Skip to main content

Advertisement

SpringerLink
Log in

Fast spectroscopic multiple analysis (FASMA) for brain tumor classification: a clinical decision support system utilizing multi-parametric 3T MR data

  • Original Article
  • Published:
International Journal of Computer Assisted Radiology and Surgery Aims and scope Submit manuscript

Abstract

Introduction

   A clinical decision support system (CDSS) for brain tumor classification can be used to assist in the diagnosis and grading of brain tumors. A Fast Spectroscopic Multiple Analysis (FASMA) system that uses combinations of multiparametric MRI data sets was developed as a CDSS for brain tumor classification.

Methods

   MRI metabolic ratios and spectra, from long and short TE, respectively, as well as diffusion and perfusion data were acquired from the intratumoral and peritumoral area of 126 patients with untreated intracranial tumors. These data were categorized based on the pathology, and different machine learning methods were evaluated regarding their classification performance for glioma grading and differentiation of infiltrating versus non-infiltrating lesions. Additional databases were embedded to the system, including updated literature values of the related MR parameters and typical tumor characteristics (imaging and histological), for further comparisons. Custom Graphical User Interface (GUI) layouts were developed to facilitate classification of the unknown cases based on the user’s available MR data.

Results

   The highest classification performance was achieved with a support vector machine (SVM) using the combination of all MR features. FASMA correctly classified 89 and 79 % in the intratumoral and peritumoral area, respectively, for cases from an independent test set. FASMA produced the correct diagnosis, even in the misclassified cases, since discrimination between infiltrative versus non-infiltrative cases was possible.

Conclusions

   FASMA is a prototype CDSS, which integrates complex quantitative MR data for brain tumor characterization. FASMA was developed as a diagnostic assistant that provides fast analysis, representation and classification for a set of MR parameters. This software may serve as a teaching tool on advanced MRI techniques, as it incorporates additional information regarding typical tumor characteristics derived from the literature.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

References

  1. The brain tumor society. http://www.tbts.org

  2. Mehndiratta A, Giesel FL (2011) Brain tumor imaging. In: Abujamra AL (ed) Diagnostic techniques and surgical management of brain tumors. InTech Publications

  3. Pollice S, Morlino G, Capuano M, Scarabino T (2012) Brain tumors. Imaging gliomas after treatment. Spinger, Berlin, pp 3–10

  4. Cha S (2009) Neuroimaging in neuro-oncology. Neurotherapeutics 6(3):465–477

    Article  CAS  PubMed  Google Scholar 

  5. Chiang IC, Kuo YT, Lu CY et al (2004) Distinction between high-grade gliomas and solitary metastases using peritumoral 3-T magnetic resonance spectroscopy, diffusion, and perfusion imagings. Neuroradiology 46(8):619–627

    Article  PubMed  Google Scholar 

  6. Tsolaki E, Svolos P, Kousi E, Kapsalaki E, Fountas K, Theodorou K, Tsougos I (2013) Automated differentiation of glioblastomas from intracranial metastases using 3T MR spectroscopic and perfusion data. Int J Comput Assist Radiol Surg 8(5):751- 761.

  7. Tsougos I, Svolos P, Kousi E, Fountas K, Theodorou K, Fezoulidis I, Kapsalaki E (2012) Differentiation of glioblastoma multiforme from metastatic brain tumor using proton magnetic resonance spectroscopy, diffusion and perfusion metrics at 3 T. Cancer Imaging 12:423–436

    Article  PubMed Central  PubMed  Google Scholar 

  8. Law M, Cha S, Knopp EA et al (2002) High grade gliomas and solitary metastases: differentiation by using perfusion and proton spectroscopic MR imaging. Radiology 222(3):715–721

    Article  PubMed  Google Scholar 

  9. Liu X, Tian W, Kolar B, Yeaney GA, Qiu X, Johnson MD et al (2011) MR diffusion tensor and perfusion-weighted imaging in preoperative grading of supratentorial nonenhancing gliomas. Neuro Oncol 13(4):447–455

    Article  PubMed Central  PubMed  Google Scholar 

  10. Svolos P, Tsolaki E, Theodorou K, Fountas K, Kapsalaki E, Fezoulidis I, Tsougos I (2013) Classification methods for the differentiation of atypical meningiomas using diffusion and perfusion techniques at 3-T MRI. Clin Imaging 37(5):856–64

    Article  PubMed  Google Scholar 

  11. Karlsson D (2001) Aspects of the use of medical decision-support systems: the role of context in decision support. PhD thesis, Institute of Technology, Linköping University.

