Automatic detection of epileptiform activity by single-level wavelet analysis

Sartoretto, Flavio; Ermani, Mario

doi:10.1016/s0013-4694(98)00116-3

Cited by 54 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Theoretically, DB4 has the most suitable waveform to retain the morphological traits of epileptic spike in different resolution levels (20), though there are still cases based on other wavelets yielding high detection rate. In Table 1, 3 out of 5 researches using DB4 wavelet yield detection rates over 90% (10,20,33), while only 3 out of 8 cases achieve this level of results with other mother wavelets (30,41,46). Nonclercq's work even pushes the detection rate to 99% on ideal toy data with DB4 (33).…”

Section: Per Hour (65)mentioning

confidence: 93%

“…Two crucial factors affecting the analysis result are the selection of mother wavelet and the number of decomposition levels (10,41). They are directly related to the prominence of spikes in corresponding subbands.…”

Section: Wavelet Featuresmentioning

confidence: 99%

“…Haar wavelet (10,42) Symlets family (10,48), all of them have been looked over for usability in spike detection. There are also other orthogonal wavelet choices (41). Among these mother wavelet, Daubechies of order 4 (DB4), which has been adopted mostly (10,20,28,33,47,49), offers better efficiency than others (10,20).…”

Section: Wavelet Featuresmentioning

confidence: 99%

See 2 more Smart Citations

A retrospective glance at automatic detection of epileptic spike in electroencephalogram

Zhou¹

2015

Eur J Bio Med Res

View full text Add to dashboard Cite

Automatic detection of epileptic spikes is an important clinical application. It has been developed nearly 40 years. Yet the current automatic detection results are still not as reliable as experienced human interpreters, mainly due to the complex morphology of spikes and the similarity between paroxysmal events in brain activities. By reviewing the previous work, it is noticeable that the implementation of wavelet, ANN and spatiotemporal analysis show promising prospect.By reasonable combination of detection strategies, the detection rate can reach 90% with acceptable false detection rate. Current researches also reveal the reality of lacking of uniform dataset and rules for algorithm comparison. This review aims to compare the pros and cons of current researches and discuss the trend of development in the future.

show abstract

Section: Per Hour (65)mentioning

confidence: 93%

Section: Wavelet Featuresmentioning

confidence: 99%

See 1 more Smart Citation

A retrospective glance at automatic detection of epileptic spike in electroencephalogram

Zhou¹

2015

Eur J Bio Med Res

View full text Add to dashboard Cite

show abstract

“…1) Relative amplitude 1 ( and : Voltage difference between the peak and valleys of a wave divided by the background amplitude (the subscript stands for the ascending branch and the subscript for the descending branch) (22) where is the background amplitude of wavelet coefficients at the time when the wave reaches the peak. The background amplitude is calculated using (20) and (21 Turning point is defined as the point where the slope decreases more than 50% compared to that of the preceding point for the first time (starting from the peak point).…”

Section: A Feature Extractionmentioning

confidence: 99%

“…However, most epilepsy detection algorithms in the literature are based on the identification of sharp transients such as spike and sharp wave [2]- [4], [8], [11], [17], [18], [20]. This is quite insufficient because during the ictal period the EEG often appears to be rhythmic and slow waves become an important sign in such circumstances.…”

Section: Introductionmentioning

confidence: 99%

A multistage, multimethod approach for automatic detection and classification of epileptiform EEG

Liu

Zhang

2002

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-An efficient system for detection of epileptic activity in ambulatory electroencephalogram (EEG) must be sensitive to abnormalities while keeping the false-detection rate to a low level. Such requirements could be fulfilled neither by single stage nor by simple method strategy, due to the extreme variety of EEG morphologies and frequency of artifacts. The present study proposes a robust system that combines multiple signal-processing methods in a multistage scheme, integrating adaptive filtering, wavelet transform, artificial neural network, and expert system. The system consists of two main stages: a preliminary screening stage in which data are reduced significantly, followed by an analytical stage. Unlike most systems that merely focus on sharp transients, our system also takes into account slow waves. A nonlinear filter for separation of nonstationary and stationary EEG components is also developed in this paper. The system was evaluated on testing data from 81 patients, totaling more than 800 hours of recordings. 90.0% of the epileptic events were correctly detected. The detection rate of sharp transients was 98.0% and overall false-detection rate was 6.1%. We conclude that our system has good performance in detecting epileptiform activities and the multistage multimethod approach is an appropriate way of solving this problem.Index Terms-Adaptive filtering, artificial neural network, electroencephalogram (EEG), epilepsy, wavelet transform.

show abstract

Wavelets

Freeman¹,

Quiroga²

2012

Imaging Brain Function With EEG

View full text Add to dashboard Cite

Automatic detection of epileptiform activity by single-level wavelet analysis

Cited by 54 publications

References 19 publications

A retrospective glance at automatic detection of epileptic spike in electroencephalogram

A retrospective glance at automatic detection of epileptic spike in electroencephalogram

A multistage, multimethod approach for automatic detection and classification of epileptiform EEG

Wavelets

Contact Info

Product

Resources

About