Journal of Neuro-Oncology

, Volume 138, Issue 3, pp 619–625 | Cite as

Malignancy probability map as a novel imaging biomarker to predict malignancy distribution: employing MRS in GBM patients

  • Manijeh Beigi
  • Kevan Ghasemi
  • Parvin Mirzaghavami
  • Mohammadreza Khanmohammadi
  • Hamidreza SalighehRad
Clinical Study


The main aim of this study was to propose a new statistical method for evaluation of spatial malignancy distribution within Magnetic Resonance Spectroscopy (MRS) grid in Glioblastoma Multiforme patients. Voxels with different malignancy probabilities were presented as a novel MRS-based Malignancy Probability Map (MPM). For this purpose, a predictive probability-based clustering approach was developed, including the two following steps: (1) Gaussian Mixture Model, (2) Quadratic Discriminate Analysis coupled with Genetic Algorithm. Clustered probability values from two methods were then integrated to exploit the MPM. Results show that the suggested method is able to estimate the malignancy distribution with over 90% sensitivity and specificity. The proposed MRS-based MPM has an acceptable accuracy for providing useful complementary information about regional diffuse glioma malignancy, with the potential to lead to better detection of tumoral regions with high probability of malignancy. So, it also may encourage the use of additional information of this map as a tool for dose painting.


Glioblastoma multiform Magnetic resonance spectroscopy Gaussian mixture model Genetic algorithm 



This work was fully supported by Tehran University of Medical Science.

Compliance with ethical standards

Conflict of interest

The authors declare no conflict of interest.


