Epileptic Seizure Detection Based on Path Signature and Bi-LSTM Network with Attention Mechanism

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 32; p. 1
• Main Authors: Tang, Yixuan, Wu, Qianyi, Mao, Haifeng, Guo, Lihua
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Attention Mechanism; Bi-directional LSTM; Brain modeling; Channels; Complications; Convolutional neural networks; Convulsions & seizures; Data mining; Deep learning; EEG; Electroencephalography; Electroencephalography - methods; Epilepsy; Epilepsy - diagnosis; Feature extraction; Heuristic algorithms; Humans; Long short-term memory; Machine learning; Neural networks; Neural Networks, Computer; Path signature; Patients; Risk reduction; Seizure detection; Seizures; Seizures - diagnosis; Signal Processing, Computer-Assisted
• ISSN: 1534-4320; 1558-0210
• DOI: 10.1109/TNSRE.2024.3350074

Automatic seizure detection using electroencephalogram (EEG) can significantly expedite the diagnosis of epilepsy, thereby facilitating prompt treatment and reducing the risk of future seizures and associated complications. While most existing EEG-based epilepsy detection studies employ deep learning models, they often ignore the chronological relationships between different EEG channels. To tackle this limitation, a novel automatic epilepsy detection method is proposed, which leverages path signature and Bidirectional Long Short-Term Memory (Bi-LSTM) neural network with an attention mechanism. The path signature algorithm is used to extract discriminative features for capturing the dynamic dependencies between different channels of EEG, while Bi-LSTM with attention further analyzes the inherent temporal dependencies hidden in EEG signal features. Our method is evaluated on two public EEG databases with different sizes (CHB-MIT and TUEP) and a private database from a local hospital. Two experimental settings are used, i.e., five-fold cross-validation and leave-one-out cross-validation. Experimental results show that our method achieves 99.09%, 95.60%, and 99.87% average accuracies on CHB-MIT, TUEP with 250Hz, and TUEP with 256Hz, respectively. On the private dataset, our method also achieves 99.40% average accuracy, which outperforms other methods. Furthermore, our method exhibits robustness in patients, as demonstrated by the evaluation results of cross-patient experiments.