Abstract
In cancer diagnosis, classification of the different tumor types is of great importance. An accurate prediction of basic tumor types provides better treatment and may minimize the negative impact of incorrectly targeted toxic or aggressive treatments. Moreover, the correct prediction of cancer types in the brain using non-invasive information –e.g. 1H-MRS data– could avoid patients to suffer collateral problems derived from exploration techniques that require surgery. We present a feature selection algorithm that is specially designed to be used in 1H-MRS (Proton Magnetic Resonance Spectroscopy) data of brain tumors. This algorithm takes advantage of the fact that some metabolic levels may consistently present notorious differences between specific tumor types. We present detailed experimental results using an international dataset in which highly attractive models are obtained. The models are evaluated according to their accuracy, simplicity and medical interpretability. We also explore the influence of redundancy in the modelling process. Our results suggest that a moderate amount of redundant metabolites can actually enhance class-separability and therefore accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Zamani, A.: Proton MR Spectroscopy. In: Minimal invasive Neurosurgery, pp. 75–86. Humana Press (2005)
Sibtain, N.: The clinical value of proton magnetic resonance spectroscopy in adult brain tumours. Clinical Radiology 62, 109–119 (2007)
Bruhn, H., et al.: Noninvasive differentiation of tumors with use of localized h-1 mr spectroscopy in vivo: initial experience in patients with cerebral tumors. Radiology 172, 541–548 (1989)
Hansen, J., et al.: 1h-mr spectroscopy of the brain: Absolute quantification of metabolites. Radiology 246(2), 318–332 (2006)
Tate, A., et al.: Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra. NMR in Biomedicine 19, 411–434 (2006)
Garcia, J., et al.: On the use of long te and short te sv mr. spectroscopy to improve the automatic brain. tumor diagnosis. Tech. rep. (2007), ftp://ftp.esat.kuleuven.ac.be/pub/SISTA/ida/reports/07-55.pdf
Vellido, A., et al.: Outlier exploration and diagnostic classification of a multi-centre 1h-mrs brain tumour database. Neurocomputing 72, 3085–3097 (2009)
Usenius, J., et al.: Automated classification of human brain tumors by neural network analysis using in vivo 1h magnetic resonance spectroscopic metabolite phenotypes. Neuroreport 7(10), 1597–1600 (1996)
Ala-Korpela, M., et al.: Artificial neural network analysis of 1h nuclear magnetic resonance spectroscopic data from human plasma. Neurocumputing 13-15, 3085–3097 (2009)
Majos, C., et al.: Brain tumor classification by proton mr spectroscopy: Comparison of diagnostic accuracy at short and long te. American Journal of Neuroradiology 25, 1696–1704 (2004)
Devos, A.: Quantification and classification of mrs data and applications to brain tumour recognition. Ph.D. thesis, Katholieke Univ. Leuven (2005)
Lukas, L., et al.: Brain tumor classification based on long echo proton mrs signals. Artificial Intelligence in Medicine 31, 73–89 (2004)
Huang, Y., Lisboa, P., El-Deredy, W.: Tumour grading from magnetic resonance spectroscopy: a comparison fo feature extraction with variable selection. Statistics in Medicine 22, 147–164 (2003)
Nikulin, A., et al.: Near-optimal region selection for feature space reduction: novel preprocessing methods for classifying mr spectra. NMR in Biomedicine 11, 209–216 (1998)
Luts, J., et al.: A combined mri and mrsi based multiclass system from brain tumour recognition using ls-svms with class probabilities and feature selection. Artificial Ingelligence in Medicine 40, 87–102 (2007)
González, F., et al.: Feature and model selection with discriminatory visualization for diagnostic classification of brain tumors. Neurocomputing 73, 622–632 (2010)
Romero, E., Vellido, A., Sopena, J.M.: Feature Selection with Single-Layer Perceptrons for a Multicentre 1h-mrs Brain Tumour Database. In: Cabestany, J., Sandoval, F., Prieto, A., Corchado, J.M. (eds.) IWANN 2009, Part I. LNCS, vol. 5517, pp. 1013–1020. Springer, Heidelberg (2009)
Lisboa, P., et al.: Classification, dimensionality reduction, and maximally discriminatory visualization of a multicentre 1h-mrs database of brain tumors. In: ICMLA 2008: Proceedings of the 2008 Seventh International Conference on Machine Learning and Applications, pp. 613–618. IEEE Computer Society (2008)
Castillo, M., Kwock, L., Mukherji, S.: Clinical applications of proton mr spectroscopy. AJNR 17, 1–15 (1996)
INTERPRET, International network for pattern recognition of tumours using magnetic resonance project (2002), http://azizu.uab.es/INTERPRET
Ladroue, C.: Pattern recognition techniques for the study of magnetic resonance spectra of brain tumours. Ph.D. thesis, St. George’s Hospital Medical School (2003)
Govindaraju, V., Young, K., Maudsley, A.: Proton nmr chemical shifts and coupling constants for brain metabolites. NMR in Biomedicine 13(3), 129–153 (2000)
Farooqui, A., Ong, W., Horrocks, L.: Glutamate and Aspartate in Brain. Springer, New York (2008)
Lisboa, P., et al.: Cluster based visualisation with scatter matrices. Pattern Recognition Letters 29(13), 1814–1823 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
González-Navarro, F.F., Belanche-Muñoz, L.A. (2012). Feature Selection for the Prediction and Visualization of Brain Tumor Types Using Proton Magnetic Resonance Spectroscopy Data. In: Biganzoli, E., Vellido, A., Ambrogi, F., Tagliaferri, R. (eds) Computational Intelligence Methods for Bioinformatics and Biostatistics. CIBB 2011. Lecture Notes in Computer Science(), vol 7548. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35686-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-35686-5_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35685-8
Online ISBN: 978-3-642-35686-5
eBook Packages: Computer ScienceComputer Science (R0)