  12. 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. Nucl Magn Reson Biomed 19(4):411–434

    CAS  Google Scholar 

  13. eTUMOUR Consortium, eTUMOUR: Web accessible MR decision support system for brain tumour diagnosis and prognosis. Incorporating in vivo and ex vivo genomic and metabolic data. FP6-2002-LIFESCHEALTH 503094, VI Framework Programme EC. http://www.etumour.net. Last Access 12/03/2013

  14. Gonzalez-Velez H, Mier M, Julià-Sapé M et al (2009) HealthAgents: distributed multi-agent brain tumor diagnosis and prognosis. J Appl Intell 30:191–202

    Article  Google Scholar 

  15. Sáez C, García-Gómez JM, Vicente J et al. (2009) Curiam BT 1.0, Decision support system for brain tumour diagnosis. In: ESMRMB congress, antalya, Turkey, EPOS Posters/Paper Posters/Info-RESO, pp 538.

  16. De Edelenyi FS, Rubin C, Estève F, Grand S, Décorps M, Lefournier V, Le Bas JF, Rémy C (2000) A new approach for analyzing proton magnetic resonance spectroscopic images of brain tumors: nosologic images. Nat Med 6(11):1287–1289

    Article  PubMed  Google Scholar 

  17. McKnight TR, Noworolski SM, Vigneron DB, Nelson SJ (2001) An automated technique for the quantitative assessment of 3D-MRSI data from patients with glioma. J Magn Reson Imaging 13:167–177

    Article  CAS  PubMed  Google Scholar 

  18. Simonetti AW, Melssen WJ, van der Graaf M, Heerschap A, Buydens LMC (2003) A new chemometric approach for brain tumor classification using magnetic resonance imaging and spectroscopy. Anal Chem 75:5352–5361

    Article  CAS  PubMed  Google Scholar 

  19. De Vos M, Laudadio T, Simonetti AW, Heerschap A, Van Huffel S (2007) Fast nosologic imaging of the brain. J Magn Reson 184(2):292–301

    Article  PubMed  Google Scholar 

  20. Laudadio T, Martinez-Bisbal MC, Celda B, Van Huffel S (2008) Fast nosological imaging using canonical correlation analysis of brain data obtained by two-dimensional turbo spectroscopic imaging. NMR Biomed 21(4):311–321

    Article  CAS  PubMed  Google Scholar 

  21. Luts J, Laudadio T, Idema AJ et al (2009) Nosologic imaging of the brain: segmentation and classification using MRI and MRSI. NMR Biomed 22:374–390

    Article  PubMed  Google Scholar 

  22. Li Y, Sima D, Van Cauter S, Himmelreich U, Pi Y, Liu Y, van Huffel S (2013) Unsupervised nosologic imaging for glioma diagnosis. IEEE Trans Biomed Eng 60(6):1760–1763

    Article  PubMed  Google Scholar 

  23. Svolos P, Tsolaki E, Kapsalaki E, Theodorou K, Fountas K, Fezoulidis I, Tsougos I (2013) Investigating brain tumor differentiation with diffusion and perfusion metrics at 3T MRI using pattern recognition techniques. Magn Resonan Imaging 31(9): 1567–1577

  24. Kousi E, Tsougos I, Tsolaki E, Fountas KN, Theodorou K, Fezoulidis I, Kapsalaki E, Kappas C (2012) Spectroscopic evaluation of glioma grading at 3T: the combined role of short and long TE. Sci World J 2012:546171

    CAS  Google Scholar 

  25. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297

    Google Scholar 

  26. John GH, Langley P (1995) Estimating continuous distributions in Bayesian classifiers. In: Besnard P, Hanks S (eds) Proceedings of the eleventh conference on uncertainty in artificial intelligence (UAI’95). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp 338–345

    Google Scholar 

  27. Kazmierska J, Malicki J (2008) Application of the Naïve Bayesian classifier to optimize treatment decisions. Radiother Oncol 86(2):211–216

    Article  PubMed  Google Scholar 

  28. Cover TM, Hart PE (1967) Nearest neighbor pattern classification. Inst Electr Electron Eng Trans Inf Theory 13:21–27

    Google Scholar 

  29. Wang J, Neskovic P, Cooper LN (2007) Improving nearest neighbor rule with a simple adaptive distance measure. Pattern Recognit Lett 28(2):207–213

    Article  Google Scholar 

  30. Fukunaga K (1990) Introduction to statistical pattern recognition, 2nd edn. Academic Press, San Diego

    Google Scholar 

  31. García-Gómez JM, Luts J, Julià-Sapé M et al (2009) Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy. Magn Reson Mater Phys 22(1):5–18

    Article  Google Scholar 

  32. Qi H (2002) Feature selection and kNN fusion in molecular classification of multiple tumor types. In: Proceedings of the mathematics and engineering techniques in medicine and biological sciences, Las Vegas, Nevada, USA.

