Ali Emami1, Naoto Kunii2, Takeshi Matsuo3, Takashi Shinozaki4, Kensuke Kawai5, Hirokazu Takahashi6. 1. Research Center for Advanced Science and Technology, The University of Tokyo, Japan. 2. Department of Neurosurgery, Graduate School of Medicine, The University of Tokyo, Japan. 3. Tokyo Metropolitan Neurological Hospital, Japan. 4. National Institute of Information and Communications Technology, Japan. 5. Department of Neurosurgery, Jichi Medical University, Japan. Electronic address: kenkawai-tky@umin.net. 6. Research Center for Advanced Science and Technology, The University of Tokyo, Japan. Electronic address: takahashi@i.u-tokyo.ac.jp.
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.
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.