Abstract
In this paper, a synergy of advanced signal processing and soft computing strategies is applied in order to identify different types of human brain tumors, as a help to confirm the histological diagnosis of experts and consequently to facilitate the decision about the correct treatment or the necessity of an operation. A computational tool has been developed that merges, on the one hand, wavelet transform to reduce the size of the biomedical spectra and to extract the main features, and on the other hand, Support Vector Machine and Neural Networks to classify them. The influence of some of the configuration parameters of each of those soft computing techniques on the clustering is analyzed. These two methods and another one based on medical knowledge are compared. The classification results obtained by these computational tools are promising specially taking into account that medical knowledge has not been considered and that the number of samples of each class is very low in some cases.
Similar content being viewed by others
References
Daubechies I (1992) Ten lectures on wavelets: CBMS lectures series. SIAM, Philadelphia
Demuth H, Beale M (1998) Neural network toolbox user’s guide. The MathWorks Inc, USA
Duda RO, Hart PE, Stork D (2001) Pattern classification. Wiley, New York
Farias G, Santos M (2005) Analysis of the wavelet transform parameters in images processing. LNCCS 2:51–54
Farias G, Santos M, López V (2008) Brain tumour diagnosis with wavelets and support vector machines. Proceedings of the 3rd IEEE international conference on intelligent systems and knowledge engineering, pp 1453–1459
García-Martín ML, Hérigault G, Rémy CH, Farion R, Ballesteros P, Coles J, Cerdán S (2001) Mapping extracellular pH in rat brain gliomas “in vivo” by H magnetic resonance spectroscopic imaging: comparison with maps of metabolites. Cancer Res 61:6524–6531
Hagberg G (1998) From magnetic resonance spectroscopy to classification tumors: a review of pattern recognition methods. NMR Biomed 11:148–156
Haykin S (1999) Neural networks: a comprehensive foundation, 2nd. edn. Prentice-Hall, Upper Saddle River, NJ
Hore P (1983) Solvent suppression in Fourier Transform nuclear magn. reson. J Magn Reson 55:283–300
Howells SL, Maxwell R, Griffiths JR (1992) An investigation of tumor 1H NMR spectra by pattern recognition. NMR Biomed 5:59–64
Kim I, Watada J, Shigaki I (2008) Complementary case-based reasoning and competitive fuzzy cognitive maps for advanced medical decision. Soft Comput 12:191–199
Kinoshita Y, Yokota A (1997) Absolute concentrations of metabolites in human brain tumours using in vitro proton magn. reson. spectroscopy. NMR Biomed 10:2–12
Laguna P, Moody GB, García J, Goldberger AL, Mark RG (1999) Analysis of the ST-T complex using the KL transform: adaptative monitoring and alternant detection. Med Biol Eng Comput 37(2):175–189
Mallat SG (2001) A wavelet tour of signal processing, 2nd edn. Academic Press, San Diego
Martínez-Pérez I, Maxwell RJ, Howells SL, van der Bogaart A, Mazucco R, Griffiths JR, Arús C (1995) Pattern recognition analysis of 1H NMR spectra from human brain tumours biopsies. Proceedings Soc magnetic resonance. 3rd annual meeting Abstract P1709
MathWorks Inc (1989) MATLAB®, MA, USA
Maxwell RJ, Martínez-P. I, Cerdán S, Cabañas ME, Arús C, Moreno A, Capdevila A, Ferrer E, Bartomeus F, Aparicio A, Conesa G, Roda JM, Carceller F, Pascual JM, Howells SL, Mazzuco R, Griffiths J (1998) Pattern recognition analysis oh 1H NMR spectra from perchloric acid extracts of human brain tumor biopsies. Magn Reson Med 39:869–877
Misiti M, Misiti Y, Oppenheim G, Poggi J-M (1997) Users Guide: Wavelet Toolbox for use with MATLAB. The MathWorks, Inc, Natick
Pascual J, Carceller F, Cerdán S, Roda JM (1998) Diagnóstico diferencial de tumores cerebrales “in vitro” por espectroscopia de resonancia magnética de protón. Método de los cocientes espectrales. Neurocirugía 9:4–10
Peeling J, Sutherland G (1992) High-resolution 1H NMR spectroscopy studies of extracts of human cerebral neoplasm. Magn Reson Med 24:123–136
Rafiei D, Mendelzon A (1998) Efficient retrieval of similar time sequences using DFT. Proceedings of the 5th international conference on foundations of data organization, pp 249–257
Roda JM, Pascual JM, Carceller F, Gonzalez-Llanos F (2000) Nonhistological diagnosis of human cerebral tumors by 1H magnetic resonance spectroscopy and amino acid analysis. Clin Cancer Res 6:3983–3993
Rojas R (1995) Neural networks: a systematic introduction. Springer, New York
Ruiz-Molina JC, Navarro-Moreno J, Oya A (2001) Signal detection using approximate Karhunen-Loève expansions. IEEE Trans Inf Theory 47(4):1672–1680
Somorjai RL, Dolenko B, Nikulin AK, Pizzi N, Scarth G, Zhilkin P, Halliday W, Fewer D, Hill N, Ross I, West M, Smith ICP, Donnelly SM, Kuesel AC, Bière KM (1996) Classification of 1H MR spectra of human brain neoplasms: the influence of preprocessing and computerized consensus diagnosis on classification accuracy. J Magn Reson Imaging 6:437–444
Tate AR (1997) Statistical pattern recognition for the analysis of biomedical magnetic resonance spectra. J Magn Reson Anal 3:63–78
Tate AR, Griffiths JR, Martínez PI, Moreno A, Barba I, Cabañas M, Watson D, Alonso J, Bartumeus F, Isamat F, Ferrer I, Vila F, Ferrer E, Capdevilla A, Arús C (1998) Towards a method for automated classification of 1H MRS spectra from brain tumours. NMR Biomed 11:177–191
Therrien CW (1992) Discrete random signals and statistical signal processing. Prentice-Hall, Upper Saddle River, NJ
Unser M, Aldroubi A (1995) A review of wavelets in biomedical applications. Proc IEEE 48:626–638
Vapnik VN (2000) The nature of statistical learning theory, 2nd edn. Springer, New York
Wen X, Zhang H, Xu X, Quan J (2009) A new watermarking approach based on probabilistic neural network in wavelet domain. Soft Comput 13:355–360
Yin P, Sun F, Wang C, Liu H (2008) An adaptive feature fusion framework for multi-class classification based on SVM. Soft Comput 12:685–691
Acknowledgments
We appreciate the collaboration of the members of the Neurosurgery Service at University Hospital of La Paz (Madrid, Spain) and the Biomedical Research Institute (CSIC), who have provided us with the signals and data used in this work.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Farias, G., Santos, M. & López, V. Making decisions on brain tumor diagnosis by soft computing techniques. Soft Comput 14, 1287–1296 (2010). https://doi.org/10.1007/s00500-009-0495-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-009-0495-0