Imaging the time series of one single referenced EEG electrode for Epileptic Seizures Risk Analysis

TL;DR

This paper proposes a novel seizure risk prediction method using image transformations of single-electrode EEG time series and CNN-based likelihood estimation, showing promising results but requiring further validation.

Contribution

It introduces a new approach combining image transformation of EEG segments and CNN softmax likelihood averaging for seizure risk forecasting.

Findings

Effective seizure prediction for some patients and seizures.

Different thresholds improve forecasting performance.

Further testing needed for broader validation.

Abstract

The time series captured by a single scalp electrode (plus the reference electrode) of refractory epileptic patients is used to forecast seizures susceptibility. The time series is preprocessed, segmented, and each segment transformed into an image, using three different known methods: Recurrence Plot, Gramian Angular Field, Markov Transition Field. The likelihood of the occurrence of a seizure in a future predefined time window is computed by averaging the output of the softmax layer of a CNN, differently from the usual consideration of the output of the classification layer. By thresholding this likelihood, seizure forecasting has better performance. Interestingly, for almost every patient, the best threshold was different from 50%. The results show that this technique can predict with good results for some seizures and patients. However, more tests, namely more patients and more seizures, are needed to better understand the real potential of this technique.