Artificial Intelligence in Medicine
Volume 40, Issue 2 , Pages 87-102 , June 2007

A combined MRI and MRSI based multiclass system for brain tumour recognition using LS-SVMs with class probabilities and feature selection

  • Jan Luts

      Affiliations

    • Katholieke Universiteit Leuven, Department of Electrical Engineering, ESAT-SCD (SISTA), Kasteelpark Arenberg 10, B-3001 Leuven-Heverlee, Belgium
    • Corresponding Author InformationCorresponding author. Tel.: +32 16 321065; fax: +32 16 321970.
    • ,
  • Arend Heerschap

      Affiliations

    • University of Nijmegen, University Medical Center Sint Radboud, Department of Radiology, Geert Grooteplein Z18, PO Box 9101, 6500 HB Nijmegen, The Netherlands
    • ,
  • Johan A.K. Suykens

      Affiliations

    • Katholieke Universiteit Leuven, Department of Electrical Engineering, ESAT-SCD (SISTA), Kasteelpark Arenberg 10, B-3001 Leuven-Heverlee, Belgium
    • ,
  • Sabine Van Huffel

      Affiliations

    • Katholieke Universiteit Leuven, Department of Electrical Engineering, ESAT-SCD (SISTA), Kasteelpark Arenberg 10, B-3001 Leuven-Heverlee, Belgium

Received 7 July 2006 ,Revised 20 February 2007 ,Accepted 26 February 2007.

