Optimizing detection and deep learning-based classification of pathological high-frequency oscillations in epilepsy

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

doi:10.1016/j.clinph.2023.07.012

Optimizing detection and deep learning-based classification of pathological high-frequency oscillations in epilepsy

Clin Neurophysiol. 2023 Oct:154:129-140. doi: 10.1016/j.clinph.2023.07.012. Epub 2023 Aug 9.

Authors

Affiliations

¹ Department of Electrical and Computer Engineering, University of California, Los Angeles, CA, USA.
² Division of Pediatric Neurology, Department of Pediatrics, UCLA Mattel Children's Hospital, David Geffen School of Medicine, Los Angeles, CA, USA.
³ Department of Neurosurgery, UCLA Medical Center, David Geffen School of Medicine, Los Angeles, CA, USA.
⁴ Division of Pediatric Neurology, Department of Pediatrics, UCLA Mattel Children's Hospital, David Geffen School of Medicine, Los Angeles, CA, USA; The UCLA Children's Discovery and Innovation Institute, Los Angeles, CA, USA.
⁵ Department of Neurology, UCLA Medical Center, David Geffen School of Medicine, Los Angeles, CA, USA.
⁶ Department of Bioengineering, University of California, Los Angeles, CA, USA; Department of Radiological Sciences, University of California, Los Angeles, CA, USA.
⁷ Division of Pediatric Neurology, Department of Pediatrics, UCLA Mattel Children's Hospital, David Geffen School of Medicine, Los Angeles, CA, USA; The UCLA Children's Discovery and Innovation Institute, Los Angeles, CA, USA. Electronic address: hnariai@mednet.ucla.edu.

Abstract

Objective: This study aimed to explore sensitive detection methods for pathological high-frequency oscillations (HFOs) to improve seizure outcomes in epilepsy surgery.

Methods: We analyzed interictal HFOs (80-500 Hz) in 15 children with medication-resistant focal epilepsy who underwent chronic intracranial electroencephalogram via subdural grids. The HFOs were assessed using the short-term energy (STE) and Montreal Neurological Institute (MNI) detectors and examined for spike association and time-frequency plot characteristics. A deep learning (DL)-based classification was applied to purify pathological HFOs. Postoperative seizure outcomes were correlated with HFO-resection ratios to determine the optimal HFO detection method.

Results: The MNI detector identified a higher percentage of pathological HFOs than the STE detector, but some pathological HFOs were detected only by the STE detector. HFOs detected by both detectors had the highest spike association rate. The Union detector, which detects HFOs identified by either the MNI or STE detector, outperformed other detectors in predicting postoperative seizure outcomes using HFO-resection ratios before and after DL-based purification.

Conclusions: HFOs detected by standard automated detectors displayed different signal and morphological characteristics. DL-based classification effectively purified pathological HFOs.

Significance: Enhancing the detection and classification methods of HFOs will improve their utility in predicting postoperative seizure outcomes.

Keywords: Deep learning; HFO; MNI; Machine learning; STE.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

MeSH terms

Child
Deep Learning*
Drug Resistant Epilepsy* / diagnosis
Drug Resistant Epilepsy* / surgery
Electroencephalography / methods
Epilepsy* / diagnosis
Epilepsy* / surgery
Humans
Seizures

Abstract

Publication types

MeSH terms

Grants and funding