Epileptic Seizure Detection by Cascading Isolation Forest-based Anomaly Screening and EasyEnsemble

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 30; p. 1
• Main Authors: Guo, Yao, Jiang, Xinyu, Tao, Linkai, Meng, Long, Dai, Chenyun, Long, Xi, Wan, Feng, Zhang, Yuan, Van Dijk, Johannes, Aarts, Ronald M., Chen, Wei, Chen, Chen
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-01-2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: aEEG; Algorithms; Anomalies; Anomaly detection; Band-pass filters; Child; Convulsions & seizures; EEG; Electroencephalography; Epilepsy; Epilepsy - diagnosis; Feature extraction; Forestry; Forests; Humans; Hybrid systems; Labeling; Labelling; Learning; Low-pass filters; Machine learning; Modules; Screening; Segmentation; Segments; Seizure detection system; Seizures; Seizures - diagnosis; Sensitivity; Signal Processing, Computer-Assisted; supervised learning; unsupervised learning; Workload; Workloads
• ISSN: 1534-4320; 1558-0210
• DOI: 10.1109/TNSRE.2022.3163503

The electroencephalogram (EEG), for measuring the electrophysiological activity of the brain, has been widely applied in automatic detection of epilepsy seizures. Various EEG-based seizure detection algorithms have already yielded high sensitivity, but training those algorithms requires a large amount of labelled data. Data labelling is often done with a lot of human efforts, which is very time-consuming. In this study, we propose a hybrid system integrating an unsupervised learning (UL) module and a supervised learning (SL) module, where the UL module can significantly reduce the workload of data labelling. For preliminary seizure screening, UL synthesizes amplitude-integrated EEG (aEEG) extraction, isolation forest-based anomaly detection, adaptive segmentation, and silhouette coefficient-based anomaly detection evaluation. The UL module serves to quickly locate the determinate subjects (seizure segments and seizure-free segments) and the indeterminate subjects (potential seizure candidates). Afterwards, more robust seizure detection for the indeterminate subjects is performed by the SL using an EasyEnsemble algorithm. EasyEnsemble, as a class-imbalance learning method, can potentially decrease the generalization error of the seizure-free segments. The proposed method can significantly reduce the workload of data labelling while guaranteeing satisfactory performance. The proposed seizure detection system is evaluated using the Children's Hospital Boston - Massachusetts Institute of Technology (CHB-MIT) scalp EEG dataset, and it achieves a mean accuracy of 92.62%, a mean sensitivity of 95.55%, and a mean specificity of 92.57%. To the best of our knowledge, this is the first epilepsy seizure detection study employing the integration of both the UL and the SL modules, achieving a competitive performance superior or similar to that of the state-of-the-art methods.