gms | German Medical Science

57th Annual Meeting of the German Society of Neurosurgery
Joint Meeting with the Japanese Neurosurgical Society

German Society of Neurosurgery (DGNC)

11 - 14 May, Essen

Development of an automatical classificator for the evaluation of extracellular microrecording signals in stereotactic surgery of the subthalamic nucleus

Entwicklung eines automatischen Klassifikators zur Evaluation von extrazellulären Mikrosignalen bei stereotaktischen Operationen des Nucleus Subthalamicus

Meeting Abstract

  • corresponding author T. Henrichs - Innovative und angewandte Informatik, Fachhochschule Trier
  • F. Hertel - Neurochirurgie Brüderkrankenhaus Trier
  • C. Decker - Neurochirurgie Brüderkrankenhaus Trier
  • P. Gemmar - Neurochirurgie Brüderkrankenhaus Trier

Deutsche Gesellschaft für Neurochirurgie. Japanische Gesellschaft für Neurochirurgie. 57. Jahrestagung der Deutschen Gesellschaft für Neurochirurgie e.V. (DGNC), Joint Meeting mit der Japanischen Gesellschaft für Neurochirurgie. Essen, 11.-14.05.2006. Düsseldorf, Köln: German Medical Science; 2006. DocP 03.42

The electronic version of this article is the complete one and can be found online at:

Published: May 8, 2006

© 2006 Henrichs et al.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License ( You are free: to Share – to copy, distribute and transmit the work, provided the original author and source are credited.



Objective: To develop a computer – based system fort he automatical classification of microrecording systems of the subthalamic region to distinguish automatically STN versus non – STN signals.

Methods: In a 3 step algorithm, the microrecording signals (MER) were classified, using different mathematical transformations, such as Wavelet transformations. We analyzed the 2434 MER recordings of STN surgery of 14 consecutive patients with advanced PD. The tests were performed in a double blind manner according to the investigators.

Results: The overall reliability of the automatical classificatory reached 95%. Within the individual patient, the reliability varied between 89,6 and 97,4%. Those signals which were clearly defined - by a neurophysiologically experienced stereotactic and functional neurosurgeon – could be identified in almost 100% of the cases correctly by the algorithm. The signals which could not clearly be defined manually, were also difficult to classify automatically, though even in those latter traces, the concordance between the automatic system and the investigator was above 89%.

Conclusions: Automatical detection of MER signals of the STN seems to be possible by a multistep computer algorithm, implicating Wavelet transformation with a significant high reliability.

This system could support the neurosurgeon and neurophysiologist during functional STN sugery.