Seizure localisation with attention-based graph neural networks

作者：

Highlights：

• We present a new method for seizure localisation in subjects with epilepsy.

• Our method is based on graph neural networks (GNNs) with an attentional layer.

• The attention scores of the GNN predict the clinically-identified seizure onset zones.

• In uncertain clinical outcomes, our GNN also shows uncertainty in the localisation.

• Our method works well even in the case of small training datasets available.

摘要

•We present a new method for seizure localisation in subjects with epilepsy.•Our method is based on graph neural networks (GNNs) with an attentional layer.•The attention scores of the GNN predict the clinically-identified seizure onset zones.•In uncertain clinical outcomes, our GNN also shows uncertainty in the localisation.•Our method works well even in the case of small training datasets available.

论文关键词：Graph neural networks,Seizure localisation

论文评审过程：Received 31 January 2022, Revised 20 April 2022, Accepted 25 April 2022, Available online 5 May 2022, Version of Record 11 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117330