Deep learning for spike detection in deep brain stimulation surgery

TL;DR

This paper presents a deep learning approach using CNNs to detect neuronal spikes during deep brain stimulation surgery, achieving high accuracy without data preprocessing.

Contribution

Introduces a CNN-based method for spike detection in DBS surgery recordings, eliminating the need for data preprocessing and demonstrating high accuracy.

Findings

Maximum accuracy of 98.98% in spike detection

AUC of 0.9898 indicating excellent classifier performance

Effective real-time analysis without data preprocessing

Abstract

Deep brain stimulation (DBS) is a neurosurgical procedure successfully used to treat conditions such as Parkinson's disease. Electrostimulation, carried out by implanting electrodes into an identified focus in the brain, makes it possible to reduce the symptoms of the disease significantly. In this paper, a method for analyzing recordings of neuronal activity acquired during DBS neurosurgery using deep learning is presented. We tested using a convolutional neural network (CNN) for this purpose. Based on the time window, the classifier assesses whether neuronal activity (spike) is present. The maximum accuracy value for the classifier was 98.98%, and the area under the receiver operating characteristic curve (AUC) was 0.9898. The method made it possible to obtain a classification without using data preprocessing.