Seizure Prediction Using Directed Transfer Function and Convolution Neural Network on Intracranial EEG

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 28; no. 12; pp. 2711 - 2720
• Main Authors: Wang, Gang, Wang, Dong, Du, Changwang, Li, Kuo, Zhang, Junhao, Liu, Zhian, Tao, Yi, Wang, Maode, Cao, Zehong, Yan, Xiangguo
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Biological neural networks; Brain; Brain modeling; Convolution; convolution neural networks; Convulsions & seizures; Deep learning; directed transfer function; EEG; Electroencephalography; Epilepsy; Feature extraction; Flow mapping; Information flow; Information transfer; Intracranial electroencephalogram (iEEG); Machine learning; Neural networks; Prediction algorithms; Predictions; Robustness (mathematics); seizure prediction; Seizures; Transfer functions
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2020.3035836

Automatic seizure prediction promotes the development of closed-loop treatment system on intractable epilepsy. In this study, by considering the specific information exchange between EEG channels from the perspective of whole brain activities, the convolution neural network (CNN) and the directed transfer function (DTF) were merged to present a novel method for patient-specific seizure prediction. Firstly, the intracranial electroencephalogram (iEEG) signals were segmented and the information flow features of iEEG signals were calculated by using the DTF algorithm. Then, these features were reconstructed as the channel-frequency maps according to channel pairs and the frequency of information flow. Finally, these maps were fed into the CNN model and the outputs were post-processed by the moving average approach to predict the epileptic seizures. By the evaluation of cross-validation method, the proposed algorithm achieved the averaged sensitivity of 90.8%, the averaged false prediction rate of 0.08 per hour. Compared to the random predictor and other existing algorithms tested on the Freiburg EEG dataset, our proposed method achieved better performance for seizure prediction in all patients. These results demonstrated that the proposed algorithm could provide an robust seizure prediction solution by using deep learning to capture the brain network changes of iEEG signals from epileptic patients.