References 

  1. Danielsen RE, Ross B. Magnetic resonance spectroscopy diagnosis of neurological diseases. New York: Marcel Dekker Inc.; 1999;
  2. Preul MC, Caramanos Z, Collins DL, Villemure JG, Leblanc R, Olivier A, et al. Accurate, noninvasive diagnosis of human brain tumors by using proton magnetic resonance spectroscopy. Nat Med. 1996;2:323–325
  3. Szabo de Edelenyi F, Rubin C, Esteve F, Grand S, Decorps M, Lefournier V, et al. A new approach for analyzing proton magnetic resonance spectroscopic images of brain tumors: nosologic images. Nat Med. 2000;6:1287–1289
  4. International network for pattern recognition of tumours using magnetic resonance., http://azizu.uab.es/INTERPRET/ (Accessed: 3 December 2006).
  5. Tate AR, Underwood J, Acosta DM, Julia-Sape M, Majos C, Moreno-Torres A, et al. 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. 2006;19(4):411–434
  6. Earnest F, Kelly PJ, Scheithauer BW, Kall BA, Cascino TL, Ehman RL, et al. Cerebral astrocytomas: histopathologic correlation of MR and CT contrast enhancement with stereotactic biopsy. Radiology. 1988;166:823–827
  7. Dean BL, Drayer BP, Bird CR, Flom RA, Hodak JA, Coons SW, et al. Gliomas: classification with MR imaging. Radiology. 1990;174:411–415
  8. Preul MC, Caramanos Z, Leblanc R, Villemure JG, Arnold DL. Using pattern analysis of in vivo proton MRSI data to improve the diagnosis and surgical management of patients with brain tumors. Nucl Magn Reson Biomed. 1998;11:192–200
  9. Poptani H, Kaartinen J, Gupta RK, Niemitz M, Hiltunen Y, Kauppinen RA. Diagnostic assessment of brain tumours and non-neoplastic brain disorders in vivo using proton nuclear magnetic resonance spectroscopy and artificial neural networks. J Cancer Res Clin Oncol. 1999;125:343–349
  10. Lindon JC, Holmes E, Nicholson JK. Pattern recognition methods and applications in biomedical magnetic resonance. Prog Nucl Magn Reson Spectrosc. 2001;39:1–40
  11. Ye CZ, Yang J, Geng DY, Zhou Y, Chen NY. Fuzzy rules to predict degree of malignancy in brain glioma. Med Biol Eng Comput. 2002;40:145–152
  12. Tate AR, Majos C, Moreno A, Howe FA, Griffiths JR, Arus C. Automated classification of short echo time in in vivo 1H brain tumor spectra: a multicenter study. Magn Reson Med. 2003;49:29–36
  13. Devos A, Lukas L, Suykens JAK, Vanhamme L, Tate AR, Howe FA, et al. Classification of brain tumours using short echo time 1H MR spectra. J Magn Reson. 2004;170:164–175
  14. Simonetti AW, Melssen WJ, van der Graaf M, Heerschap A, Buydens LMC. A new chemometric approach for brain tumor classification using magnetic resonance imaging and spectroscopy. Anal Chem. 2003;75:5352–5361
  15. Devos A, Simonetti AW, van der Graaf M, Lukas L, Suykens JAK, Vanhamme L, et al. The use of multivariate MR imaging intensities versus metabolic data from MR spectroscopic imaging for brain tumour classification. J Magn Reson. 2005;173:218–228
  16. Suykens JAK, Vandewalle J. Least squares support vector machine classifiers. Neural Process Lett. 1999;9(3):293–300
  17. Suykens JAK, Van Gestel T, De Brabanter J, De Moor B, Vandewalle J. Least squares support vector machines. Singapore: World Scientific; 2002;
  18. Van Gestel T, Suykens JAK, Lanckriet G, Lambrechts A, De Moor B, Vandewalle J. Bayesian framework for least squares support vector machine classifiers, Gaussian processes and kernel Fisher discriminant analysis. Neural Comput. 2002;14:1115–1147
  19. Abe S. Support vector machines for pattern classification. New York: Springer-Verlag; 2005;
  20. Simonetti AW, Melssen WJ, Szabo de Edelenyi F, van Asten JJA, Heerschap A, Buydens LMC. Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification. Nucl Magn Reson Biomed. 2005;18:34–43
  21. Wehrens R, Simonetti AW, Buydens LMC. Mixture modelling of medical magnetic resonance data. J Chemometrics. 2002;16:274–282
  22. Klose U. In vivo proton spectroscopy in presence of eddy currents. Magn Reson Med. 1990;14:26–30
  23. Simonetti AW, Melssen WJ, van der Graaf M, Heerschap A, Buydens LMC. Automated correction of unwanted phase jumps in reference signals which corrupt MRSI spectra after eddy current correction. J Magn Reson. 2002;159:151–157
  24. Pijnappel WWF, van den Boogaart A, de Beer R, van Ormondt D. SVD-based quantification of magnetic resonance signals. J Magn Reson. 1992;97:122–134
  25. Tong Z, Yamaki T, Harada K, Houkin K. In vivo quantification of the metabolites in normal brain and brain tumors by proton MR spectroscopy using water as an internal standard. Magn Reson Imag. 2004;22:735–742
  26. Govindaraju V, Young K, Maudsley AA. Proton NMR chemical shifts and coupling constants for brain metabolites. Nucl Magn Reson Biomed. 2000;13:129–153
