STIED: A deep learning model for the SpatioTemporal detection of focal Interictal Epileptiform Discharges with MEG

TL;DR

STIED is a deep learning model that accurately detects and localizes interictal epileptiform discharges in MEG data, potentially improving clinical epilepsy diagnosis through automated analysis.

Contribution

This work introduces STIED, a novel supervised deep learning approach combining spatial and temporal features for MEG-based IED detection, inspired by clinical guidelines.

Findings

Achieved over 85% accuracy, sensitivity, and specificity in IED detection.

Successfully localized IEDs in both FE and presurgical epilepsy groups.

Demonstrated potential for clinical integration of DL in MEG analysis.

Abstract

Magnetoencephalography (MEG) allows the non-invasive detection of interictal epileptiform discharges (IEDs). Clinical MEG analysis in epileptic patients traditionally relies on the visual identification of IEDs, which is time consuming and partially subjective. Automatic, data-driven detection methods exist but show limited performance. Still, the rise of deep learning (DL)-with its ability to reproduce human-like abilities-could revolutionize clinical MEG practice. Here, we developed and validated STIED, a simple yet powerful supervised DL algorithm combining two convolutional neural networks with temporal (1D time-course) and spatial (2D topography) features of MEG signals inspired from current clinical guidelines. Our DL model enabled both temporal and spatial localization of IEDs in patients suffering from focal epilepsy with frequent and high amplitude spikes (FE group), with high-performance metrics-accuracy, specificity, and sensitivity all exceeding 85%-when learning from spatiotemporal features of IEDs. This performance can be attributed to our handling of input data, which mimics established clinical MEG practice. Reverse engineering further revealed that STIED encodes fine spatiotemporal features of IEDs rather than their mere amplitude. The model trained on the FE group also showed promising results when applied to a separate group of presurgical patients with different types of refractory focal epilepsy, though further work is needed to distinguish IEDs from physiological transients. This study paves the way of incorporating STIED and DL algorithms into the routine clinical MEG evaluation of epilepsy.