Applications of decision support systems in functional neurosurgery

Ciecierski, K.A; Mandat, T

  • Trends in Advanced Intelligent Control, Optimization and Automation, Seria: Advances in Intelligent Systems and Computing;
  • Tom: 577;
  • Strony: 838-847;
  • 2017;

Functional neurosurgery is used for treatment of conditions in central nervous system that arise from its improper physiology. One of the possible approaches is Deep Brain Stimulation (DBS). In this pro-cedure a stimulating electrode is placed in desired brain's area to locally affect its activity. Among others, DBS can be used as a treatment for dys-tonia, depression, obsessive-compulsive disorder (OCD) and Parkinson's Disease (PD). In this paper authors focus on application of classifers in Deep Brain Stimulation (DBS) for Parkinson's Disease (PD).In neuro- surgical treatment of the Parkinson's Disease the target is a small (9 x 7x 4 mm) deeply in brain situated structure called Subthalamic Nucleus (STN). The goal of the Deep Brain Stimulation is the precise perma-nent placement of the stimulating electrode within target nucleus. As this structure poorly visible in CT4 or MRI5 it is usually stereotacti-cally located using microelectrode recording. Several microelectrodes are parallelly inserted into the brain and then in measured steps advanced to-wards expected location of the nucleus. At each step, usually from 10 mm above expected center of the STN, the neuronal activity is recorded. Be-cause STN has a distinct physiology, the signals recorded within it also present specific features. By extraction certain attributes from record-ings provided by the microelectrodes, it is possible to construct a binary classifer that provides useful discrimination. This discrimination divides the recordings into two classes, i.e. those registered within the STN and those registered outside of it. From this it is known which microelec-trodes and at which depths have passed through the STN and thus a physiological map of its surrounding is made.

Słowa kluczowe: decision support system, signal power, random forest,