Abstract

EEG signal processing is a fundamental method for neurophysiology research and clinical neurology practice. Historically the classification of EEG into physiological, pathological, or artifacts has been performed by expert visual review of the recordings. However, the size of EEG data recordings is rapidly increasing with a trend for higher channel counts, greater sampling frequency, and longer recording duration and complete reliance on visual data review is not sustainable. In this study, we publicly share annotated intracranial EEG data clips from two institutions: Mayo Clinic, MN, USA and St. Anne’s University Hospital Brno, Czech Republic. The dataset contains intracranial EEG that are labeled into three groups: physiological activity, pathological/epileptic activity, and artifactual signals. The dataset published here should support and facilitate training of generalized machine learning and digital signal processing methods for intracranial EEG and promote research reproducibility. Along with the data, we also propose a statistical method that is recommended for comparison of candidate classifier performance utilizing out-of-institution/out-of-patient testing.

Highlights

  • Background & SummaryIntracranial electroencephalography is an invasive procedure commonly used for localization of epileptic seizure onset zones in patients with drug resistant epilepsy

  • The improvement of EEG acquisition systems, data storage, and surgical techniques allows for large scale data collection spanning over multiple days to weeks, recording from hundreds of electrodes with sampling rates reaching up to 32 kHz in research settings[1]

  • The automatic classification of artifacts and segmentation of Intracranial electroencephalography (iEEG) recordings is recognized as a challenging task, and many interesting studies have been published addressing the challenges[4,5]

Read more

Summary

Introduction

Background & SummaryIntracranial electroencephalography (iEEG) is an invasive procedure commonly used for localization of epileptic seizure onset zones in patients with drug resistant epilepsy. We have recently demonstrated robust generalization of automated detection algorithms for artifact classification using training and testing datasets collected from different institutions, acquisition systems, under different measurement conditions[7,8]. The patients undergoing the iEEG monitoring have electrodes implanted into the brain structures that are assumed to generate the epileptic/pathological activity like interictal epileptiform spikes and high-frequency-oscillations[13].

Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call