Optical Flow Estimation Improves Automated Seizure Detection in Neonatal EEG

Joel R Martin, Paolo Gabriel, Jeffrey Gold, Richard Haas, Sue Davis, David Gonda, Cia Sharpe, Scott Wilson, Nicolas Nierenberg, Mark Scheuer, Sonya Wang

Research output: Contribution to journalArticlepeer-review

1 Scopus citations


INTRODUCTION: Existing automated seizure detection algorithms report sensitivities between 43% and 77% and specificities between 56% and 90%. The algorithms suffer from false alarms when applied to neonatal EEG because of the high degree of nurse handling and rhythmic patting used to soothe neonates. Computer vision technology that quantifies movement in real time could distinguish artifactual motion and improve automated neonatal seizure detection algorithms.

METHODS: The authors used video EEG recordings from 43 neonates undergoing monitoring for seizures as part of the NEOLEV2 clinical trial. The Persyst neonatal automated seizure detection algorithm ran in real time during study EEG acquisitions. Computer vision algorithms were applied to extract detailed accounts of artifactual movement of the neonate or people near the neonate though dense optical flow estimation.

RESULTS: Using the methods mentioned above, 197 periods of patting activity were identified and quantified, of which 45 generated false-positive automated seizure detection events. A binary patting detection algorithm was trained with a subset of 470 event videos. This supervised detection algorithm was applied to a testing subset of 187 event videos with 8 false-positive events, which resulted in a 24% reduction in false-positive automated seizure detections and a 50% reduction in false-positive events caused by neonatal care patting, while maintaining 11 of 12 true-positive seizure detection events.

CONCLUSIONS: This work presents a novel approach to improving automated seizure detection algorithms used during neonatal video EEG monitoring. This artifact detection mechanism can improve the ability of a seizure detector algorithm to distinguish between artifact and true seizure activity.

Original languageEnglish (US)
Pages (from-to)235-239
Number of pages5
JournalJournal of clinical neurophysiology : official publication of the American Electroencephalographic Society
Issue number3
Early online dateAug 17 2020
StatePublished - Mar 1 2022

Bibliographical note

Funding Information:
This work was partially funded by the NEOLEV-2 trial (FDA R01FD004147) and the University of California, San Diego Young Investigator Fund.

Publisher Copyright:
© 2022 Lippincott Williams and Wilkins. All rights reserved.


  • Algorithms
  • Artifacts
  • Electroencephalography/methods
  • Humans
  • Infant, Newborn
  • Optic Flow
  • Seizures/diagnosis

PubMed: MeSH publication types

  • Journal Article


Dive into the research topics of 'Optical Flow Estimation Improves Automated Seizure Detection in Neonatal EEG'. Together they form a unique fingerprint.

Cite this