Advertisement

Compatibility between 3T 1H SV-MRS data and automatic brain tumour diagnosis support systems based on databases of 1.5T 1H SV-MRS spectra

  • Elies Fuster-Garcia
  • Clara Navarro
  • Javier Vicente
  • Salvador Tortajada
  • Juan M. García-Gómez
  • Carlos Sáez
  • Jorge Calvar
  • John Griffiths
  • Margarida Julià-Sapé
  • Franklyn A. Howe
  • Jesús Pujol
  • Andrew C. Peet
  • Arend Heerschap
  • Àngel Moreno-Torres
  • M. C. Martínez-Bisbal
  • Beatriz Martínez-Granados
  • Pieter Wesseling
  • Wolfhard Semmler
  • Jaume Capellades
  • Carles Majós
  • Àngel Alberich-Bayarri
  • Antoni Capdevila
  • Daniel Monleón
  • Luis Martí-Bonmatí
  • Carles Arús
  • Bernardo Celda
  • Montserrat Robles
Research Article

Abstract

Object

This study demonstrates that 3T SV-MRS data can be used with the currently available automatic brain tumour diagnostic classifiers which were trained on databases of 1.5T spectra. This will allow the existing large databases of 1.5T MRS data to be used for diagnostic classification of 3T spectra, and perhaps also the combination of 1.5T and 3T databases.

Materials and methods

Brain tumour classifiers trained with 154 1.5T spectra to discriminate among high grade malignant tumours and common grade II glial tumours were evaluated with a subsequently-acquired set of 155 1.5T and 37 3T spectra. A similarity study between spectra and main brain tumour metabolite ratios for both field strengths (1.5T and 3T) was also performed.

Results

Our results showed that classifiers trained with 1.5T samples had similar accuracy for both test datasets (0.87 ± 0.03 for 1.5T and 0.88 ± 0.03 for 3.0T). Moreover, non-significant differences were observed with most metabolite ratios and spectral patterns.

Conclusion

These results encourage the use of existing classifiers based on 1.5T datasets for diagnosis with 3T 1H SV-MRS. The large 1.5T databases compiled throughout many years and the prediction models based on 1.5T acquisitions can therefore continue to be used with data from the new 3T instruments.

