Automatic annotation correction for wearable EEG based epileptic seizure detection.

Autor:	Zhang J; Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium., Chatzichristos C; Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium., Vandecasteele K; Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium., Swinnen L; Laboratory for Epilepsy Research, KU Leuven, Leuven, Belgium., Broux V; Department of Neurology, Reference Center for Refractory Epilepsy, UZ Leuven, Leuven, Belgium., Cleeren E; Department of Neurology, Reference Center for Refractory Epilepsy, UZ Leuven, Leuven, Belgium., Van Paesschen W; Laboratory for Epilepsy Research, KU Leuven, Leuven, Belgium.; Department of Neurology, Reference Center for Refractory Epilepsy, UZ Leuven, Leuven, Belgium., De Vos M; Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium.; Department of Development and Regeneration, KU Leuven, Leuven, Belgium.
Jazyk:	angličtina
Zdroj:	Journal of neural engineering [J Neural Eng] 2022 Feb 28; Vol. 19 (1). Date of Electronic Publication: 2022 Feb 28.
DOI:	10.1088/1741-2552/ac54c1
Abstrakt:	Objective . Video-electroencephalography (vEEG), which defines the ground truth for the detection of epileptic seizures, is inadequate for long-term home monitoring. Thanks to advantages in comfort and unobtrusiveness, wearable EEG devices have been suggested as a solution for home monitoring. However, one of the challenges in data-driven automated seizure detection with wearable EEG data is to have reliable seizure annotations. Seizure annotations on the gold-standard 25-channel vEEG recordings may not be optimal to delineate seizure activity on the concomitantly recorded wearable EEG, due to artifacts or absence of ictal activity on the limited set of electrodes of the wearable EEG. This paper aims to develop an automatic approach to correct for imperfect annotations of seizure activity on wearable EEG, which can be used to train seizure detection algorithms. Approach . This paper first investigates the effectiveness of correcting the seizure annotations for the training set with a visual annotation correction. Then a novel approach has been proposed to automatically remove non-seizure data from wearable EEG in epochs annotated as seizures in gold-standard video-EEG recordings. The performance of the automatic annotation correction approach was evaluated by comparing the seizure detection models trained with (a) original vEEG seizure annotations, (b) visually corrected seizure annotations, and (c) automatically corrected seizure annotations. Main results . The automated seizure detection approach trained with automatically corrected seizure annotations was more sensitive and had fewer false-positive detections compared to the approach trained with visually corrected seizure annotations, and the approach trained with the original seizure annotations from gold-standard vEEG. Significance . The wearable EEG seizure detection approach performs better when trained with automatic seizure annotation correction. (© 2022 IOP Publishing Ltd.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu