Advertisement

Accurate classification of childhood brain tumours by in vivo 1H MRS – A multi-centre study

Published:October 04, 2012DOI:https://doi.org/10.1016/j.ejca.2012.09.003

      Abstract

      Aims

      To evaluate the accuracy of single-voxel Magnetic Resonance Spectroscopy (1H MRS) as a non-invasive diagnostic aid for paediatric brain tumours in a multi-national study. Our hypotheses are (1) that automated classification based on 1H MRS provides an accurate non-invasive diagnosis in multi-centre datasets and (2) using a protocol which increases the metabolite information improves the diagnostic accuracy.

      Methods

      Seventy-eight patients under 16 years old with histologically proven brain tumours from 10 international centres were investigated. Discrimination of 29 medulloblastomas, 11 ependymomas and 38 pilocytic astrocytomas (PILOAs) was evaluated. Single-voxel MRS was undertaken prior to diagnosis (1.5 T Point-Resolved Spectroscopy (PRESS), Proton Brain Exam (PROBE) or Stimulated Echo Acquisition Mode (STEAM), echo time (TE) 20–32 ms and 135–136 ms). MRS data were processed using two strategies, determination of metabolite concentrations using TARQUIN software and automatic feature extraction with Peak Integration (PI). Linear Discriminant Analysis (LDA) was applied to this data to produce diagnostic classifiers. An evaluation of the diagnostic accuracy was performed based on resampling to measure the Balanced Accuracy Rate (BAR).

      Results

      The accuracy of the diagnostic classifiers for discriminating the three tumour types was found to be high (BAR 0.98) when a combination of TE was used. The combination of both TEs significantly improved the classification performance (p < 0.01, Tukey’s test) compared with the use of one TE alone. Other tumour types were classified accurately as glial or primitive neuroectodermal (BAR 1.00).

      Conclusion

      1H MRS has excellent accuracy for the non-invasive diagnosis of common childhood brain tumours particularly if the metabolite information is maximised and should become part of routine clinical assessment for these children.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to European Journal of Cancer
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Venkatramani R.
        • Dhall G.
        • Patel M.
        • et al.
        Supratentorial ependymoma in children: to observe or to treat following gross total resection?.
        Pediatr Blood Cancer. 2011; 58: 380-383
        • Horn B.
        • Heideman R.
        • Geyer R.
        • et al.
        A multi-institutional retrospective study of intracranial ependymoma in children: identification of risk factors.
        J Pediatr Hematol Oncol. 1999; 21: 203-211
        • Albright A.L.
        • Wisoff J.H.
        • Zeltzer P.M.
        • et al.
        Effects of medulloblastoma resections on outcome in children: a report from the children’s cancer group.
        Neurosurgery. 1996; 38: 265-271
        • Ogiwara H.
        • Bowman R.M.
        • Tomita T.
        Long-term follow-up of pediatric benign cerebellar astrocytomas.
        Neurosurgery. 2012; 70: 40-48
        • Kubben P.L.
        • ter Meulen K.J.
        • Schijns O.E.
        • et al.
        Intraoperative MRI-guided resection of glioblastoma multiforme: a systematic review.
        Lancet Oncol. 2011; 12: 1062-1070
        • Ellison D.
        • Kocak M.
        • Dalton J.
        • et al.
        Definition of disease-risk stratification groups in childhood medulloblastoma using combined clinical, pathologic, and molecular variables.
        J Clin Oncol. 2010; 29: 1400-1407
        • Peet A.
        • Davies N.
        • Ridley L.
        • et al.
        Magnetic resonance spectroscopy suggests key differences in the metastatic behaviour of medulloblastoma.
        Eur J Cancer. 2007; 6: 1037-1044
        • Tate A.R.
        • Underwood J.
        • Acosta D.M.
        • et al.
        Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra.
        NMR Biomed. 2006; 19: 411-434
        • Hagberg G.
        From magnetic resonance spectroscopy to classification of tumors. A review of pattern recognition methods.
        NMR Biomed. 1998; 11: 148-156
        • Menze B.H.
        • Lichy M.P.
        • Bachert P.
        • et al.
        Optimal classification of long echo time in vivo magnetic resonance spectra in the detection of recurrent brain tumors.
        NMR Biomed. 2006; 19: 599-609
        • Lukas L.
        • Devos A.
        • Suykens J.A.K.
        • et al.
        Brain tumor classification based on long echo proton MRS signals.
        Artif Intell Med. 2004; 31: 73-89
        • Simonetti A.W.
        • Melssen W.J.
        • Szabo de Edelenyi F.
        • et al.
        Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification.
        NMR Biomed. 2005; 18: 34-43
        • Devos A.
        • Lukas L.
        • Suykens J.A.K.
        • et al.
        Classification of brain tumours using short echo time 1H MR spectra.
        J Magn Reson. 2004; 170: 164-175
        • Huang Y.
        • Lisboa P.J.G.
        • El-Deredy W.
        Tumour grading from magnetic resonance spectroscopy: a comparison of feature extraction with variable selection.
        Stat Med. 2003; 22: 147-164
        • García-Gómez J.M.
        • Luts J.
        • Julià-Sapé M.
        • et al.
        Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy.
        Magn Reson Mater Phys Biol Med. 2009; 22: 5-18
        • Pollack I.F.
        Brain tumors in children [review].
        N Engl J Med. 1994; 331: 1501-1507
        • Pollack I.F.
        Pediatric brain tumors.
        Semin Surg Oncol. 1999; 16: 73-90
        • Imamura K.
        Proton MR spectroscopy of the brain with a focus in chemical issues.
        Mag Reson Med Sci. 2003; 2: 117-132
        • Rossi A.
        • Gandolfo C.
        • Morana G.
        • et al.
        New MR sequences (diffusion, perfusion, spectroscopy) in brain tumours.
        Pediatr Radiol. 2010; 40: 999-1009
        • García-Gómez J.M.
        • Tortajada S.
        • Vidal C.
        • et al.
        The effect of combining two echo times in automatic brain tumor classification by MRS.
        NMR Biomed. 2008; 21: 1112-1125
      1. eTUMOUR Consortium. eTumour: web accessible MR decision support system for brain tumour diagnosis and prognosis, incorporating in vivo and ex vivo genomic and metabolomic data. Available from: FP6-2002-LIFESCIHEALTH 503094, VI framework programme, EC, http://www.etumour.net [accessed 20.02.12].

