Optical Flow Estimation Improves Automated Seizure Detection in Neonatal EEG.

PURPOSE: 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.

Neural correlates of unstructured motor behaviors.

OBJECTIVE: We studied the relationship between uninstructed, unstructured movements and neural activity in three epilepsy patients with intracranial electroencephalographic (iEEG) recordings. APPROACH: We used a custom system to continuously record high definition video precisely time-aligned to clinical iEEG data. From these video recordings, movement periods were annotated via semi-automatic tracking based on dense optical flow. MAIN RESULTS: We found that neural signal features (8-32 Hz and 76-100 Hz power) previously identified from task-based experiments are also modulated before and during a variety of movement behaviors. These movement behaviors are coarsely labeled by time period and movement side (e.g. 'Idle' and 'Move', 'Right' and 'Left'); movements within a label can include a wide variety of uninstructed behaviors. A rigorous nested cross-validation framework was used to classify both movement onset and lateralization with statistical significance for all subjects. SIGNIFICANCE: We demonstrate an evaluation framework to study neural activity related to natural movements not evoked by a task, annotated over hours of video. This work further establishes the feasibility to study neural correlates of unstructured behavior through continuous recording in the epilepsy monitoring unit. The insights gained from such studies may advance our understanding of how the brain naturally controls movement, which may inform the development of more robust and generalizable brain-computer interfaces.