Keywords

Brain tumours Magnetic resonance spectroscopy Clinical decision support systems 

Abbreviations

1H SV-MRS

Single voxel proton magnetic resonance spectroscopy

ACC

Accuracy

ANN

Artificial neural networks

CDSS

Clinical decision support systems

CG2G

Common grade II glial

G

Geometric mean of recalls

HGM

High grade malignant

KNN

k-nearest neighbors

LDA

Linear discriminant analysis

PI

Peak integration

SNR

Signal-to-noise ratio

SW

Stepwise

TE

Echo time

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    García-Gómez JM, Luts J, Julià-Sapé M, Krooshof P, Tortajada S, Vicente Robledo J, Melssen W, Fuster-García E, Olier I, Postma G, Monleón D, Moreno-Torres À, Pujol J, Candiota AP, Martínez-Bisbal M, Suykens J, Buydens L, Celda B, Van Huffel S, Arús C, Robles M (2009) Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy. Magn Reson Mater Phy 22: 5–18CrossRefGoogle Scholar
  2. 2.
    Lukas L, Devos A, Suykens JAK, Vanhamme L, Howe FA, Majós C, Moreno-Torres A, Vander Graaf M, Tate AR, Arús C, Van Huffel S (2004) Brain tumor classification based on long echo proton MRS signals. Artif Intell Med 31: 73–89CrossRefPubMedGoogle Scholar
  3. 3.
    Devos A, Lukas L, Suykens JAK, Vanhamme L, Tate AR, Howe FA, Majos C, Moreno-Torres A, Van der Graaf M, Arús C, Van Huffel S (2004) Classification of brain tumours using short echo time 1H MR spectra. J Magn Reson 170: 164–175CrossRefPubMedGoogle Scholar
  4. 4.
    Tate AR, Majós C, Moreno A, Howe FA, Griffiths JR, Arús C (2003) Automated classification of short echo time in in vivo 1H brain tumor spectra: a multicenter study. Magn Reson Med 49: 29–36CrossRefPubMedGoogle Scholar
  5. 5.
    Tate AR, Underwood J, Acosta DM, Julià-Sapé M, Majós C, Moreno-Torres A, Howe FA, Van der Graaf M, Lefournier V, Murphy MM, Loosemore A, Ladroue C, Wesseling P, Luc Bosson J, Cabanas ME, Simonetti AW, Gajewicz W, Calvar J, Capdevila A, Wilkins PR, Bell BA, Remy C, Heerschap A, Watson D, Griffiths JR, Arús C (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: 411–434CrossRefPubMedGoogle Scholar
  6. 6.
    Celda B, Monleón D, Martínez-Bisbal MC, Esteve V, Martínez-Granados B, Piñero E, Ferrer R, Piquer J, Martí-Bonmatí L, Cervera J (2006) MRS as endogenous molecular imaging for brain and prostate tumors: FP6 project “eTUMOR”. Adv Exp Med Biol 587: 285–302CrossRefPubMedGoogle Scholar
  7. 7.
    Laudadio T, Martínez-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: 311–321CrossRefPubMedGoogle Scholar
  8. 8.
    Martínez-Bisbal M, Celda B, Martí-Bonmatí L, Ferrer P, Revert A, Piquer J, Mollá E, Arana E, Dosdá R (2002) Contribution of magnetic resonance spectroscopy to the classification of hogh glial tumours. Predictive value of macromolecules. Rev Neurol 34: 309–313PubMedGoogle Scholar
  9. 9.
    Opstad K, Provencher S, Bell B, Griffiths J, Howe F (2009) Detection of elevated glutathione in meningiomas by quantitative in vivo 1H MRS. Magn Reson Med 49: 632–637CrossRefGoogle Scholar
  10. 10.
    Sundgren P, Nagesh V, Elias A, Tsien C, Junck L, Gomez~Hassan D, Lawrence T, Chenevert T, Rogers L, McKeever P, Cao Y (2003) Metabolic alterations: a biomarker for radiation-induced normal brain injury-an MR spectroscopy study. J Magn Reson Imaging 29: 291–297CrossRefGoogle Scholar
  11. 11.
    Hattingen E, Raab P, Franz K, Lanfermann H, Setzer M, Gerlach R, Zanella F, Pilatus U (2008) Prognostic value of choline and creatine in WHO grade II gliomas. Neuroradiology 50: 759–767CrossRefPubMedGoogle Scholar
  12. 12.
    Server A, Josefsen R, Kulle B, Maehlen J, Schellhorn T, Gadmar, Kumar T, Haakonsen M, Langberg C, Nakstad P (2010) Proton magnetic resonance spectroscopy in the distinction of high-grade cerebral gliomas from single metastatic brain tumors. Acta Radiol 51: 316–325CrossRefPubMedGoogle Scholar
  13. 13.
    Theodoridis S, Koutroumbas K (2006) Pattern recognition. 3rd edn. Academic Press, San DiegoGoogle Scholar
  14. 14.
    Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New YorkGoogle Scholar
  15. 15.
    Duda RO, Hart PE, Stork DG (2000) Pattern classification. 2nd edn. Wiley-Interscience, New YorkGoogle Scholar
  16. 16.
    Kim J, Chang K, Na DG, Song IC, Kim SJ, Kwon BJ, Han MH (2006) Comparison of 1.5T and 3T 1H-MR spectroscopy for human brain tumors. Korean J Radiol 7: 156–161CrossRefPubMedGoogle Scholar
  17. 17.
