TY - GEN
T1 - Detection of Traumatic Brain Injury Using Single Channel Electroencephalogram in Mice
AU - Sutandi, A.
AU - Dhillon, N.
AU - Lim, M.
AU - Cao, H.
AU - Si, D.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12/5
Y1 - 2020/12/5
N2 - Preclinical studies of traumatic brain injury (TBI) are often performed using a murine model of mild traumatic brain injury (mTBI) due to highly controlled settings and high reproducibility in this experimental model, compared to studies of human TBI. We have previously demonstrated persistent changes in the sleep wake cycle using a widely accepted mouse model of mTBI. The gold standard of sleep wake assessment is achieved by recording brain electroencephalogram (EEG), which not only allows for standard sleep staging but also allows further signal processing through quantitative EEG methods. Conventional methods of sleep staging require manual scoring by a trained expert. Here, a 1-D deep convolutional neural network (Deep CNN) is proposed to automatically score sleep stages and identify mTBI from a single-channel EEG signal with duration of 64 seconds by classifying the EEG signal into one of four classes: sham (control) wake, sham (control) sleep, mTBI wake, and mTBI sleep. We demonstrated that the proposed Deep CNN has the ability to learn features to classify the target classes. Deployment of the trained model on Raspberry Pi further indicates the capacity to perform classification in real time and mobile applications. Thus, the proposed system has the potential to provide a low-cost and fast method for detection of TBI in individuals.
AB - Preclinical studies of traumatic brain injury (TBI) are often performed using a murine model of mild traumatic brain injury (mTBI) due to highly controlled settings and high reproducibility in this experimental model, compared to studies of human TBI. We have previously demonstrated persistent changes in the sleep wake cycle using a widely accepted mouse model of mTBI. The gold standard of sleep wake assessment is achieved by recording brain electroencephalogram (EEG), which not only allows for standard sleep staging but also allows further signal processing through quantitative EEG methods. Conventional methods of sleep staging require manual scoring by a trained expert. Here, a 1-D deep convolutional neural network (Deep CNN) is proposed to automatically score sleep stages and identify mTBI from a single-channel EEG signal with duration of 64 seconds by classifying the EEG signal into one of four classes: sham (control) wake, sham (control) sleep, mTBI wake, and mTBI sleep. We demonstrated that the proposed Deep CNN has the ability to learn features to classify the target classes. Deployment of the trained model on Raspberry Pi further indicates the capacity to perform classification in real time and mobile applications. Thus, the proposed system has the potential to provide a low-cost and fast method for detection of TBI in individuals.
UR - http://www.scopus.com/inward/record.url?scp=85101815324&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101815324&partnerID=8YFLogxK
U2 - 10.1109/SPMB50085.2020.9353651
DO - 10.1109/SPMB50085.2020.9353651
M3 - Conference contribution
AN - SCOPUS:85101815324
T3 - 2020 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2020 - Proceedings
BT - 2020 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2020 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2020
Y2 - 5 December 2020
ER -