        • van der Graaf M.
        • Julià-Sapé M.
        • Howe F.A.
        • et al.
        MRS quality assessment in a multicentre study on MRS-based classification of brain tumours.
        NMR Biomed. 2008; 21: 148-158
        • Louis D.N.
        • Ohgaki H.
        • Wiestler O.D.
        • et al.
        WHO classification of tumours of the central nervous system.
        IARC Press, Lyon, France2007
        • Julià-Sapé M.
        • Acosta D.
        • Mier M.
        • et al.
        A multi-centre, web-accessible and quality control-checked database of in vivo MR spectra of brain tumour patients.
        Magn Reson Mater Phys. 2006; 19: 22-33
        • Wilson M.
        • Reynolds G.
        • Kauppinen R.A.
        • et al.
        A constrained least-squares approach to the automated quantitation of in vivo 1H magnetic resonance spectroscopy data.
        Magn Reson Med. 2011; 65: 1-12
        • Luts J.
        • Poullet J.-B.
        • García-Gómez J.M.
        • et al.
        Effect of feature extraction for brain tumor classification based on short echo time 1H MR spectra.
        Magn Reson Med. 2008; 60: 288-298
        • Wang Z.
        • Sutton L.N.
        • Cnaan A.
        • et al.
        Proton MR spectroscopy of pediatric cerebellar tumors.
        Am J Neuroradiol. 1995; 16: 1821-1833
        • Arle J.E.
        • Morriss C.
        • Wang Z.J.
        • et al.
        Prediction of posterior fossa tumor type in children by means of magnetic resonance image properties, spectroscopy, and neural networks.
        J Neurosurg. 1997; 86: 755-761
        • Schneider J.F.
        • Confort-Gouny S.
        • Viola A.
        • et al.
        Multiparametric differentiation of posterior fossa tumors in children using diffusion-weighted imaging and short echo-time 1H-MR spectroscopy.
        J Magn Reson Imaging. 2007; 26: 1390-1398
        • Davies N.P.
        • Wilson M.
        • Harris L.M.
        • et al.
        Identification and characterisation of childhood cerebellar tumours by in vivo proton MRS.
        NMR Biomed. 2008; 21: 908-918
      2. Guyon I, Alamdari ARSA, Dror G, et al. Performance prediction challenge. In: IJCNN ’06. International joint conference on neural networks; 2006. p. 1649–56.

        • Remy C.
        • Fouilhe N.
        • Barba I.
        • et al.
        Evidence that mobile lipids detected in rat brain glioma by 1H nuclear magnetic resonance correspond to lipid droplets.
        Cancer Res. 1997; 57: 407-414
      3. Martinez-Pérez I, Moreno A, Barba I, et al. Large lipid droplets observed by electron microscopy in six human brain tumors with lipid 1H MRS in vivo pattern. In: Abstracts of Soc Magn Reson Med, New York; 1996. p. 976.

        • Panigrahy A.
        • Krieger M.D.
        • Gonzalez-Gomez I.
        • et al.
        Quantitative short echo time 1H-MR spectroscopy of untreated pediatric brain tumors: preoperative diagnosis and characterization.
        Am J Neuroradiol. 2006; 27: 560-572
        • Peet A.C.
        • Lateef S.
        • MacPherson L.
        • et al.
        Short echo time 1H magnetic resonance spectroscopy of childhood brain tumours.
        Childs Nerv Syst. 2007; 23: 163-169
        • Moreno-Torres A.
        • Martínez-Pérez I.
        • Baquero M.
        • et al.
        Taurine detection by proton magnetic resonance spectroscopy in medulloblastoma: contribution to noninvasive differential diagnosis with cerebellar astrocytoma.
        Neurosurgery. 2004; 4: 824-8295
      4. Sáez C, García-Gómez J, Vicente J, et al. Curiam BT 1.0, decision support system for brain tumour diagnosis. In: ESMRMB 2009 congress: EPOS posters, paper posters, Info-RESO, vol. 22 (Antalya, Turkey). Berlin, Heidelberg: Springer; May 2009. p. 538.

        • Sáez C.
        • García-Gómez J.M.
        • Vicente J.
        • et al.
        A generic and extensible automatic classification framework applied to brain tumour diagnosis in HealthAgents.
        Knowl Eng Rev. 2011; 26: 283-301