    Barker PB, Hearshen DO, Boska MD (2001) Single-voxel proton MRS of the human brain at 1.5T and 3.0T. Magn Reson Med 45: 765–769CrossRefPubMedGoogle Scholar
  18. 18.
    Roser W, Hagberg G, Mader I, Dellas S, Seelig J, Radue E, Steinbrich W (1997) Assignment of glial brain tumors in humans by in vivo 1H-magnetic resonance spectroscopy and multidimensional metabolic classification. Magn Reson Mater Phy 5: 179–183CrossRefGoogle Scholar
  19. 19.
    Berner, ES (eds) (2007) Clinical decision support systems: theory and practice. Springer, New YorkGoogle Scholar
  20. 20.
    Sim I, Gorman P, Greenes RA, Haynes RB, Kaplan B, Lehmann H, Tang PC (2001) Clinical decision support systems for the practice of evidence-based medicine. J Am Med Inform Assn 8: 527–534Google Scholar
  21. 21.
    González-Vélez H, Mier M, Julià-Sapé M, Arvanitis T, García-Gómez JM, Robles M, Lewis P, Dasmahapatra S, Dupplaw D, Peet A, Arús C, Celda B, Van Huffel S, Lluch-Ariet M (2009) HealthAgents: distributed multi-agent brain tumor diagnosis and prognosis. Appl Intell 30: 191–202CrossRefGoogle Scholar
  22. 22.
    Sáez C, García-Gómez JM, Vicente J, Tortajada S, Esparza M, Navarro A, Fuster-Garcia E, Robles M, Martí-Bonmatí L, Arús C (2008) A generic decision support system featuring an assembled view of predictive models for magnetic Resonance and clinical data. In: ESMRMB 25th annual meeting, Valencia, 2–4. SpringerGoogle Scholar
  23. 23.
    García-Gómez JM, Tortajada S, Vidal C, Julia-Sape M, Luts J, Van Huffel S, Arús C, Robles M (2008) The influence of combining two echo times in automatic brain tumor classification by Magnetic Resonance Spectroscopy. NMR Biomed 21: 1112–1125CrossRefPubMedGoogle Scholar
  24. 24.
    The eTUMOUR Consortium (2007) eTUMOUR: web accessible MR decision support system for brain tumour diagnosis and prognosis, incorporating in vivo and ex vivo genomic and metabolomic data, VI framework programme, EC, http://www.etumour.net. Technical Report FP6-2002-LIFESCIHEALTH 503094
  25. 25.
    Vander Graaf M, Juliá-Sapè M, Howe FA, Ziegler A, Majós C, Moreno-Torres A, Rijpkema M, Acosta D, Opstad KS, Van der Meulen Y, Arús C, Heerschap A (2008) MRS quality assessment in a multicentre study on MRS-based classification of brain tumours. NMR Biomed 21: 148–158CrossRefGoogle Scholar
  26. 26.
    Pérez-Ruiz A, Olier-Caparroso IA, Julià-Sapé M, Candiota AP, Arús C (2008) Brain tumor diagnosis with MRS: the single voxel INTERPRET decision-support system version 2.0. In: ESMRMB 25th annual meeting, Valencia, 2–4. Magn Reson Mater PhyGoogle Scholar
  27. 27.
    Klose U (1990) In vivo proton spectroscopy in presence of eddy currents. Magn Reson Med 14: 26–30CrossRefPubMedGoogle Scholar
  28. 28.
    Van den Boogaart A, Van Hecke P, Van Huffel S, Graveron-Demilly S, Van Ormondt D, de Beer R (1996) MRUI: a graphical user interface for accurate routine MRS data analysis. In: ESMRMB 13th annual meeting, Prague, 12–15. SpringerGoogle Scholar
  29. 29.
    Luts J, Poullet J, Garcia-Gomez J, Heerschap A, Robles M, Suykens J, Van Huffel S (2008) Effect of feature extraction for brain tumor classification based on short echo time 1H MR spectra. Magn Reson Mater Phy 60: 88–98Google Scholar
  30. 30.
    Russell SJ, Norvig P (1995) Artificial intelligence: a modern approach. Prentice-Hall, Upper Saddle RiverGoogle Scholar
  31. 31.
    Opstad KS, Ladroue C, Bell BA, Griffiths JR, Howe FA (2007) Linear discriminant analysis of brain tumour 1H MR spectra: a comparison of classification using whole spectra versus metabolite quantification. NMR Biomed 20: 763–770CrossRefPubMedGoogle Scholar
  32. 32.
    Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugenic 7: 179–188Google Scholar
  33. 33.
    Kubat M, Matwin S (1997) Addressing the curse of imbalanced training sets: one-sided selection. In: Proceedings of 14th international conference on machine learning, pp 179–186. Morgan KaufmannGoogle Scholar
  34. 34.
    Giraud-Carrier C (2000) A note on the utility of incremental learning. AI Commun 13: 215–223Google Scholar
  35. 35.
    Gonen O, Gruber S, Li B, Mlynrik V, Moser E (2001) Multivoxel 3D proton spectroscopy in the brain at 1.5 versus 3.0 T: signal-to-noise ratio and resolution comparison. Am J Neuroradiol 22: 1727–1731PubMedGoogle Scholar
  36. 36.
    Dydak U, Meier D, Lamerichs R, Boesiger P (2006) Effect of feature extraction for brain tumor classification based on short echo time 1H MR spectra. Am J Neuroradiol 27: 1441–1446PubMedGoogle Scholar