  27. Luts J., Heerschap A., Suykens J., Van Huffel S., MRI and MRSI based multiclass system for brain tumour recognition using LS-SVMs, Internal Report 06–143, ESAT-SISTA, K.U. Leuven (Leuven, Belgium).
  28. Blumer A, Ehrenfeucht A, Haussler D, Marmuth MK. Occam’s razor. Inform Process Lett. 1987;24:377–380
  29. Wettschereck D, Aha DW, Mohri T. A review and empirical evaluation of feature weighting methods for a class of lazy learning algorithms. Artif Intell Rev. 1997;11:273–314
  30. Kohavi R, John GH. Wrappers for feature subset selection. Artif Intell. 1997;97:273–324
  31. Blum A, Langley P. Selection of relevant features and examples in machine learning. Artif Intell. 1997;97:245–271
  32. Dietterich TG. Machine learning research: four current directions. Artif Intell Magn. 1998;18:97–136
  33. Almuallim H, Dietterich TG. Learning with many irrelevant features. In: Proceedings of the ninth national conference on artificial intelligence (AAAI-91), vol. 2. AAAI Press, Anaheim, California. 1991;p. 547–552
  34. Kira K, Rendell LA. A practical approach to feature selection. In:  Sleeman DH,  Edwards P editor. The ninth international workshop on machine learning. Morgan Kaufmann, Palo Alto. 1992;p. 249–256
  35. John GH, Kohavi R, Pfleger K. Irrelevant features and the subset selection problem. In: International conference on machine learning. Morgan Kaufmann, Palo Alto. 1994;p. 121–129
  36. Neter J, Kutner MH, Wasserman W, Nachtsheim CJ. Applied linear statistical models. Boston: McGraw-Hill/Irwin; 1996;
  37. Ginsberg ML. Essentials of artificial intelligence. Palo Alto: Morgan Kaufmann; 1993;
  38. Robnik-Sikonja M, Kononenko I. Theoretical and empirical analysis of ReliefF and RReliefF. Mach Learn. 2003;53:23–69
  39. Van Gestel T, Suykens JAK, De Moor B, Vandewalle J. Automatic relevance determination for least squares support vector machine classifiers. In: European symposium on artificial neural networks. D-facto publications, Evere. 2001;p. 13–18
  40. Fisher RA. The use of multiple measurements in taxonomic problems. Ann Eugenics. 1936;7:179–188
  41. Hollander M, Wolfe DA. Nonparametric statistical methods. New York: Wiley; 1973;
  42. Hogg RV, Ledolter J. Engineering statistics. New York: MacMillan; 1987;
  43. MacKay DJC. Introduction to gaussian processes. In:  Bishop CM editors. Neural networks and machine learning, vol. 168, NATO advanced study institute. Berlin: Springer-Verlag; 1998;
  44. Suykens JAK, Vandewalle J. Multiclass least squares support vector machines. In: Proceedings international joint conference on neural networks (IJCNN’99). Washington DC. 1999;
  45. Dietterich TG, Bakiri G. Solving multiclass learning problems via error-correcting output codes. J Artif Intell Res. 1995;2:263–286
  46. Allwein E, Schapire R, Singer Y. Reducing multiclass to binary: a unifying approach for margin classifiers. J Mach Learn Res. 2000;1:113–141
  47. Kressel UH-G. Pairwise classification and support vector machines. In:  Scholkopf B,  Burges CCJ,  Smola AJ editor. Advances in kernel methods: support vector learning. Cambridge: MIT Press; 1999;
  48. Price D, Knerr S, Personnaz L, Dreyfus G. Pairwise neural network classifiers with probabilistic outputs. Neural Inform Process Syst. 1994;7:1109–1116
  49. Hastie T, Tibshirani R. Classification by pairwise coupling. Ann Stat. 1998;26:451–471
  50. Wu T, Lin C, Weng R. Probability estimates for multi-class classification by pairwise coupling. J Mach Learn Res. 2004;5:975–1005
  51. Refregier P, Vallet F. Probabilistic approach for multiclass classification with neural networks. In: Proceedings of international conference on artificial networks. Amsterdam: North-Holland; 1991;p. 1003–1007
  52. Friedman J., Another approach to polychotomous classification, Technical report (1996). Stanford University.
  53. Hochberg Y, Tamhane AC. Multiple comparison procedures. New York: Wiley; 1987;
  54. Brier GW. Verification of forecasts expressed in probabilities. Monthly Weather Rev. 1950;1–3
  55. McLachlan GJ. Discriminant analysis and statistical pattern recognition. New York: Wiley; 1992;
  56. Simonetti A.W., Investigation of brain tumor classification and its reliability using chemometrics on MR spectroscopy and MR imaging data, PhD thesis, University of Nijmegen.
  57. The eTUMOUR consortium., http://www.etumour.net/ (Accessed: 3 December 2006).
  58. The HealthAgents project., http://www.healthagents.net/ (Accessed: 3 December 2006).

PII: S0933-3657(07)00018-8

doi: 10.1016/j.artmed.2007.02.002

Artificial Intelligence in Medicine
Volume 40, Issue 2 , Pages 87-102 , June 2007

Article Tools

* Image Usage & Resolution