Abstract
The presurgical evaluation of epilepsy patients relies on an exact localization and delineation of the generators of epileptic seizures. During the registration of the electroencephalogram (EEG) sharp transient signals called spikes can be observed. These spikes give hints for the so called epileptogenic zone in the brain. In order to decide whether these spikes derive from single or multiple generators an incrementing topology preserving map with insertion and deletion of units was trained for the EEG data of individual patients. By deleting of units the net was separated into subnets. Thus it could be further used for vector quantization. The spatial distributions of the peak amplitude of the spikes in all channels as well as the time differences of their peaks were used as input signals. The separation of spatio-temporal clusters of the spikes was compared with those clusters identified by a human reviewer.
Preview
Unable to display preview. Download preview PDF.
References
Blume, W., Lemieux, J., Morphology of spikes in spike-and-wave complexes, Electroencephalograhy and clinical Neurophysiology 69 (1988), pp 508–515
Elo, P., Saarinen, J., Värri, A., et. al., Classification of Epileptic EEG by Using Self-Organizing Maps, in: Artificial Neural Networks 2, Aleksander, I., Taylor, J., Elsevier, Amsterdam, (1992)
Dümpelmann, M., Hufnagel, A., Burr, W., Elger, C., Determination of the Epileptogenic zone by use of Spike Clustering and Spike-Amplitude-Latency-Topograms, Epilepsia, 35 (Sup. 8) (1994), p 28
Fritzke, B., Vector Quantization in a Growing and Splitting Elastic Net, in: Proc. ICANN'93, Int. Conf. on Artificial Neural Networks, Gielen, S., Kappen, B., Springer, London, (1993)
Fritzke, B., Growing Feature Maps and Growing Cell Structures — a Performance Comparison, in: Advances in Neural Information Processing Systems 5, Giles, L., Hanson, S., Cowan, J., Morgan Kaufmann Publishers, San Mateo, CA, (1993)
Fritzke, B., Growing cell structures — a self-organizing network for unsupervised and supervised learning, Neural Networks 7(9)(1994), pp 1441–1460
Fritzke, B., Fast learning with incremental RBF networks, Neural Processing Letters, 1(1) (1994), pp 2–5
Hufnagel, A., Burr, W., Elger, C., et al., Localization of the epileptic focus during methohexital induced anesthesia, Epilepsia, 33(2) (1992), pp 271–284
Kaski, S., Joutsiniemi, S., Monitoring EEG Signal with the Self-Organizing Map, in: Proc. ICANN'93, Int. Conf. on Artificial Neural Networks, Gielen, S., Kappen, B., Springer, London, (1993)
Kohonen, T., Self-Organization and Associative Memory, Springer Series in Information Sciences 8, Springer, Heidelberg, (1984)
Kohonen, T., The Self-Organizing Map, Proc. IEEE 78 (1990), pp 1464–1480
Kohonen, T., Self-Organizing Maps, Springer Series in Information Sciences 30, Springer, Heidelberg, (1995)
Lopes da Silva, F., Dijk, A., Smits, H., Detection of Nonstationarities in EEGs using the Autoregressive Model. An application to the EEGs of Epileptics, in: CEAN: Computerized EEG-Analysis, Dolce, G., Künkel, H., Fischer, Stuttgart, (1975)
Lüders, H., Awad, I., Conceptual Considerations, in: Epilepsy surgery, Lüders, H., Raven Press, New York, (1992)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dümpelmann, M., Elger, C.E. (1996). Separating EEG spike-clusters in epilepsy by a growing and splitting net. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_43
Download citation
DOI: https://doi.org/10.1007/3-540-61510-5_43
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61510-1
Online ISBN: 978-3-540-68684-2
eBook Packages: Springer Book Archive