REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates

Arshia Afzal, Grigorios Chrysos, Volkan Cevher, Mahsa Shoaran
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:271-290, 2024.

Abstract

EEG-based seizure detection models face challenges in terms of inference speed and memory efficiency, limiting their real-time implementation in clinical devices. This paper introduces a novel graph-based residual state update mechanism (REST) for real-time EEG signal analysis in applications such as epileptic seizure detection. By leveraging a combination of graph neural networks and recurrent structures, REST efficiently captures both non-Euclidean geometry and temporal dependencies within EEG data. Our model demonstrates high accuracy in both seizure detection and classification tasks. Notably, REST achieves a remarkable 9-fold acceleration in inference speed compared to state-of-the-art models, while simultaneously demanding substantially less memory than the smallest model employed for this task. These attributes position REST as a promising candidate for real-time implementation in clinical devices, such as Responsive Neurostimulation or seizure alert systems.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-afzal24a, title = {{REST}: Efficient and Accelerated {EEG} Seizure Analysis through Residual State Updates}, author = {Afzal, Arshia and Chrysos, Grigorios and Cevher, Volkan and Shoaran, Mahsa}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {271--290}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/afzal24a/afzal24a.pdf}, url = {https://proceedings.mlr.press/v235/afzal24a.html}, abstract = {EEG-based seizure detection models face challenges in terms of inference speed and memory efficiency, limiting their real-time implementation in clinical devices. This paper introduces a novel graph-based residual state update mechanism (REST) for real-time EEG signal analysis in applications such as epileptic seizure detection. By leveraging a combination of graph neural networks and recurrent structures, REST efficiently captures both non-Euclidean geometry and temporal dependencies within EEG data. Our model demonstrates high accuracy in both seizure detection and classification tasks. Notably, REST achieves a remarkable 9-fold acceleration in inference speed compared to state-of-the-art models, while simultaneously demanding substantially less memory than the smallest model employed for this task. These attributes position REST as a promising candidate for real-time implementation in clinical devices, such as Responsive Neurostimulation or seizure alert systems.} }
Endnote
%0 Conference Paper %T REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates %A Arshia Afzal %A Grigorios Chrysos %A Volkan Cevher %A Mahsa Shoaran %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-afzal24a %I PMLR %P 271--290 %U https://proceedings.mlr.press/v235/afzal24a.html %V 235 %X EEG-based seizure detection models face challenges in terms of inference speed and memory efficiency, limiting their real-time implementation in clinical devices. This paper introduces a novel graph-based residual state update mechanism (REST) for real-time EEG signal analysis in applications such as epileptic seizure detection. By leveraging a combination of graph neural networks and recurrent structures, REST efficiently captures both non-Euclidean geometry and temporal dependencies within EEG data. Our model demonstrates high accuracy in both seizure detection and classification tasks. Notably, REST achieves a remarkable 9-fold acceleration in inference speed compared to state-of-the-art models, while simultaneously demanding substantially less memory than the smallest model employed for this task. These attributes position REST as a promising candidate for real-time implementation in clinical devices, such as Responsive Neurostimulation or seizure alert systems.
APA
Afzal, A., Chrysos, G., Cevher, V. & Shoaran, M.. (2024). REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:271-290 Available from https://proceedings.mlr.press/v235/afzal24a.html.

Related Material