Abstract
Localization of epileptic focus is a worldwide problem. Many studies find that high frequency oscillations (HFOs) seem to be a very specific indicator of the seizure onset zone (SOZ) in recent years. However, it is hard to detect HFOs accurately and many algorithms have a high sensitivity but unsatisfactory specificity. In this study, a novel method combining wavelet decomposition and back propagation (BP) neural network was proposed to increase the specificity of HFOs detection. Three epileptic patients with medically intractable epilepsy were recruited and underwent an individually presurgical monitoring with around 54–90 channels of intracranial electroencephalograph (iEEG). Over 3970 analyzed HFOs events from 420 hours of iEEG data, the sensitivity and the false discovery rate (FDR) of the present approach were 90% and 8.50%, respectively. The obtained results showed that the proposed BP neural network combined with wavelet decomposition could obviously decrease the influence of spikes and high-frequency noise caused by patient motion, which both are similar to HFOs, meanwhile effectively improve the specificity of HFOs detection.
Published Version
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
