. Chinese medical journal, 121(23):2415–2419, 2008.Google Scholar
  30. 30.
    Hong Quan, Yue Liu, Shanglian Bao, Shaowu Li, Yaoqin Xie, Binghe Miao, Huiliang Wang. Diagnosis of glioma by multivoxel 1H-MRSI. Progress in Natural Science, 14(9):770–773, 2004.CrossRefGoogle Scholar
  31. 31.
    V. Rajanayagam, J. Grad, W. Krivit, DJ Loes, L. Lockman, E. Shapiro, M. Balthazor, D. Aeppli, and AE Stillman. Proton mr spectroscopy of childhood adrenoleukodystrophy. American journal of neuroradiology, 17(6):1013, 1996.Google Scholar
  32. 32.
    O.M. Sandra, O. Iván, J.S. Margarida, and A. Carles. Spectraclassifier 1.0: a user friendly, automated mrs-based classifier-development system. BMC Bioinformatics, 11:106, 2010.Google Scholar
  33. 33.
    NA Sibtain, FA Howe, and DE Saunders. The clinical value of proton magnetic resonance spectroscopy in adult brain tumours. Clinical radiology, 62(2):109–119, 2007.CrossRefGoogle Scholar
  34. 34.
    A. Skoch, F. Jiru, and J. Bunke. Spectroscopic imaging: basic principles. European Journal of Radiology, 67(2):230–239, 2008.CrossRefGoogle Scholar
  35. 35.
    C.Y. Tang, J. Friedman, D. Shungu, L. Chang, T. Ernst, D. Stewart, A. Hajianpour, D. Carpenter, J. Ng, X. Mao, et al. Correlations between diffusion tensor imaging(dti) and magnetic resonance spectroscopy(1 h mrs) in schizophrenic patients and normal controls. BMC psychiatry, 7(1):25, 2007.Google Scholar
  36. 36.
    A.R. Tate, J. Underwood, D.M. Acosta, M. Julià-Sapé, C. Majós, À. Moreno-Torres, F.A. Howe, M. Van Der Graaf, V. Lefournier, M.M. Murphy, et al. Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra. NMR in Biomedicine, 19(4):411–434, 2006.CrossRefGoogle Scholar
  37. 37.
    A.A. Tzika, W.S. Ball Jr, D.B. Vigneron, R.S. Dunn, and D.R. Kirks. Clinical proton mr spectroscopy of neurodegenerative disease in childhood. American journal of neuroradiology, 14(6):1267, 1993.Google Scholar
  38. 38.
    M.P. Wattjes, M. Harzheim, G.G. Lutterbey, M. Bogdanow, S. Schmidt, H.H. Schild, and F. Träber. Prognostic value of high-field proton magnetic resonance spectroscopy in patients presenting with clinically isolated syndromes suggestive of multiple sclerosis. Neuroradiology, 50(2):123–129, 2008.CrossRefGoogle Scholar
  39. 39.
    M.P. Wattjes, M. Harzheim, G.G. Lutterbey, L. Klotz, H.H. Schild, and F. Traber. Axonal damage but no increased glial cell activity in the normal-appearing white matter of patients with clinically isolated syndromes suggestive of multiple sclerosis using high-field magnetic resonance spectroscopy. American Journal of Neuroradiology, 28(8):1517, 2007.Google Scholar
  40. 40.
    P. Zonari, P. Baraldi, and G. Crisi. Multimodal MRI in the characterization of glial neoplasms: the combined role of single-voxel MR spectroscopy, diffusion imaging and echo-planar perfusion imaging. Neuroradiology, 49(10):795–803, 2007.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2012

Authors and Affiliations

  • Evaggelia Tsolaki
    • 1
  • Evanthia Kousi
    • 1
  • Eftychia Kapsalaki
    • 2
  • Ioannis Dimou
    • 3
  • Kyriaki Theodorou
    • 1
  • Georgios C. Manikis
    • 3
  • Constantin Kappas
    • 1
  • Ioannis Tsougos
    • 1
  1. 1.Medical Physics Department, School of MedicineUniversity of ThessalyLarissaGreece
  2. 2.Diagnostic Radiology Department, School of MedicineUniversity of ThessalyLarissaGreece
  3. 3.ECE Department Technical University of CreteChaniaHellas, Greece

Personalised recommendations