TY - JOUR
T1 - Automated inter-patient seizure detection using multichannel Convolutional and Recurrent Neural Networks
AU - Craley, Jeff
AU - Johnson, Emily
AU - Jouny, Christophe
AU - Venkataraman, Archana
N1 - Funding Information:
This work was supported by a JHU Discovery Award, USA (Venkat-araman/Johnson) and NSF CAREER, USA 1845430 (Venkataraman).
Publisher Copyright:
© 2020 Elsevier Ltd
PY - 2021/2
Y1 - 2021/2
N2 - We present an end-to-end deep learning model that can automatically detect epileptic seizures in multichannel electroencephalography (EEG) recordings. Our model combines a Convolutional Neural Network (CNN) and a Bidirectional Long Short-Term Memory (BLSTM) network to efficiently mine information from the EEG data using a small number of trainable parameters. Specifically, the CNN learns a latent encoding for each one second window of raw multichannel EEG data. In conjunction, the BLSTM learns the temporal evolution of seizure presentations given the CNN encodings. The combination of these architectures allows our model to capture both the short time scale EEG features indicative of seizure activity as well as the long term correlations in seizure presentations. Unlike most prior work in seizure detection, we mimic an in-patient monitoring setting through a leave-one-patient-out cross validation procedure, attaining an average seizure detection sensitivity of 0.91 across all patients. This strategy verifies that our model can generalize to new patients. We demonstrate that our CNN–BLSTM outperforms both conventional feature extraction methods and state-of-the-art deep learning approaches that rely on larger and more complex network architectures.
AB - We present an end-to-end deep learning model that can automatically detect epileptic seizures in multichannel electroencephalography (EEG) recordings. Our model combines a Convolutional Neural Network (CNN) and a Bidirectional Long Short-Term Memory (BLSTM) network to efficiently mine information from the EEG data using a small number of trainable parameters. Specifically, the CNN learns a latent encoding for each one second window of raw multichannel EEG data. In conjunction, the BLSTM learns the temporal evolution of seizure presentations given the CNN encodings. The combination of these architectures allows our model to capture both the short time scale EEG features indicative of seizure activity as well as the long term correlations in seizure presentations. Unlike most prior work in seizure detection, we mimic an in-patient monitoring setting through a leave-one-patient-out cross validation procedure, attaining an average seizure detection sensitivity of 0.91 across all patients. This strategy verifies that our model can generalize to new patients. We demonstrate that our CNN–BLSTM outperforms both conventional feature extraction methods and state-of-the-art deep learning approaches that rely on larger and more complex network architectures.
KW - Convolutional Neural Networks
KW - Epilepsy
KW - Long Short-Term Memory networks
KW - Seizure detection
UR - http://www.scopus.com/inward/record.url?scp=85096650624&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096650624&partnerID=8YFLogxK
U2 - 10.1016/j.bspc.2020.102360
DO - 10.1016/j.bspc.2020.102360
M3 - Article
AN - SCOPUS:85096650624
SN - 1746-8094
VL - 64
JO - Biomedical Signal Processing and Control
JF - Biomedical Signal Processing and Control
M1 - 102360
ER -