  33. Li S, Harner EJ, Adjeroh DA (2011) Random KNN feature selection-a fast and stable alternative to Random Forest. BMC Bioinform 12:450

    Article  Google Scholar 

  34. Webb AR (2002) Statistical pattern recognition. Wiley, West Sussex

    Book  Google Scholar 

  35. Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugen 7:179–188

    Article  Google Scholar 

  36. Pöyhönen S, Arkkio A, Jover P, Hyötyniemi H (2005) Coupling pairwise support vector machines for fault classification. Control Eng Pract 13(6):759–769

    Article  Google Scholar 

  37. http://www.mathworks.com/products/compiler/mcr/index.htm

  38. Rijpkema M, Schuuring J, van der Meulen Y et al (2003) Characterization of oligodendrogliomas using short echo time 1H MR spectroscopic imaging. NMR Biomed 16:12–18

    Article  CAS  PubMed  Google Scholar 

  39. Majós C, Aguilera C, Cos M et al (2009) In vivo proton magnetic resonance spectroscopy of intraventricular tumours of the brain. Eur Radiol 19(8):2049–2059

    Article  PubMed  Google Scholar 

  40. Porto L, Kieslich M, Franz K et al (2011) MR spectroscopy differentiation between high and low grade astrocytomas: a comparison between paediatric and adult tumours. Eur J Paediatr Neurol 15(3):214–221

    Article  PubMed  Google Scholar 

  41. Law M, Yang S, Wang H et al (2003) Glioma grading: sensitivity, specificity and predictive values of perfusion MR imaging and proton MR spectroscopic imaging compared with conventional MR imaging. AJNR Am J Neuroradiol 24(10):1989–1998

    PubMed  Google Scholar 

  42. Howe FA, Barton SJ, Cudlip SA et al (2003) Metabolic profiles of human brain tumors using quantitative in vivo 1H magnetic resonance spectroscopy. Magn Reson Med 49:223–232

    Article  CAS  PubMed  Google Scholar 

  43. Castillo M, Smith JK, Kwock L (2000) Correlation of myo-inositol levels and grading of cerebral astrocytomas. AJNR Am J Neuroradiol 21(9):1645–1649

    CAS  PubMed  Google Scholar 

  44. Möller-Hartmann W, Herminghaus S, Krings T et al (2002) Clinical application of proton magnetic resonance spectroscopy in the diagnosis ofintracranial mass lesions. Neuroradiology 44(5):371–381

    Article  PubMed  Google Scholar 

  45. Yamasaki F, Kurisu K, Satoh K et al (2005) Apparent diffusion coefficient of human brain tumors at MR imaging. Radiology 235(3):985–991

    Article  PubMed  Google Scholar 

  46. Price SJ (2010) Advances in imaging low-grade gliomas. Adv Tech Stand Neurosurg 35:1–34

    PubMed  Google Scholar 

  47. Hakyemez B, Yildirim N, Erdoğan C et al (2006) Meningiomas with conventional MRI findings resembling intraaxial tumors: can perfusion-weighted MRI be helpful in differentiation? Neuroradiology 48(10):695–702

    Article  PubMed  Google Scholar 

  48. Majós C, Alonso J, Aguilera C et al (2003) Proton magnetic resonance spectroscopy (1H MRS) of human brain tumours: assessment of differences between tumour types and its applicability in brain tumour categorization. Eur Radiol 13(3):582–591

    PubMed  Google Scholar 

  49. Lehnhardt FG, Bock C, Röhn G, Ernestus RI, Hoehn M (2005) Metabolic differences between primary and recurrent human brain tumors: a 1H NMR spectroscopic investigation. NMR Biomed 18:371–382

    Article  CAS  PubMed  Google Scholar 

  50. Kousi E, Tsougos I, Fountas K, Theodorou K, Tsolaki E, Fezoulidis I, Kapsalaki E (2012) Distinct peak at 3.8 ppm observed by 3T MR spectroscopy in meningiomas, while nearly absent in high-grade gliomas and cerebral metastases. Mol Med Rep 5(4):1011–1018.

