eduzhai > Applied Sciences > Engineering >

Staging Epileptogenesis with Deep Neural Networks

  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: Epilepsy is a common neurological disorder characterized by recurrentseizures accompanied by excessive synchronous brain activity. The process ofstructural and functional brain alterations leading to increased seizuresusceptibility and eventually spontaneous seizures is called epileptogenesis(EPG) and can span months or even years. Detecting and monitoring theprogression of EPG could allow for targeted early interventions that could slowdown disease progression or even halt its development. Here, we propose anapproach for staging EPG using deep neural networks and identify potentialelectroencephalography (EEG) biomarkers to distinguish different phases of EPG.Specifically, continuous intracranial EEG recordings were collected from arodent model where epilepsy is induced by electrical perforant pathwaystimulation (PPS). A deep neural network (DNN) is trained to distinguish EEGsignals from before stimulation (baseline), shortly after the PPS and longafter the PPS but before the first spontaneous seizure (FSS). Experimentalresults show that our proposed method can classify EEG signals from the threephases with an average area under the curve (AUC) of 0.93, 0.89, and 0.86. Tothe best of our knowledge, this represents the first successful attempt tostage EPG prior to the FSS using DNNs.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×