Stop! border ahead: Automatic detection of subthalamic exit during deep brain stimulation surgery

• Published in: Movement disorders 2017-01, Vol.32 (1), p.70-79
• Main Authors: Valsky, Dan, Marmor‐Levin, Odeya, Deffains, Marc, Eitan, Renana, Blackwell, Kim T., Bergman, Hagai, Israel, Zvi
• Format: Article
• Language: English
• Subjects: Aged; Classification; Cognitive science; Deep brain stimulation; Deep Brain Stimulation - methods; Electrical stimuli; Electrodes, Implanted; Electrophysiological Phenomena; Female; Humans; Learning algorithms; Life Sciences; Male; Markov Chains; Mathematical models; microelectrode recording; Microelectrodes; Middle Aged; Movement disorders; Neurodegenerative diseases; Parkinson Disease - surgery; Parkinson Disease - therapy; Parkinson's disease; Signal Processing, Computer-Assisted; Solitary tract nucleus; Substantia nigra; Substantia Nigra - anatomy & histology; Substantia Nigra - physiology; Substantia nigra pars reticulata; Subthalamic nucleus; Subthalamic Nucleus - anatomy & histology; Subthalamic Nucleus - physiology; Support Vector Machine; Surgery
• ISSN: 0885-3185; 1531-8257
• DOI: 10.1002/mds.26806

ABSTRACT Background Microelectrode recordings along preplanned trajectories are often used for accurate definition of the subthalamic nucleus (STN) borders during deep brain stimulation (DBS) surgery for Parkinson's disease. Usually, the demarcation of the STN borders is performed manually by a neurophysiologist. The exact detection of the borders is difficult, especially detecting the transition between the STN and the substantia nigra pars reticulata. Consequently, demarcation may be inaccurate, leading to suboptimal location of the DBS lead and inadequate clinical outcomes. Methods We present machine‐learning classification procedures that use microelectrode recording power spectra and allow for real‐time, high‐accuracy discrimination between the STN and substantia nigra pars reticulata. Results A support vector machine procedure was tested on microelectrode recordings from 58 trajectories that included both STN and substantia nigra pars reticulata that achieved a 97.6% consistency with human expert classification (evaluated by 10‐fold cross‐validation). We used the same data set as a training set to find the optimal parameters for a hidden Markov model using both microelectrode recording features and trajectory history to enable real‐time classification of the ventral STN border (STN exit). Seventy‐three additional trajectories were used to test the reliability of the learned statistical model in identifying the exit from the STN. The hidden Markov model procedure identified the STN exit with an error of 0.04 ± 0.18 mm and detection reliability (error