Abstract
In this paper we present a multi-stage classifier for magnetic resonance spectra of human brain tumours which is being developed as part of a decision support system for radiologists. The basic idea is to decompose a complex classification scheme into a sequence of classifiers, each specialising in different classes of tumours and trying to reproduce part of the WHO classification hierarchy. Each stage uses a particular set of classification features, which are selected using a combination of classical statistical analysis, splitting performance and previous knowledge. Classifiers with different behaviour are combined using a simple voting scheme in order to extract different error patterns: LDA, decision trees and the k-NN classifier. A special label named “unknown” is used when the outcomes of the different classifiers disagree. Cascading is also used to incorporate class distances computed using LDA into decision trees. Both cascading and voting are effective tools to improve classification accuracy. Experiments also show that it is possible to extract useful information from the classification process itself in order to help users (clinicians and radiologists) to make more accurate predictions and reduce the number of possible classification mistakes.
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
Danielsen, E.R., Ross, B.: MRS Diagnosis of Neurological Diseases. Marcel Dekker, Inc, NY (1999)
Preul, M.C., et al.: Accurate, noninvasive diagnosis of human brain tumors by using proton magnetic resonance spectroscopy. Nature Medicine 2 (1996) 323–325
Hagberg, G., et al.: In vivo proton MR spectroscopy of human gliomas: Definition of metabolic coordinates for multi-dimensional classification. Magnetic Resonance in Medicine 34 (1995) 242–252
Tate, A.R., et al.: Towards a method for automated classification of 1H MRS spectra from brain tumours. NMR in Biomedicine 11 (1998) 177–191
Kleihues, P., Sobin, L.H.: WHO classification of tumors. Cancer 88 (2000) 2887
Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and Regression Trees. Wadsworth International Group (1984)
Tate, A.R., Ladroue, C., Minguillón, J.: Developing classifiers for single-voxel 1H brain tumour in vivo spectra for the INTERPRET decision support tool. Technical Report CSRP543, U. of Sussex, Cognitive and Comp. Sciences (2002)
Domingos, P.: A unified bias-variance decomposition and its applications. In: Proc. of the 17th Int. Conf. on ML, Stanford, CA, USA (2000) 231–238
Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning. Data mining, inference and prediction. Springer series in statistics. Springer (2001)
Dasarathy, B.: Nearest Neighbor Pattern Classification Techniques. IEEE Computer Society Press, Los Alamitos, CA, USA (1991)
Gama, J., Brazdil, P.: Cascade generalization. ML 41 (2000) 315–343
Minguillón, J., Pujol, J., Zeger, K.: Progressive classification scheme for document layout recognition. In: SPIE Proc., Volume 3816, Denver, CO (1999) 241–250
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Minguillón, J., Tate, A.R., Arús, C., Griffiths, J.R. (2002). Classifier Combination for In Vivo Magnetic Resonance Spectra of Brain Tumours. In: Roli, F., Kittler, J. (eds) Multiple Classifier Systems. MCS 2002. Lecture Notes in Computer Science, vol 2364. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45428-4_28
Download citation
DOI: https://doi.org/10.1007/3-540-45428-4_28
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43818-2
Online ISBN: 978-3-540-45428-1
eBook Packages: Springer Book Archive