Copyright information

© ESMRMB 2011

Authors and Affiliations

  • Elies Fuster-Garcia
    • 1
    • 2
  • Clara Navarro
    • 3
  • Javier Vicente
    • 2
  • Salvador Tortajada
    • 2
  • Juan M. García-Gómez
    • 2
  • Carlos Sáez
    • 2
  • Jorge Calvar
    • 4
  • John Griffiths
    • 5
  • Margarida Julià-Sapé
    • 6
    • 7
    • 8
  • Franklyn A. Howe
    • 9
  • Jesús Pujol
    • 6
    • 10
  • Andrew C. Peet
    • 11
  • Arend Heerschap
    • 12
  • Àngel Moreno-Torres
    • 6
    • 13
  • M. C. Martínez-Bisbal
    • 6
    • 14
  • Beatriz Martínez-Granados
    • 14
  • Pieter Wesseling
    • 12
  • Wolfhard Semmler
    • 15
  • Jaume Capellades
    • 16
  • Carles Majós
    • 6
    • 17
  • Àngel Alberich-Bayarri
    • 3
  • Antoni Capdevila
    • 13
  • Daniel Monleón
    • 18
  • Luis Martí-Bonmatí
    • 3
  • Carles Arús
    • 6
    • 7
    • 8
  • Bernardo Celda
    • 14
  • Montserrat Robles
    • 2
  1. 1.Universitat Internacional ValencianaValenciaSpain
  2. 2.Biomedical Mining Group, IBIME, Instituto de Aplicaciones de las Tecnologías de la Información y de las Comunicaciones Avanzadas (ITACA)Universidad Politécnica de ValenciaValenciaSpain
  3. 3.Radiology DepartmentQuirón Valencia HospitalValenciaSpain
  4. 4.Institute for Neurological Research (FLENI)Buenos AiresArgentina
  5. 5.CR UK Cambridge Research Institute CambridgeCambridgeUK
  6. 6.Networking Research Center on Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN)ZaragozaSpain
  7. 7.Department of Biochemistry and Molecular BiologyUniversitat Autònoma de BarcelonaCerdanyola del VallèsSpain
  8. 8.Institut de Biotecnologia i Biomedicina (IBB)Universitat Autònoma de Barcelona (UAB)Cerdanyola del VallèsSpain
  9. 9.Cardiac and Vascular SciencesSt. George’s, University of LondonLondonUK
  10. 10.CRC Corporació Sanitària, Institut d’Alta Tecnologia-PRBBBarcelonaSpain
  11. 11.Academic Department of Paediatrics and Child HealthUniversity of BirminghamBirminghamUK
  12. 12.Nijmegen Medical Centre, Radiology and PathologyRadboud UniversityNijmegenThe Netherlands
  13. 13.Research DepartmentCentre Diagnòstic PedralbesEsplugues de LlobregatSpain
  14. 14.Physical-ChemistryUniversity of ValenciaBurjassot, ValenciaSpain
  15. 15.Department of Medical Physics in RadiologyGerman Cancer Research Center (DKFZ)HeidelbergGermany
  16. 16.Hospital Universitari Germans Trias i PujolBadalonaSpain
  17. 17.Hospital Universitari de BellvitgeInstitut de Diagnóstic per la Imatge, L´Hospitalet de LlobregatBarcelonaSpain
  18. 18.Fundación Investigacion Hospital Clínico Valencia /INCLIVAValenciaSpain

Personalised recommendations