Automated detection of subthalamic nucleus in deep brain stimulation surgery for Parkinson’s disease using microelectrode recordings and wavelet packet features

• Published in: Journal of neuroscience methods 2020-09, Vol.343, p.108826-108826, Article 108826
• Main Authors: Karthick, P.A., Wan, Kai Rui, An Qi, Angela See, Dauwels, Justin, King, Nicolas Kon Kam
• Format: Article
• Language: English
• Subjects: Classification; Deep brain stimulation; Microelectrode recording; Nucleus; Parkinson’s disease; Subthalamic; Wavelet packet
• ISSN: 0165-0270; 1872-678X
• DOI: 10.1016/j.jneumeth.2020.108826

•Microelectrode recordings performed during DBS surgery are stochastic and non-stationary, therefore, their interpretation is challenging.•Wavelet packet based features are explored to localize the pre-STN, STN and post-STN.•k-NN, support vector machine and random forest models are designed to detect the STN.•Proposed system achieves a maximum average accuracy of 85.01 % in the classification non-STN vs. STN with random forest.•Proposed method is a fast and reliable, therefore, it may facilitate real-time intraoperative STN identification. Deep brain stimulation (DBS) to the subthalamic nucleus (STN) is an effective neurosurgery that overcomes the motor system alternations of patients with advanced Parkinson’s disease. The most challenging aspect of DBS surgery is the accurate identification of STN and its borders. In general, it is performed manually by a neurophysiologist using the microelectrode recordings (MERs). This process is subjective, and tedious and further, interpretation of MERs is difficult because of its inherent nonstationary variations. In this work, the wavelet-packet based features are proposed to automatically localize the STN and its subcortical structures using microelectrode recorded signals during DBS surgery. The study analyses 2904 MERs of 26 PD patients who underwent DBS implantation. The low and high order statistical parameters are extracted from the wavelet packet coefficients of MERs and used in the classifications, namely, non-STN vs. STN, pre-STN vs. STN and STN vs. post-STN. Most of the features are significantly different in STN and its subcortical regions, namely, pre-STN and post-STN. The proposed features achieve an average accuracy of 85 % in non-STN vs. STN, 87.2 % in pre-STN vs. STN and 77.7 % in STN vs. post-STN. The accuracy is improved by around 10 % in non-STN vs. STN and STN vs. post-STN when the transition error is 1 mm. The proposed features are found to be better than the wavelet features. The proposed approach could be a potential useful adjunct for the real-time rapid intraoperative identification of STN and its anatomical borders.