Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals.

https://www.ncbi.nlm.nih.gov/pubmed/28974302

Comput Biol Med. 2017 Sep 27. pii: S0010-4825(17)30315-3. doi: 10.1016/j.compbiomed.2017.09.017. [Epub ahead of print]

Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals.

Acharya UR1, Oh SL2, Hagiwara Y2, Tan JH2, Adeli H3.

Author information

1

Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore; Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore; Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Malaysia. Electronic address: aru@np.edu.sg.

2

Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore.

3

Departments of Neuroscience, Neurology, Biomedical Engineering, Biomedical Informatics, and Civil, Environmental, and Geodetic Engineering, The Ohio State University, 470 Hitchcock Hall, 2070 Neil Avenue, Columbus, OH, 43210, United States.

Abstract

An encephalogram (EEG) is a commonly used ancillary test to aide in the diagnosis of epilepsy. The EEG signal contains information about the electrical activity of the brain. Traditionally, neurologists employ direct visual inspection to identify epileptiform abnormalities. This technique can be time-consuming, limited by technical artifact, provides variable results secondary to reader expertise level, and is limited in identifying abnormalities. Therefore, it is essential to develop a computer-aided diagnosis (CAD) system to automatically distinguish the class of these EEG signals using machine learning techniques. This is the first study to employ the convolutional neural network (CNN) for analysis of EEG signals. In this work, a 13-layer deep convolutional neural network (CNN) algorithm is implemented to detect normal, preictal, and seizure classes. The proposed technique achieved an accuracy, specificity, and sensitivity of 88.67%, 90.00% and 95.00%, respectively.

Copyright © 2017 Elsevier Ltd. All rights reserved.

KEYWORDS:

Convolutional neural network; Deep learning; Encephalogram signals; Epilepsy; Seizure

PMID:

 

28974302

 

DOI:

 

10.1016/j.compbiomed.2017.09.017