Patient-Specific Seizure Prediction From Electroencephalogram Signal via Multichannel Feedback Capsule Network

In recent years, the use of convolutional neural networks (CNNs) has 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 the 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 1-D convolution to reduce the data dimensionality. Then, it uses the 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 positive rate (FPR), and 0.948 area under curve (AUC) on the CHB-MIT scalp data set and 88.6% sensitivity, 0.127/h FPR, and 0.837 AUC on Kaggle data set.