Abstract
A computer-aided system was developed for the automatic diagnosis of brain tumours using a novel density estimation method for image segmentation and independent component analysis (ICA) combined with Support Vector Machines (SVM) for image classification. Images from 87 tumor biopsies were digitized and classified into low and high-grade. Segmentation was performed utilizing a density estimation clustering method that isolated nuclei from background. Nuclear features were quantified to encode tumour malignancy. 46 cases were used to construct the SVM classifier. ICA determined the most important feature combination. Classifier performance was evaluated using the leave-one-out method. 41 cases collected from a different hospital were used to validate the systems’ generalization. For the training set the SVM classifier gave 84.9%. For the validation set classification performance was 82.9%. The proposed methodology is a dynamic new alternative to computer-aided diagnosis of brain tumours malignancy since it combines robust segmentation and high effective classification algorithm.
Keywords
- Support Vector Machine
- Probability Density Function
- Linear Discriminant Analysis
- Independent Component Analysis
- Independent Component Analysis
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
DeAngelis, L.M.: Brain tumors. New England Journal of Medicine 344, 114–123 (2001)
Shapiro, W.: Biology and treatment of malignant gliomas. Oncology 12, 233–240 (1998)
Mittler, M., Walters, B., Stopa, E.: Observer reliability in histological grading of astrocytoma. Journal of Neurosurgery 85, 1091–1094 (1996)
Scarpelli, M., Bartels, P., Montironi, R., Thompson, D.: Morphometrically assisted grading of astrocytomas. Analytical and quantitative Cytology and Histology 16, 351–356 (1994)
Kolles, H., van Wangenheim, A.: Automated grading of astrocytomas based on histo- morphometric analysis of ki-67 and Fleugen stained paraffin sections. Analytical cellular pathology 8, 101–116 (1995)
McKeown, M., Ramsay, A.: Classification of Astrocytomas and Malignant Astrocytomas by Principal Component analysis and a Neural Net. Neuropathology & Experimental Neurology 55, 1238–1245 (1996)
Kolles, H., van Wangenheim, A., Rahmel, J., Niedermayer, I., Feiden, W.: Data-Driven Approaches for decision making in Automated Tumour Grading. An example in Astrocytoma Grading. Analytical and Quantitative Cytology and Histopathology 18, 298–304 (1996)
Decaestecker, C., Salmon, I., Dewitte, O., Camby, I., Van Ham, P.: Nearest-neighbor classification for identification of aggressive versus nonaggressive astrocytic tumours by means of image cytometry-generated variables. Journal of Neurosurgery 86, 532–537 (1997)
Sallinen, P., Sallinen, S., Helen, T., Rantala, I., Helin, H., Kalimo, H.: Grading of diffusely infiltrating astrocytomas by quantitative histopathology, cell proliferation and image cytometric DNA analysis. Neuropathology and Applied Neurobiology 26, 319–331 (2000)
Glotsos, D.P., Petalas, P., Cavouras, D., Ravazoula, I., Dadioti, P., Lekka, I., Nikiforidis, G.: Computer-Based Malignancy Grading of Astrocytomas Employing a Support Vector Machine Classifier, the WHO Grading System and the Regular Hematoxylin-Eosin Diagnostic Staining Procedure. Analytical and Quantitative Cytology and Histopathology 26, 77–83 (2003)
Kleihues, P., Burger, P., Scheithauer, B.: Histological typing of tumours of the central nervous system. World Health Organization, Geneva (1993)
Spyridonos, P., Ravazoula, P., Cavouras, D., Nikiforidis, G.: Neural Network based segmentation and classification system for the automatic grading of histopathological sections of urinary bladder carcinoma. Analytical and Quantitative Cytology Histopathology 24, 317–324 (2002)
Glotsos, D., Tohka, J., Soukka, J., Ruotsalainen, U.: A new Approach to Robust Clustering by Density Estimation in an Autocorrelation Derived Feature Space. In: Proceedings of the 6th NORDIC signal processing symposium, pp. 296–299 (2004)
Spyridonos, P., Ravazoula, P., Cavouras, D., Berberidis, K., Nikiforidis, G.: Computerbased grading of haematoxylin-eosin stained tissue sections of urinary bladder carcinomas. Medical Informatics & The Internet in Medicine 26, 179–190 (2001)
Deniz, O., Castrillon, M., Hernadez, M.: Face recognition using independent component analysis and support vector machines. Pattern recognition letters 24, 2153–2157 (2003)
Theodoridis, S., Koutroubas, K.: Pattern recognition, p. 342. Academic Press, London (1999)
Kechman, V.: Learning and Soft Computing, pp. 121–189. MIT, USA (2001)
Christianini, N., Taylor, J.S.: An introduction to support vector machines and other kernelbased learning methods, pp. 135–136. Cambridge University Press, UK (2000)
Schad, L., Schmit, H., Lrenz, W., Scarpelli, M., Bartels, R.: Numerical grading of astrocytomas. Medical informatics 12, 11–22 (1987)
Specht, D.: Probabilistic neural networks. Neural Networks 3, 109–118 (1990)
Lee, K.-M., Street, N.: A fast and robust approach for automated segmentation of breast cancer nuclei. In: Proceedings of the IASTED International Conference on Computer Graphics and Imaging, pp. 42–47 (1999)
Reinhold, N., Schlote, W.: Topometric Analysis of Diffuse Astrocytomas. Analytical and Quantitative Cytology and Histopathology 25, 12–18 (2003)
Belacel, N., Boulassel, M.: Multicriteria fuzzy assignment method: a useful tool to assist medical diagnosis. Artificial intelligence in medicine 21, 201–207 (2001)
Murphey, Y.L., Guo, H.: Automatic feature selection - a hybrid statistical approach. In: Proceedings of the 15th International Conference on Pattern Recognition, pp. 382–385 (2000)
Bressan, M., Vitria, J.: On the selection and classification of independent features. IEEE Transactions on Pattern Analysis and Machine Intelligence 25, 1312–1317 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Glotsos, D., Spyridonos, P., Ravazoula, P., Cavouras, D., Nikiforidis, G. (2004). Automated Diagnosis of Brain Tumours Using a Novel Density Estimation Method for Image Segmentation and Independent Component Analysis Combined with Support Vector Machines for Image Classification. In: Pal, N.R., Kasabov, N., Mudi, R.K., Pal, S., Parui, S.K. (eds) Neural Information Processing. ICONIP 2004. Lecture Notes in Computer Science, vol 3316. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30499-9_164
Download citation
DOI: https://doi.org/10.1007/978-3-540-30499-9_164
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23931-4
Online ISBN: 978-3-540-30499-9
eBook Packages: Springer Book Archive