Wavelet based automatic seizure detection in intracerebral electroencephalogram
Montreal Neurological Institute and Department of Neurology and Neurosurgery, McGill University, Room 767, 3801 University Street, Quebec, Canada H3A 2B4. Clinical Neurophysiology
(Impact Factor: 3.1).
06/2003; 114(5):898-908. DOI: 10.1016/S1388-2457(03)00035-X
Automatic seizure detection is often used during long-term monitoring, and is particularly important during intracerebral investigations. Existing methods make many false detections, particularly in intracerebral electroencephalogram (EEG) because of frequent large amplitude rhythmic activity bursts that are non-epileptiform.
To develop a seizure detection method for intracerebral monitoring that is as sensitive as existing methods but has fewer false detections.
To capture the rhythmic nature of seizure discharges, we developed a wavelet-based method, examining how different frequency ranges fluctuate compared to the background. In particular, the system remembers rhythmic bursts occurring commonly in the background to avoid detecting them as seizures.
The method was evaluated on test data from 11 patients, including 229 h and 66 seizures, and its performance compared to the method of Gotman (Electroencephalogr clin Neurophysiol 76 (1990) 317). Detection sensitivity was unchanged at close to 90%, but false detections were reduced from 2.4 to 0.3/h.
Perfect sensitivity is unlikely because the morphology of seizure discharges is so variable. Nevertheless, the 87% sensitivity obtained in the combined training and testing data is quite high. We reduced the average false alarm rate to one per 3 h of recording, or 6 per 24-h period. Given how rapidly one can decide visually that a detection is erroneous, false detections should not cause any burden to the reviewer.
In intracerebral EEG it is possible to detect seizures automatically with high sensitivity and high specificity.
Available from: Omar Farooq
- "Normalization of features by 25 s background is done to provide robustness into features and to remove subject dependent variations. A gap of 15 s is used as the guard time between normal and seizure activity (Khan and Gotman, 2003). A seizure is considered to be detected if at least in one of the channels, seizure is detected i.e. minimum one detection is required to confirm the presence of a seizure. "
[Show abstract] [Hide abstract]
ABSTRACT: Detection of non-convulsive seizures (NCSz) is a challenging task because it lack convulsions, meaning no physical visible symptoms are there to detect the presence of a seizure activity. Hence its diagnosis is not easy, also continuous observation of full length EEG for the detection of non-convulsive seizures (NCSz) by expert or technician is a very exhaustive, time consuming job. A technique for the automatic detection of NCSz is proposed in this paper. Database used in this research was recorded at All India Institute of Medical Sciences (AIIMS), New Delhi. 13 EEG recordings of 9 subjects consisting of a total 23 seizures of 29.42 minutes duration were used for analysis. Normalized modified Wilson amplitude is used as a key feature to classify between normal and seizure activity. Main advantage of this study lies in the fact that no classifier is used here and hence algorithm is very simple and computationally fast. With the use of only one feature, all of the seizures under test were detected correctly, and hence the median sensitivity and specificity of 100% and 99.21% were achieved respectively.
Available from: S. Patidar
- "All rights reserved. http://dx.doi.org/10.1016/j.cmpb.2013.11.014 using the wavelet transform       , and the multiwavelet transform  have been developed. The research based on nonlinear parameters has been found clinically fruitful for detection and identification of epileptic seizure EEG signals. "
[Show abstract] [Hide abstract]
ABSTRACT: Epileptic seizure occurs as a result of abnormal transient disturbance in
the electrical activities of the brain. The electrical activities of brain fluctuate frequently
and can be analyzed using electroencephalogram (EEG) signals. Therefore,
the EEG signals are commonly used signal for obtaining the information related to
the pathological states of brain. The long-term EEG recordings of an epileptic patient
contain a large amount of EEG data which may require cumbersome and hectic
manual interpretations. Thus, automatic EEG signal analysis using advanced signal
processing techniques plays a significant role to recognize epilepsy in EEG recordings
of long duration. In this work, empirical mode decomposition (EMD) has been
applied for analysis of normal and epileptic seizure EEG signals. The EMD generates
the set of amplitude and frequency modulated components known as intrinsic
mode functions (IMFs). Two area measures have been computed, one for the graph
obtained as the analytic signal representation of IMFs in complex plane and another
for second-order difference plot (SODP) of IMFs of EEG signals. Both of these
area measures have been computed for first four IMFs of the normal and epileptic
seizure EEG signals. These eight features obtained from both area measures of
first four IMFs have been used as input feature set for classification of normal and
epileptic seizure EEG signals using least square support vector machine (LS-SVM)
classifier. Among all three kernel functions namely, linear, polynomial, and radial
basis function (RBF) used for classification, the RBF kernel has provided best classification
accuracy in the classification of normal and epileptic seizure EEG signals.
Available from: Tobias Loddenkemper
- "A wavelet decomposition results in components at multiple levels of resolution (computational microscopes) . This system has been evaluated in both intracranial and surface EEG recordings   . Principal component analysis (PCA) Identify the set of principal components using orthogonal transformation and sorted by variance. "
[Show abstract] [Hide abstract]
ABSTRACT: Nearly one-third of patients with epilepsy continue to have seizures despite optimal medication management. Systems employed to detect seizures may have the potential to improve outcomes in these patients by allowing more tailored therapies and might, additionally, have a role in accident and SUDEP prevention. Automated seizure detection and prediction require algorithms which employ feature computation and subsequent classification. Over the last few decades, methods have been developed to detect seizures utilizing scalp and intracranial EEG, electrocardiography, accelerometry and motion sensors, electrodermal activity, and audio/video captures. To date, it is unclear which combination of detection technologies yields the best results, and approaches may ultimately need to be individualized. This review presents an overview of seizure detection and related prediction methods and discusses their potential uses in closed-loop warning systems in epilepsy.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.