Time CNN and Graph Convolution Network for Epileptic Spike Detection in MEG Data
This work addresses the burdensome and error-prone task of manual spike detection in epilepsy patients using MEG data, offering an automated solution with improved performance, though it is incremental as it builds on existing deep learning methods.
The authors tackled the problem of detecting epileptic spikes in MEG data, which is typically done manually and is error-prone, by proposing a hybrid 1D temporal CNN and graph convolutional network (GCN) model. Their method achieved an f1-score of 76.7% on a balanced dataset and 25.5% on a realistic imbalanced dataset, outperforming deep learning-based state-of-the-art approaches.
Magnetoencephalography (MEG) recordings of patients with epilepsy exhibit spikes, a typical biomarker of the pathology. Detecting those spikes allows accurate localization of brain regions triggering seizures. Spike detection is often performed manually. However, it is a burdensome and error prone task due to the complexity of MEG data. To address this problem, we propose a 1D temporal convolutional neural network (Time CNN) coupled with a graph convolutional network (GCN) to classify short time frames of MEG recording as containing a spike or not. Compared to other recent approaches, our models have fewer parameters to train and we propose to use a GCN to account for MEG sensors spatial relationships. Our models produce clinically relevant results and outperform deep learning-based state-of-the-art methods reaching a classification f1-score of 76.7% on a balanced dataset and of 25.5% on a realistic, highly imbalanced dataset, for the spike class.