Automated Detection of Videotaped Neonatal Seizures of Epileptic Origin

Abstract

Summary:Purpose: This study aimed at the development of a seizure-detection system by training neural networks with quantitative motion information extracted from short video segments of neonatal seizures of the myoclonic and focal clonic types and random infant movements.Methods: The motion of the infants' body parts was quantified by temporal motion-strength signals extracted from video segments by motion-segmentation methods based on optical flow computation. The area of each frame occupied by the infants' moving body parts was segmented by clustering the motion parameters obtained by fitting an affine model to the pixel velocities. The motion of the infants' body parts also was quantified by temporal motion-trajectory signals extracted from video recordings by robust motion trackers based on block-motion models. These motion trackers were developed to adjust autonomously to illumination and contrast changes that may occur during the video-frame sequence. Video segments were represented by quantitative features obtained by analyzing motion-strength and motion-trajectory signals in both the time and frequency domains. Seizure recognition was performed by conventional feedforward neural networks, quantum neural networks, and cosine radial basis function neural networks, which were trained to detect neonatal seizures of the myoclonic and focal clonic types and to distinguish them from random infant movements.Results: The computational tools and procedures developed for automated seizure detection were evaluated on a set of 240 video segments of 54 patients exhibiting myoclonic seizures (80 segments), focal clonic seizures (80 segments), and random infant movements (80 segments). Regardless of the decision scheme used for interpreting the responses of the trained neural networks, all the neural network models exhibited sensitivity and specificity >90%. For one of the decision schemes proposed for interpreting the responses of the trained neural networks, the majority of the trained neural-network models exhibited sensitivity >90% and specificity >95%. In particular, cosine radial basis function neural networks achieved the performance targets of this phase of the project (i.e., sensitivity >95% and specificity >95%).Conclusions: The best among the motion segmentation and tracking methods developed in this study produced quantitative features that constitute a reliable basis for detecting neonatal seizures. The performance targets of this phase of the project were achieved by combining the quantitative features obtained by analyzing motion-strength signals with those produced by analyzing motion-trajectory signals. The computational procedures and tools developed in this study to perform off-line analysis of short video segments will be used in the next phase of this project, which involves the integration of these procedures and tools into a system that can process and analyze long video recordings of infants monitored for seizures in real time.

Quantifying Limb Movements in Epileptic Seizures Through Color-Based Video Analysis

“…Furthermore, as a motion-based method, tracking tends to become unreliable over time. Thus, the maximum length of the processed video segments in [15]- [19] is only 20 s and this approach is not suitable for long-term monitoring either. This paper proposes a new unobtrusive color-based video analytic system for quantifying limb movements in epileptic seizure monitoring, as shown in Fig.…”

“…This paper focuses on unobtrusive video-based seizure detection. To the best of our knowledge, the only existing system in this category is developed by Karayiannis et al for neonates [15]- [19]. They select anatomic sites on moving limbs by thresholding the motion vector magnitudes and then track the selected sites.…”

Markerless video analysis for movement quantification in pediatric epilepsy monitoring

“…This approach relies purely on motion information so the level of details in quantifications is limited and coarse. As a motion-based method, tracking tends to become unreliable over time so the processed video segments are only up to 20 seconds long in [9], [10]. In clinical studies, this system is only applied to manually selected sequences to differentiate neonatal seizures from random movements [9], [10].…”

“…We can see that for a pediatric population, these solutions are problematic. Thus, this paper focuses on non- To the best of the authors' knowledge, the only existing non-intrusive markerless video-based seizure detection system is the one developed by the University of Houston for neonates [9], [10]. Anatomic sites on the moving body part are selected by thresholding the magnitudes of the motion vectors and then the selected sites are tracked.…”

“…The objective is to quantify body part movements in greater details than the motion-based system in [9], [10], and comparable to the marker-based or accelerometer-based systems. We propose such a system that only requires a patient to wear a pajama with specific colors, without attaching any sensor or marker to his/her body.…”