Time-Series Generative Adversarial Network Approach of Deep Learning Improves Seizure Detection From the Human Thalamic SEEG

Bhargava Ganti; Ganne Chaitanya; Ridhanya Sree Balamurugan; Nithin Nagaraj; Karthi Balasubramanian; Sandipan Pati

doi:10.3389/fneur.2022.755094

Time-Series Generative Adversarial Network Approach of Deep Learning Improves Seizure Detection From the Human Thalamic SEEG

Front Neurol. 2022 Feb 16:13:755094. doi: 10.3389/fneur.2022.755094. eCollection 2022.

Authors

Bhargava Ganti¹, Ganne Chaitanya^{2

3}, Ridhanya Sree Balamurugan⁴, Nithin Nagaraj⁵, Karthi Balasubramanian¹, Sandipan Pati^{2

3}

Affiliations

¹ Department of Electronics and Communication Engineering, Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore, India.
² Texas Institute of Restorative Neurotechnologies, University of Texas Health Science Center, Houston, TX, United States.
³ Department of Neurology, University of Alabama at Birmingham, Birmingham, AL, United States.
⁴ School of Biotechnology, National Institute of Technology Calicut, Kozhikode, India.
⁵ Consciousness Studies Programme, National Institute of Advanced Studies, Bengaluru, India.

Abstract

Seizure detection algorithms are often optimized to detect seizures from the epileptogenic cortex. However, in non-localizable epilepsies, the thalamus is frequently targeted for neuromodulation. Developing a reliable seizure detection algorithm from thalamic SEEG may facilitate the translation of closed-loop neuromodulation. Deep learning algorithms promise reliable seizure detectors, but the major impediment is the lack of larger samples of curated ictal thalamic SEEG needed for training classifiers. We aimed to investigate if synthetic data generated by temporal Generative Adversarial Networks (TGAN) can inflate the sample size to improve the performance of a deep learning classifier of ictal and interictal states from limited samples of thalamic SEEG. Thalamic SEEG from 13 patients (84 seizures) was obtained during stereo EEG evaluation for epilepsy surgery. Overall, TGAN generated synthetic data augmented the performance of the bidirectional Long-Short Term Memory (BiLSTM) performance in classifying thalamic ictal and baseline states. Adding synthetic data improved the accuracy of the detection model by 18.5%. Importantly, this approach can be applied to classify electrographic seizure onset patterns or develop patient-specific seizure detectors from implanted neuromodulation devices.

Keywords: Bidirectional Long-Short Term Memory (Bi-LSTM); Generative Adversarial Network (GAN); seizure detection algorithm; temporal lobe epilepsy; thalamus.