Automated Interictal Epileptiform Discharge Detection from Scalp EEG Using Scalable Time-series Classification Approaches

D Nhu; M Janmohamed; L Shakhatreh; O Gonen; P Perucca; A Gilligan; P Kwan; TJ O’Brien; CW Tan; L Kuhlmann

Journal article

Automated Interictal Epileptiform Discharge Detection from Scalp EEG Using Scalable Time-series Classification Approaches

D Nhu, M Janmohamed, L Shakhatreh, O Gonen, P Perucca, A Gilligan, P Kwan, TJ O’Brien, CW Tan, L Kuhlmann

International Journal of Neural Systems | Published : 2023

DOI: 10.1142/S0129065723500016

Abstract

Deep learning for automated interictal epileptiform discharge (IED) detection has been topical with many published papers in recent years. All existing works viewed EEG signals as time-series and developed specific models for IED classification; however, general time-series classification (TSC) methods were not considered. Moreover, none of these methods were evaluated on any public datasets, making direct comparisons challenging. This paper explored two state-of-the-art convolutional-based TSC algorithms, InceptionTime and Minirocket, on IED detection. We fine-tuned and cross-evaluated them on a public (Temple University Events — TUEV) and two private datasets and provided ready metrics for..

View full abstract

University of Melbourne Researchers

Piero Perucca Author

Amanda Gilligan Author

Patrick Kwan Author

Levin Kuhlmann Author

Related Projects (2)

CRITICAL SLOWING ON LONG-TIME SCALES IS A BIOMARKER FOR EPILEPTIC SEIZURE FORECASTING

Changes in resilience - a phenomenon stemming from dynamical systems theory - has been observed in a wide range natural systems prior to a c..

INVESTIGATING THE GENETIC CONTRIBUTION TO THE FOCAL EPILEPSIES

Focal epilepsies are the most common forms of epilepsy. In most people with these epilepsies, no cause for the seizures can be identified wi..

Grants

Awarded by Norman Beischer Medical Research Foundation

Funding Acknowledgements

D. N. was supported by the GRIP scholarship at Monash University, Australia. P. K. is supported by a Practitioner Fellowship from the Australian Medical Research Future Fund (Grant No. MRF1136427).L. K. is supported by NHMRC Grant Nos.(GNT1183119 and GNT1160815). P. P. is supported by an Early Career Fellowship from the National Health and Medical Research Council (Grant No.APP1163708), the Epilepsy Foundation, the Royal Australasian College of Physicians, The University of Melbourne, Monash University, the Weary Dunlop Medical Research Foundation, Brain Australia, and the Norman Beischer Medical Research Foundation.