Autoencoding of long-term scalp electroencephalogram to detect epileptic seizure for diagnosis support system. (July 2019)

• Record Type: Journal Article
• Authors: Emami, Ali; Kunii, Naoto; Matsuo, Takeshi; Shinozaki, Takashi; Kawai, Kensuke; Takahashi, Hirokazu
• Is Part Of: Computers in biology and medicine. Volume 110(2019)
• Page Start: 227
• Page End: 233
• Publication Date: 2019-07
• Subjects: Autoencoder -- Seizure detection -- Scalp electroencephalogram -- Unsupervised learning -- Epilepsy; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2019.05.025
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Introduction: Epileptologists could benefit from a diagnosis support system that automatically detects seizures because visual inspection of long-term electroencephalograms (EEGs) is extremely time-consuming. However, the diversity of seizures among patients makes it difficult to develop universal features that are applicable for automatic seizure detection in all cases, and the rarity of seizures results in a lack of sufficient training data for classifiers. Methods: To overcome these problems, we utilized an autoencoder (AE), which is often used for anomaly detection in the field of machine learning, to perform seizure detection. We hypothesized that multichannel EEG signals are compressible by AE owing to their spatio-temporal coupling and that the AE should be able to detect seizures as anomalous events from an interictal EEG. Results: Through experiments, we found that the AE error was able to classify seizure and nonseizure states with a sensitivity of 100% in 22 out of 24 available test subjects and that the AE was better than the commercially available software BESA and Persyst for half of the test subjects. Conclusions: These results suggest that the AE error is a feasible candidate for a universal seizure detection feature. Highlights: Autoencoder (AE) was used to detect seizures as anomalous events from interictal EEG. Long-term EEG data from subjects with various backgrounds were tested. For these wide range of data, the AE error increased during detect seizures. The AE error is a feasible candidate for a universal seizure detection feature. An unsupervised form of learning in the AE offers practical advantages.