Optimizing Detection and Deep Learning-based Classification of Pathological High-Frequency Oscillations in Epilepsy

• DOI: 10.1101/2023.04.13.23288435
• Publication Date: 2023-04-18T04:45:12Z
• Authors: Tonmoy Monsoor; Yipeng Zhang; Atsuro Daida; Shingo Oana; Qiujing Lu; Shaun A. Hussain; Aria Fallah; Raman Sankar; Richard J. Staba; William Speier; Vwani Roychowdhury; Hiroki Nariai
• Keywords: Drug Resistant Epilepsy; Deep Learning; Epilepsy; Seizures; Machine learning; Humans; Deep learning; Electroencephalography; MNI; HFO; Child; STE

This study aimed to explore sensitive detection methods and deep learning (DL)-based classification for pathological high-frequency oscillations (HFOs).We analyzed interictal HFOs (80-500 Hz) in 15 children with medication-resistant focal epilepsy who underwent resection after chronic intracranial electroencephalogram via subdural grids. The were assessed using the short-term energy (STE) Montreal Neurological Institute (MNI) detectors examined features based on spike association time-frequency plot characteristics. A DL-based was applied purify HFOs. Postoperative seizure outcomes correlated HFO-resection ratios determine optimal HFO method.The MNI detector identified a higher percentage of than STE detector, but some detected only by detector. both exhibited most features. Union which detects either or outperformed other predicting postoperative before purification.HFOs standard automated displayed different signal morphological effectively purified HFOs.Enhancing will improve their utility outcomes.HFOs showed traits bias those detectorHFOs (the Intersection HFOs) deemed pathologicalA learning-based able distill HFOs, regard-less initial methods.