Automated detection of videotaped neonatal seizures based on motion segmentation methods

Karayiannis, N.B.; Tao, Guozhi; Frost, James D.; Wise, Merrill S.; Hrachovy, Richard A.; Mizrahi, Eli M.

doi:10.1016/j.clinph.2005.12.030

Cited by 60 publications

(41 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A second important contribution of [14] is the distinction made between different types of neonatal seizures. However, clinical manifestations of seizure such as the physical movements detected by this method are, by no means present in all neonatal seizures (in [15] Bye and Flanagan found that 85% of seizures were subclinical) and as a result this method cannot provide a complete solution to the problem, a limitation acknowledged by Karayiannis et al [16], [17]. Furthermore, many neonates under observation in the ICU are therapeutically paralyzed and so for these cases seizure-detection systems based on physical movement are not viable.…”

Section: Introductionmentioning

confidence: 93%

Electrocardiogram Based Neonatal Seizure Detection

Greene

Chazal²,

Boylan

et al. 2007

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-A method for the detection of seizures in the newborn using the electrocardiogram (ECG) signal is presented. Using a database of eight recordings, a method was developed for automatically annotating each 1-min epoch as "nonseizure" or "seizure." The system uses a linear discriminant classifier to process 41 heartbeat timing interval features. Performance assessment of the method showed that on a patient-specific basis an average accuracy of 70.5% was achieved in detecting seizures with associated sensitivity of 62.2% and specificity of 71.8%. On a patient-independent basis the average accuracy was 68.3% with sensitivity of 54.6% and specificity of 77.3%. Shifting the decision threshold for the patient-independent classifier allowed an increase in sensitivity to 78.4% at the expense of decreased specificity (51.6%), leading to increased false detections. The results of our ECG-based method are comparable with those reported for EEG-based neonatal seizure detection systems and offer the benefit of an easier acquisition methodology for seizure detection.

show abstract

Section: Introductionmentioning

confidence: 93%

Electrocardiogram Based Neonatal Seizure Detection

Greene

Chazal²,

Boylan

et al. 2007

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…Although movement detection is most studied in surveillance, some steps are already taken for the detection of epileptic seizures in adults [14] and neonates [10]. Liu et al [14] detected changes between video frames in a certain sequence of video data from epileptic seizures.…”

Section: Introductionmentioning

confidence: 99%

Automatic video detection of body movement during sleep based on optical flow in pediatric patients with epilepsy

Cuppens

Lagae

Ceulemans³

et al. 2010

Med Biol Eng Comput

View full text Add to dashboard Cite

The aim of our work is to investigate whether the optical flow algorithm applied to video recordings can be used to detect movement during sleep in pediatric patients with epilepsy. The optical flow algorithm allocates intensities to pixels proportional to their involvement in movement of an object. The average of a percentage of the highest movement vectors was plotted as a function of time (R(t)). The used dataset contains video data acquired at the University Hospital of Leuven consisting of normal sleep movement and seizure movement. We investigated R(t), to make a distinction between movement and non-movement. We used the acquisition parameters (320 x 240 at 12.5 fps), derived from a previous study (Cuppens et al., Proceedings of the 4th European congress of the international federation for medical and biological engineering (MBEC 2008), ECIFBME 2008, Antwerp, Belgium, IFMBE Proceedings, vol 22, pp 784-789, 2008). Two experiments were concluded, one with global thresholds of R(t) in all datasets and one with a variable threshold in each dataset. The latter is obtained by inspecting a non-movement epoch and calculating the mean and standard deviations of R(t) over time. The variable threshold on R(t) was then obtained for each dataset by adding to the mean a fixed multiple of the standard deviation. Optimal thresholds were derived based on a three-fold cross-validation. The best result was achieved when using a variable threshold, which resulted in a sensitivity of one in all the test sets and a PPV of 1, 0.821, and 1, respectively, for the three test sets.

show abstract

“…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].…”

Section: Introductionmentioning

confidence: 99%

“…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.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Markerless video analysis for movement quantification in pediatric epilepsy monitoring

Eng

Mandal

et al. 2011

2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

Abstract-This paper proposes a markerless video analytic system for quantifying body part movements in pediatric epilepsy monitoring. The system utilizes colored pajamas worn by a patient in bed to extract body part movement trajectories, from which various features can be obtained for seizure detection and analysis. Hence, it is non-intrusive and it requires no sensor/marker to be attached to the patient's body. It takes raw video sequences as input and a simple user-initialization indicates the body parts to be examined. In background/foreground modeling, Gaussian mixture models are employed in conjunction with HSV-based modeling. Body part detection follows a coarse-to-fine paradigm with graphcut-based segmentation. Finally, body part parameters are estimated with domain knowledge guidance. Experimental studies are reported on sequences captured in an Epilepsy Monitoring Unit at a local hospital. The results demonstrate the feasibility of the proposed system in pediatric epilepsy monitoring and seizure detection.

show abstract

Automated detection of videotaped neonatal seizures based on motion segmentation methods

Cited by 60 publications

References 16 publications

Electrocardiogram Based Neonatal Seizure Detection

Electrocardiogram Based Neonatal Seizure Detection

Automatic video detection of body movement during sleep based on optical flow in pediatric patients with epilepsy

Markerless video analysis for movement quantification in pediatric epilepsy monitoring

Contact Info

Product

Resources

About