Patient-Specific Seizure Prediction from Electroencephalogram Signal via Multi-Channel Feedback Capsule Network

In recent years, the use of convolutional neural networks (CNNs) have been common in Electroencephalogram (EEG) based seizure prediction. However, CNNs lose local and global connections and spatial information due to local connections and pooling operations. In addition, existing seizure prediction methods often require the design of special feature pre-extraction steps. Therefore, an end-to-end patient-specific seizure predictor based on feedback capsule network (FB-CapsNet) is proposed in this study. It can characterize complex temporal information and precise spatial relationships, capture and integrate spatiotemporal properties directly from the raw EEG signal, and distinguish seizure states. The proposed FB-CapsNet first uses a feedback network to extract temporal information and one-dimensional convolution to reduce the data dimensionality. Then, it uses capsule network to capture spatial information and other instantiation properties and store them in capsule vectors. Finally, it performs information flow between low-level and high-level capsules by a dynamic routing mechanism to obtain superior classification performance. The proposed FB-CapsNet achieves 95.7% sensitivity, 0.087/h false prediction rate (FPR), and 0.948 area under curve (AUC) on the CHB-MIT scalp dataset and 88.6% sensitivity, 0.127/h FPR, and 0.837 AUC on Kaggle dataset.