Deep brain stimulation signal classification using deep belief networks

Pablo Guillen-Rondon, Melvin D. Robinson

Research output: ResearchConference contribution

Abstract

An approach to modeling complex real-world data such as biomedical signals is to develop pattern recognition techniques and robust features that capture the relevant information. In this paper, we use a deep belief network (DBN) to predict subcortical structures of patients with Parkinson's disease based on microelectrode records (MER) obtained during deep brain stimulation (DBS). We report on experiments using a data set involving 52 MER for the structures: zona incerta (Zi), subthalamic nucleus (STN), thalamus nucleus (TAL), and substantia nigra (SNR). The results show that our chosen features and network architecture produces a 99.5% accuracy of detection and classification of the subcortical structures under study. Based on the results we conclude that deep belief networks could be used to predict subcortical structure-mainly the STN for neurostimulation.

LanguageEnglish (US)
Title of host publicationProceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages155-158
Number of pages4
ISBN (Electronic)9781509055104
DOIs
StatePublished - Mar 17 2017
Event2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016 - Las Vegas, United States
Duration: Dec 15 2016Dec 17 2016

Other

Other2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016
CountryUnited States
CityLas Vegas
Period12/15/1612/17/16

Fingerprint

Subthalamic Nucleus
Deep Brain Stimulation
Microelectrodes
Bayesian networks
Brain
Substantia Nigra
Thalamus
Parkinson Disease
Datasets
Zona Incerta
Network architecture
Pattern recognition
Experiments

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Health Informatics
  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Guillen-Rondon, P., & Robinson, M. D. (2017). Deep brain stimulation signal classification using deep belief networks. In Proceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016 (pp. 155-158). [7881329] Institute of Electrical and Electronics Engineers Inc.. DOI: 10.1109/CSCI.2016.0036

Deep brain stimulation signal classification using deep belief networks. / Guillen-Rondon, Pablo; Robinson, Melvin D.

Proceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 155-158 7881329.

Research output: ResearchConference contribution

Guillen-Rondon, P & Robinson, MD 2017, Deep brain stimulation signal classification using deep belief networks. in Proceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016., 7881329, Institute of Electrical and Electronics Engineers Inc., pp. 155-158, 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016, Las Vegas, United States, 12/15/16. DOI: 10.1109/CSCI.2016.0036
Guillen-Rondon P, Robinson MD. Deep brain stimulation signal classification using deep belief networks. In Proceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016. Institute of Electrical and Electronics Engineers Inc.2017. p. 155-158. 7881329. Available from, DOI: 10.1109/CSCI.2016.0036
Guillen-Rondon, Pablo ; Robinson, Melvin D./ Deep brain stimulation signal classification using deep belief networks. Proceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 155-158
@inbook{39f5a4bbdaa342aebdd7920648919d12,
title = "Deep brain stimulation signal classification using deep belief networks",
abstract = "An approach to modeling complex real-world data such as biomedical signals is to develop pattern recognition techniques and robust features that capture the relevant information. In this paper, we use a deep belief network (DBN) to predict subcortical structures of patients with Parkinson's disease based on microelectrode records (MER) obtained during deep brain stimulation (DBS). We report on experiments using a data set involving 52 MER for the structures: zona incerta (Zi), subthalamic nucleus (STN), thalamus nucleus (TAL), and substantia nigra (SNR). The results show that our chosen features and network architecture produces a 99.5% accuracy of detection and classification of the subcortical structures under study. Based on the results we conclude that deep belief networks could be used to predict subcortical structure-mainly the STN for neurostimulation.",
author = "Pablo Guillen-Rondon and Robinson, {Melvin D.}",
year = "2017",
month = "3",
doi = "10.1109/CSCI.2016.0036",
pages = "155--158",
booktitle = "Proceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - CHAP

T1 - Deep brain stimulation signal classification using deep belief networks

AU - Guillen-Rondon,Pablo

AU - Robinson,Melvin D.

PY - 2017/3/17

Y1 - 2017/3/17

N2 - An approach to modeling complex real-world data such as biomedical signals is to develop pattern recognition techniques and robust features that capture the relevant information. In this paper, we use a deep belief network (DBN) to predict subcortical structures of patients with Parkinson's disease based on microelectrode records (MER) obtained during deep brain stimulation (DBS). We report on experiments using a data set involving 52 MER for the structures: zona incerta (Zi), subthalamic nucleus (STN), thalamus nucleus (TAL), and substantia nigra (SNR). The results show that our chosen features and network architecture produces a 99.5% accuracy of detection and classification of the subcortical structures under study. Based on the results we conclude that deep belief networks could be used to predict subcortical structure-mainly the STN for neurostimulation.

AB - An approach to modeling complex real-world data such as biomedical signals is to develop pattern recognition techniques and robust features that capture the relevant information. In this paper, we use a deep belief network (DBN) to predict subcortical structures of patients with Parkinson's disease based on microelectrode records (MER) obtained during deep brain stimulation (DBS). We report on experiments using a data set involving 52 MER for the structures: zona incerta (Zi), subthalamic nucleus (STN), thalamus nucleus (TAL), and substantia nigra (SNR). The results show that our chosen features and network architecture produces a 99.5% accuracy of detection and classification of the subcortical structures under study. Based on the results we conclude that deep belief networks could be used to predict subcortical structure-mainly the STN for neurostimulation.

UR - http://www.scopus.com/inward/record.url?scp=85017293229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017293229&partnerID=8YFLogxK

U2 - 10.1109/CSCI.2016.0036

DO - 10.1109/CSCI.2016.0036

M3 - Conference contribution

SP - 155

EP - 158

BT - Proceedings - 2016 International Conference on Computational Science and Computational Intelligence, CSCI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -