Dan Valsky1,2, Odeya Marmor-Levin2, Marc Deffains2, Renana Eitan3, Kim T Blackwell4, Hagai Bergman1,2, Zvi Israel5. 1. The Edmond and Lily Safra Center for Brain Research (ELSC), The Hebrew University, Jerusalem, Israel. 2. Department of Medical Neurobiology (Physiology), Institute of Medical Research - Israel-Canada (IMRIC), The Hebrew University-Hadassah Medical School, Jerusalem, Israel. 3. Department of Psychiatry, Hadassah-Hebrew University Medical Center, Jerusalem, Israel. 4. Krasnow Institute for Advanced Study, George Mason University, Fairfax, Virginia, USA. 5. Center for Functional & Restorative Neurosurgery, Department of Neurosurgery, Hadassah-Hebrew University Medical Center, Jerusalem, Israel.
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 < 1 mm) of 94%. CONCLUSIONS: The results indicate that robust, accurate, and automatic real-time electrophysiological detection of the ventral STN border is feasible.
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 < 1 mm) of 94%. CONCLUSIONS: The results indicate that robust, accurate, and automatic real-time electrophysiological detection of the ventral STN border is feasible.
Authors: Andre Machado; Ali R Rezai; Brian H Kopell; Robert E Gross; Ashwini D Sharan; Alim-Louis Benabid Journal: Mov Disord Date: 2006-06 Impact factor: 10.338
Authors: Nicholas Maling; Scott F Lempka; Zack Blumenfeld; Helen Bronte-Stewart; Cameron C McIntyre Journal: J Neurophysiol Date: 2018-07-18 Impact factor: 2.714
Authors: Michael J Bos; Ana Maria Alzate Sanchez; Raffaella Bancone; Yasin Temel; Bianca T A de Greef; Anthony R Absalom; Erik D Gommer; Vivianne H J M van Kranen-Mastenbroek; Wolfgang F Buhre; Mark J Roberts; Marcus L F Janssen Journal: J Clin Med Date: 2020-04-24 Impact factor: 4.241
Authors: Amit Benady; Sean Zadik; Dan Eimerl; Sami Heymann; Hagai Bergman; Zvi Israel; Aeyal Raz Journal: Sci Rep Date: 2020-09-03 Impact factor: 4.379
Authors: Yanan Sui; Ye Tian; Wai Kin Daniel Ko; Zhiyan Wang; Fumin Jia; Andreas Horn; Dirk De Ridder; Ki Sueng Choi; Ausaf A Bari; Shouyan Wang; Clement Hamani; Kenneth B Baker; Andre G Machado; Tipu Z Aziz; Erich Talamoni Fonoff; Andrea A Kühn; Hagai Bergman; Terence Sanger; Hesheng Liu; Suzanne N Haber; Luming Li Journal: Front Neurol Date: 2021-01-28 Impact factor: 4.003
Authors: Cesar D Lopez; Venkat Boddapati; Joseph M Lombardi; Nathan J Lee; Justin Mathew; Nicholas C Danford; Rajiv R Iyer; Marc D Dyrszka; Zeeshan M Sardar; Lawrence G Lenke; Ronald A Lehman Journal: Global Spine J Date: 2022-02-28