Abstract
Purpose Differentiation of glioblastomas from metastases is clinical important, but may be difficult even for expert observers. To investigate the contribution of machine learning algorithms in the differentiation of glioblastomas multiforme (GB) from metastases, we developed and tested a pattern recognition system based on 3T magnetic resonance (MR) data.
Materials and Methods Single and multi-voxel proton magnetic resonance spectroscopy (1H-MRS) and dynamic susceptibility contrast (DSC) MRI scans were performed on 49 patients with solitary brain tumors (35 glioblastoma multiforme and 14 metastases). Metabolic (NAA/Cr, Cho/Cr, (Lip \(+\) Lac)/Cr) and perfusion (rCBV) parameters were measured in both intratumoral and peritumoral regions. The statistical significance of these parameters was evaluated. For the classification procedure, three datasets were created to find the optimum combination of parameters that provides maximum differentiation. Three machine learning methods were utilized: Naïve-Bayes, Support Vector Machine (SVM) and \(k\)-nearest neighbor (KNN). The discrimination ability of each classifier was evaluated with quantitative performance metrics.
Results Glioblastoma and metastases were differentiable only in the peritumoral region of these lesions (\(p<0.05\)). SVM achieved the highest overall performance (accuracy 98 %) for both the intratumoral and peritumoral areas. Naïve-Bayes and KNN presented greater variations in performance. The proper selection of datasets plays a very significant role as they are closely correlated to the underlying pathophysiology.
Conclusion The application of pattern recognition techniques using 3T MR-based perfusion and metabolic features may provide incremental diagnostic value in the differentiation of common intraaxial brain tumors, such as glioblastoma versus metastasis.
Similar content being viewed by others
References
Chiang IC et al (2004) Distinction between high-grade gliomas and solitary metastases using peritumoral 3-T magnetic resonance spectroscopy, diffusion, and perfusion imaging. Neuroradiology 46(8):619–627
Liu X et al (2011) MR diffusion tensor and perfusion-weighted imaging in preoperative grading of supratentorial nonenhancing gliomas. Neurol Oncol 13(4):447–455
Cha S (2009) Neuroimaging in neuro-oncology. Neurotherapeutics 6(3):465–477
Toh CH et al (2008) Primary cerebral lymphoma and glioblastoma multiforme: differences in diffusion characteristics evaluated with diffusion tensor imaging. Am J Neuroradiol 29(3):471–475
Law M et al (2002) High-grade gliomas and solitary metastases: differentiation by using perfusion and proton spectroscopic MR imaging. Radiology 222(3):715–721
Howe FA et al (2003) Metabolic profiles of human brain tumors using quantitative in vivo 1H magnetic resonance spectroscopy. Magn Reson Med 49(2):223–232
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
Al-Okaili RN et al (2007) Intraaxial brainmasses MR imaging- based diagnostic strategy-initial experience. Radiology 243(2): 539–550
Weber MA et al (2006) Diagnostic performance of spectroscopic and perfusion MRI for distinction of brain tumors. Neurology 66(12):1899.S–1906.S
Chawla et al (2010) Proton magnetic resonance spectroscopy in differentiating glioblastomas from primary cerebral lymphomas and brain metastases. J Comput Assist Tomogr 34(6):836–841
Lee EJ et al (2011) Diagnostic value of peritumoral minimum apparent diffusion coefficient for differentiation of glioblastoma multiforme from solitary metastatic lesions. Am J Roentgenol 196(1):71–76
Tsougos I et al (2012) Differentiation of glioblastoma multiforme from metastatic brain tumor using proton magnetic resonance spectroscopy, diffusion and perfusion metrics at 3 T. Cancer Imaging 12:1–14. doi:10.1102/1470-7330.2012.0038
García-Gómez JM (2011) Brain tumor classification using magnetic resonance spectroscopy. In: Tumors of the central nervous. System, vol 3. Springer, pp 5–19
INTERPRET Consortium, “INTERPRET”. Web site, 1999–2001. IST-1999-10310, EC. http://gabrmn.uab.es/interpret/
Tate AR 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
eTUMOUR Consortium, “eTumour: Web accessible MR Decision support system for brain tumour diagnosis and prognosis, incorporating in vivo and ex vivo genomic andmetabolomic data”.Web site. FP6-2002-LIFESCIHEALTH 503094, VI framework programme, EC. http://cordis.europa.eu/search/index.cfm?fuseaction=proj.document&PJ_RCN=7921577. Accessed 6 Oct 2012