  51. Nagar VA, Ye JR, Ng WH, Chan YH, Hui F, Lee CK, Lim CC (2008) Diffusion-weighted MR imaging: diagnosing atypical or malignant meningiomas and detecting tumor dedifferentiation. AJNR Am J Neuroradiol 29(6):1147–1152

  52. Toh CH, Castillo M, Wong AM, Wei KC, Wong HF, Ng SH, Wan YL (2008) Differentiation between classic and atypical meningiomas with use of diffusion tensor imaging. AJNR Am J Neuroradiol 9:1630–1635

  53. Zhang H, Rödiger LA, Shen T et al (2008) Perfusion MR imaging for differentiation of benign and malignant meningiomas. Neuroradiology 50(6):525–530

    Article  PubMed Central  PubMed  Google Scholar 

  54. Server A, Josefsen R, Kulle B et al (2010) Proton magnetic resonance spectroscopy in the distinction of high-grade cerebral gliomas from single metastatic brain tumors. Acta Radiol 51(3):316–325

    Article  PubMed  Google Scholar 

  55. Li G, Yang J, Ye C, Geng D (2006) Degree prediction of malignancy in brain glioma using support vector machines. Comput Biol Med 36(3):313–325

    Article  CAS  PubMed  Google Scholar 

  56. Zacharaki EI, Kanas VG, Davatzikos C (2011) Investigating machine learning techniques for MRI-based classification of brain neoplasms. Int J Comput Assist Radiol Surg 6(6):821–828

    Article  PubMed Central  PubMed  Google Scholar 

  57. Devos A et al (2005) The use of multivariate MR imaging intensities versus metabolic data from MR spectroscopic imaging for brain tumour classification. J Magn Reson 173(2):218–228

    Article  CAS  PubMed  Google Scholar 

  58. Di Costanzo A, Scarabino T, Trojsi F et al (2008) Proton MR spectroscopy of cerebral gliomas at 3 T: spatial heterogeneity, and tumour grade and extent. Eur Radiol 18:1727–1735

    Article  PubMed  Google Scholar 

  59. Zonari P, Baraldi P, Crisi G (2007) 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

    Article  PubMed  Google Scholar 

  60. Luts J, Heerschap A, Suykens JAK, Van Huffel S (2007) A combined MRI and MRSI based multiclass system for brain tumour recognition using LS-SVMs with class probabilities and feature selection. Artif Intell Med 40(2):87–102

    Article  PubMed  Google Scholar 

  61. Ben-Hur A, Weston J (2010) A user’s guide to support vector machines. Methods Mol Biol 609:223–239

    Article  CAS  PubMed  Google Scholar 

  62. Cha S (2006) Update on brain tumor imaging: from anatomy to physiology. AJNR Am J Neuroradiol 27(3):475–487

  63. Ginat DT, Mangla R et al (2010) Correlation of diffusion and perfusion MRI with Ki-67 in high-grade meningiomas. AJR Am J Roentgenol 195(6):1391–1395

    Article  PubMed  Google Scholar 

  64. Fan G, Sun B, Wu Z, Guo Q, Guo Y (2004) In vivo single-voxel proton MR spectroscopy in the differentiation of high-grade gliomas and solitary metastases. Clin Radiol 59(1):77–85

    Article  CAS  PubMed  Google Scholar 

  65. Chernov MF, Kubo O, Hayashi M et al (2005) Proton MRS of the peritumoral brain. J Neurol Sci 228(2):137–142

    Article  CAS  PubMed  Google Scholar 

Download references

Conflict of interest

The authors declare that they have no conflict of interest.

Author information

Authors and Affiliations

  1. Medical Physics Department, Medical School, University of Thessaly, 41110 , Biopolis, Larissa, Greece

    Evangelia Tsolaki, Patricia Svolos, Evanthia Kousi, Kyriaki Theodorou, Constantine Kappas & Ioannis Tsougos

  2. Department of Radiology, Medical School, University of Thessaly, 41110 , Biopolis, Larissa, Greece

    Eftychia Kapsalaki & Ioannis Fezoulidis

  3. Department of Neurosurgery, Medical School, University of Thessaly, 41110 , Biopolis, Larissa, Greece

    Konstantinos Fountas

Authors
  1. Evangelia Tsolaki
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Patricia Svolos
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Evanthia Kousi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Eftychia Kapsalaki
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ioannis Fezoulidis
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Konstantinos Fountas
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Kyriaki Theodorou
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Constantine Kappas
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Ioannis Tsougos
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ioannis Tsougos.

Appendix

Appendix

For the “Appendix” Table 8.

Table 8 Metabolite ratios, diffusion and perfusion mean values
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tsolaki, E., Svolos, P., Kousi, E. et al. Fast spectroscopic multiple analysis (FASMA) for brain tumor classification: a clinical decision support system utilizing multi-parametric 3T MR data. Int J CARS 10, 1149–1166 (2015). https://doi.org/10.1007/s11548-014-1088-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11548-014-1088-7

Keywords

Search

Navigation