  1. 1.
    Tolia M, Verganelakis D, Tsoukalas N et al. (2015) Prognostic value of MRS metabolites in postoperative irradiated high grade gliomas. BioMed Res Int 2015:1–6Google Scholar
  2. 2.
    Farace P, Giri M, Meliado G et al (2011) Clinical target volume delineation in glioblastomas: pre-operative versus post-operative/pre-radiotherapy MRI. Br J Radiol 84(999):271–278CrossRefPubMedPubMedCentralGoogle Scholar
  3. 3.
    Petrecca K, Guiot M-C, Panet-Raymond V, Souhami L (2013) Failure pattern following complete resection plus radiotherapy and temozolomide is at the resection margin in patients with glioblastoma. J Neuro Oncol 111(1):19–23CrossRefGoogle Scholar
  4. 4.
    Yu VY (2017) Improving glioblastoma multiforme (GBM) radiotherapy outcome through personalized biological modeling and optimization. UCLA, Los AngelesGoogle Scholar
  5. 5.
    Chamberlain MC (2011) Radiographic patterns of relapse in glioblastoma. J Neuro Oncol 101(2):319–323CrossRefGoogle Scholar
  6. 6.
    Minniti G, Amelio D, Amichetti M et al (2010) Patterns of failure and comparison of different target volume delineations in patients with glioblastoma treated with conformal radiotherapy plus concomitant and adjuvant temozolomide. Radiother Oncol 97(3):377–381CrossRefPubMedGoogle Scholar
  7. 7.
    Unkelbach J, Menze BH, Konukoglu E et al (2014) Radiotherapy planning for glioblastoma based on a tumor growth model: improving target volume delineation. Phys Med Biol 59(3):747CrossRefPubMedGoogle Scholar
  8. 8.
    Price S, Gillard J (2011) Imaging biomarkers of brain tumour margin and tumour invasion. Br J Radiol 84(special_issue_2):S159–S167Google Scholar
  9. 9.
    Guo J, Yao C, Chen H et al (2012) The relationship between Cho/NAA and glioma metabolism: implementation for margin delineation of cerebral gliomas. Acta Neurochir 154(8):1361–1370CrossRefPubMedPubMedCentralGoogle Scholar
  10. 10.
    Pirzkall A, Li X, Oh J et al (2004) 3D MRSI for resected high-grade gliomas before RT: tumor extent according to metabolic activity in relation to MRI. Int J Radiat Oncol Biol Phys 59(1):126–137CrossRefPubMedGoogle Scholar
  11. 11.
    Parra NA, Maudsley AA, Gupta RK et al (2014) Volumetric spectroscopic imaging of glioblastoma multiforme radiation treatment volumes. Int J Radiat Oncol Biol Phys 90(2):376–384CrossRefPubMedPubMedCentralGoogle Scholar
  12. 12.
    Guo L, Wang G, Feng Y et al (2016) Diffusion and perfusion weighted magnetic resonance imaging for tumor volume definition in radiotherapy of brain tumors. Radiat Oncol 11(1):123CrossRefPubMedPubMedCentralGoogle Scholar
  13. 13.
    Ken S, Vieillevigne L, Franceries X et al (2013) Integration method of 3D MR spectroscopy into treatment planning system for glioblastoma IMRT dose painting with integrated simultaneous boost. Radiat Oncol 8(1):1CrossRefPubMedPubMedCentralGoogle Scholar
  14. 14.
    Narayana A, Chang J, Thakur S et al. (2014) Use of MR spectroscopy and functional imaging in the treatment planning of gliomas. Br J Radiol 80(953):347–354Google Scholar
  15. 15.
    Valentini MC, Mellai M, Annovazzi L et al (2017) Comparison among conventional and advanced MRI, 18F-FDG PET/CT, phenotype and genotype in glioblastoma. Oncotarget 8(53):91636CrossRefPubMedPubMedCentralGoogle Scholar
  16. 16.
    Tate AR, Underwood J, Acosta DM et al (2006) Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra. NMR Biomed 19(4):411–434CrossRefPubMedGoogle Scholar
  17. 17.
    Fuster-Garcia E, Navarro C, Vicente J et al (2011) Compatibility between 3T 1H SV-MRS data and automatic brain tumour diagnosis support systems based on databases of 1.5 T 1H SV-MRS spectra. Magn Reson Mater Phys Biol Med 24(1):35–42CrossRefGoogle Scholar
  18. 18.
    Poullet J-B, Sima D, Luts J, Garcia MO, Croitor A, Van Huffel S (2008) Manual: simulation Package based on vitro Databases (SPID)Google Scholar
  19. 19.
    Rajan K (2013) Informatics for materials science and engineering: data-driven discovery for accelerated experimentation and application. Butterworth-Heinemann, OxfordGoogle Scholar
  20. 20.
    Opstad K, Ladroue C, Bell B, Griffiths J, Howe F (2007) Linear discriminant analysis of brain tumour 1H MR spectra: a comparison of classification using whole spectra versus metabolite quantification. NMR Biomed 20(8):763–770CrossRefPubMedGoogle Scholar
  21. 21.
    Kennard RW, Stone LA (1969) Computer aided design of experiments. Technometrics 11(1):137–148CrossRefGoogle Scholar
  22. 22.
    Benediktsson JA, Swain PH (1992) Consensus theoretic classification methods. IEEE Trans Syst Man Cybern 22(4):688–704CrossRefGoogle Scholar
  23. 23.
    Benediktsson JA, Kanellopoulos I (1999) Classification of multisource and hyperspectral data based on decision fusion. IEEE Trans Geosci Remote Sens 37(3):1367–1377CrossRefGoogle Scholar
  24. 24.
    Vartanian A, Singh SK, Agnihotri S et al (2014) GBM’s multifaceted landscape: highlighting regional and microenvironmental heterogeneity. Neuro Oncol 16(9):1167–1175CrossRefPubMedPubMedCentralGoogle Scholar
  25. 25.
    Einstein DB, Wessels B, Bangert B et al (2012) Phase II trial of radiosurgery to magnetic resonance spectroscopy–defined high-risk tumor volumes in patients with glioblastoma multiforme. Int J Radiat Oncol Biol Phys 84(3):668–674CrossRefPubMedPubMedCentralGoogle Scholar
  26. 26.
    Deviers A, Ken S, Filleron T et al (2014) Evaluation of the lactate-to-N-acetyl-aspartate ratio defined with magnetic resonance spectroscopic imaging before radiation therapy as a new predictive marker of the site of relapse in patients with glioblastoma multiforme. Int J Radiat Oncol Biol Phys 90(2):385–393CrossRefPubMedGoogle Scholar
  27. 27.
    Stagg C, Rothman DL (2013) Magnetic resonance spectroscopy: tools for neuroscience research and emerging clinical applications: Academic Press, CambridgeGoogle Scholar
  28. 28.
    Shen X, Wang E, Yao C, Tang W, Guo J (2017) Application of magnetic resonance spectroscopy in the preoperative grading of gliomas. Int J Clin Exp Med 10(2):2834–2841Google Scholar
  29. 29.
    Zarinabad N, Abernethy LJ, Avula S et al. (2017) Application of pattern recognition techniques for classification of pediatric brain tumors by in vivo 3T 1H-MR spectroscopy—a multi-center study. Magn Reson Med 79(4):2359–2366Google Scholar
  30. 30.
    Blumenthal D, Artzi M, Liberman G, Bokstein F, Aizenstein O, Bashat DB (2017) Classification of high-grade glioma into tumor and nontumor components using support vector machine. Am J Neuroradiol 38(5):908–914CrossRefPubMedGoogle Scholar
  31. 31.
    Ranjith G, Parvathy R, Vikas V, Chandrasekharan K, Nair S (2015) Machine learning methods for the classification of gliomas: initial results using features extracted from MR spectroscopy. Neuroradiol J 28(2):106–111CrossRefPubMedPubMedCentralGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Quantitative MR Imaging and Spectroscopy Group, Research Center for Cellular and Molecular Imaging, Institute for Advanced Medical ImagingTehran University of Medical SciencesTehranIran
  2. 2.Department of Medical Physics and Biomedical EngineeringTehran University of Medical SciencesTehranIran
  3. 3.Medical Physics Department, Faculty of MedicineIran University of Medical SciencesTehranIran
  4. 4.Chemistry Department, Faculty of ScienceImam Khomeini International UniversityQazvinIran

Personalised recommendations