Gonzalez Velez H et al (2009) HealthAgents: distributed multi-agent brain tumor diagnosis and prognosis. Appl Intell 30(3): 191–202
Arús C et al (2006) On the design of a web-based decision support system for brain tumour diagnosis using distributed agents. In: IAT Workshops, pp 208–211
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
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
Zacharaki EI et al (2009) Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med 62(6):1609–1618
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
Garcia-Gomez JM et al (2009) Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy. MAGMA 22(1):5–18
Blanchet L et al (2011) Discrimination between metastasis and glioblastoma multiforme based on morphometric analysis of MR images. Am J Neuroradiol 32(1):67–73
Dimou I et al (2011) Brain lesion classification using 3T MRS spectra and paired SVM kernels. Biomed Signal Process Control 6(3):314–320
Kousi E et al (2012) Spectroscopic evaluation of Glioma grading at 3T: the combined role of short and long TE. Sci World J 2012:546171
Emblem KE et al (2008) Glioma grading by cerebral blood volume maps. Radiology 247(3):808–817
Zhang H (2008) Perfusion MR imaging for differentiation of benign and malignant meningiomas. Neuroradiology 50(6):525–530
Boxerman JL, Schmainda KM, Weisskoff RM (2006) Relative cerebral blood volume maps corrected for contrast agent extravasation significantly correlate with Glioma tumor grade, whereas uncorrected maps do not. Am J Neuroradiol 27:859–867
Knopp EA, Cha S, Johnson G, Mazumdar A, Golfinos JG, Zagzag D et al (1999) Glial neoplasms: dynamic contrast-enhanced T2*-weighted MR imaging. Radiology 211(3):791–798
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297
Chang CC, Lin CJ (2001) LIBSVM: a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
John GH, Langley P (1995) Estimating continuous distributions in Bayesian classifiers. In: (UAI’95) Philippe B, Steve H (eds) Proceedings of the eleventh conference on uncertainty in artificial intelligence. Morgan Kaufmann Publishers Inc., San Francisco, pp 338–345
Kazmierska J, Malicki J (2008) Application of the Naïve Bayesian Classifier to optimize treatment decisions. Radiother Oncol 86(2):211–216
Cover TM, Hart PE (1967) Nearest neighbor pattern classification. Inst Electr Electron Eng Trans Inf Theory 13:21–27
Wang J, Neskovic P, Cooper LN (2007) Improving nearest neighbor rule with a simple adaptive distance measure. Pattern Recognit Lett 28(2):207–213
Lukas L et al (2004) Brain tumor classification based on long echo proton MRS signal. Artif Intell Med 31(1):73–89
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
Li S, Harner EJ, Adjeroh DA (2011) Random KNN feature selection-a fast and stable alternative to random forest. BMC Bioinform 12:450
Wu X et al (2008) Top 10 algorithms in data mining. Knowl Inf Syst 14(1):1–37
Opstad KS et al (2004) Differentiation of metastases from high-grade gliomas using short echo time 1H spectroscopy. J Magn Reson Imaging 20(2):187–192
Ben-Hur A, Weston J (2010) A user’s guide to support vector machines. In: Methods in molecular biology. Data Mining Techniques for the Life Sciences, vol 609. Springer, Berlin, pp 223–239
Domingos P, Pazzani M (1997) On the optimality of the simple Bayesian classifier under zero-one loss. Mach Learn 29(2–3): 103–130
Friedman JH, Fayyad U (1997) On bias, variance, 0/1-loss, and the curse-of-dimensionality. Data Min Knowl Discov 1(1):55–77
Frank E, Trigg L, Holmes G, Witten IH (2000) Technical note: Naive Bayes for regression. Mach Learn 41(1):5–25
Williams N, Zander S, Armitage G (2006) A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification. ACM SIGCOMM Comput Commun Rev 36(5)
Cunningham P, Delany SJ (2007) k-Nearest Neighbour Classifiers. Technical Report UCD-CSI-2007-4
Conflict of interest
The authors declare that they have no conflict of interest.
Author information
Authors and Affiliations
Corresponding author
Additional information
Evangelia Tsolaki and Patricia Svolos contributed equally to this work.
Rights and permissions
About this article
Cite this article
Tsolaki, E., Svolos, P., Kousi, E. et al. Automated differentiation of glioblastomas from intracranial metastases using 3T MR spectroscopic and perfusion data. Int J CARS 8, 751–761 (2013). https://doi.org/10.1007/s11548-012-0808-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-012-0808-0