Speaker
Description
Photosensitivity is a neurological disorder where the brain produces abnormal epileptic reactions to visual stimuli known as Photoparoxysmal Responses (PPR), which can sometimes result in epilepsy seizures. Diagnosing this condition uses Intermittent Photic Stimulation (IPS), which involves exposing the patient to flashing lights -firstly, at increasing frequencies and, secondly, at decreasing frequencies- while recording brain activity using an Electroencephalogram (EEG). Neurophysiologists observe the EEG signals to identify PPR, taking care to prevent triggering an epileptic seizure and halting the process if necessary. Because of the nature of the stimulation and the low prevalence of photosensitivity, automatically detecting these events is challenging because PPR activity represents minority events of unusual brain activity amidst a large volume of regular recordings.
In previous research, a Variational AutoEncoder (VAE) was used to label EEG recordings from IPS sessions; with the encoder and the decoder incorporating recurrent neural networks and dense layers to deal with the EEG channels' time series. The performance of the VAE outperformed the current state of the art and a battery of unsupervised anomaly detection methods. However, training the VAE involved Leave-One-Subject-Out cross-validation with a short number of records (gathered from up to 9 diagnosed photosensitive patients); thus, this proposal needs testing on patients who do not have photosensitivity.
This study tackles this issue, gathering data from 5 patients who, although suffering from epilepsy, are not photosensitive. In accomplishing this, the VAE training uses data from 9 patients from prior research. The resulting model then evaluates each non-photosensitive patient, identifying anomalous EEG channel sequences of values.
Results show the performance of the proposed VAE when analysing the data of these patients, either from the computer science or the neurophysiologists' point of view. This discussion leads to the design of the new generation of VAE to improve the overall performance.
