A new method for automatic marking epileptic spike-wave discharges in local field potential signals

Startceva, Sofia; Lüettjohann, Annika; Sysoev, Ilya V.; Luijtelaar, Gilles van

doi:10.1117/12.2179017

Cited by 4 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1, column "SB"). These results are beyond most methods reported previously [Ovchinnikov et al (2010); Startceva et al (2015); ], though it is not absolutely disastrous for our purpose, because the method is able to detect most event of interest.…”

Section: Resultsmentioning

confidence: 57%

“…They explicitly rely on increase of power in certain spectral ranges or indirectly use this fact to improve sensitivity and specificity ]. The exception is some approaches based on predictive models [Startceva et al (2015)]. For reinitiation detection using amplitude dynamics is unacceptable since we assume that a restart often supports discharge, that is, a significant drop in amplitude does not occur or is very short-term.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Detection Of Spike-Wave Discharge Restarts In Genetic Rat Model Based On Frequency Dynamics

Dolinina

Sysoeva

Rijn

et al. 2022

CAP

View full text Add to dashboard Cite

The spike-wave discharges in epileptic brain can be maintained by one or more sequential restarts, which should have mechanisms similar to those of discharge initiation. To examine this hypothesis an original algorithm for automatically determining restarts was developed. To implement the algorithm the windowed fast Fourier transform with a Hann window was used. The method was to track the frequency consecutive drops on a skeleton constructed from a spectrogram in a selected frequency range (7–12 Hz). The method does not rely on changes in the amplitude of the oscillations, while most of the known methods clearly rely on an increase in power in certain spectral ranges. Discharge restarts were successfully detected and were found to be not different from initial starts in terms of main frequency dynamics. Restarts were diagnosed in about four less often than starts. The existence of restarts confirms that different factors are responsible for maintenance of long spike-wave discharges: some discharges are supported by the special maintenance mechanism, others are continuous chains of short discharges.

show abstract

Section: Resultsmentioning

confidence: 57%

Section: Methodsmentioning

confidence: 99%

Detection Of Spike-Wave Discharge Restarts In Genetic Rat Model Based On Frequency Dynamics

Dolinina

Sysoeva

Rijn

et al. 2022

CAP

View full text Add to dashboard Cite

show abstract

“…We have developed an XGBoost-based algorithm, Epi-AI, that can generalise to multiple mouse models of both genetic and acquired epilepsies (Models I-III, with sensitivity 91.4%-98.8% on the mouse models used in training), including one not used in the training of the algorithm (Model IV, with sensitivity 76.3%). Previous studies have used only a single model on which to develop a detection approach [9,11,[13][14][15]40], limiting the translation and generalisation of techniques between models or individual users.…”

Section: Discussionmentioning

confidence: 99%

“…A key advantage of the Epi-AI approach is the combination of multiple different mouse models of epilepsy, with differing underlying epileptogenic mechanisms. To the best of our knowledge, none of the previously developed approaches [9,11,[13][14][15]40] have demonstrated that they can detect seizures in multiple mouse models of epilepsy in continuous EEG recordings (table 6). In previous studies, Pan et al [13], Jang et al [14] and Li et al [15] used machine learning approaches to detect seizure events in single mouse models of epilepsy, achieving 76.4% to 99.3% accuracy.…”

Section: Discussionmentioning

confidence: 99%

Detection of spontaneous seizures in EEGs in multiple experimental mouse models of epilepsy

et al. 2021

View full text Add to dashboard Cite

Objective. Electroencephalography (EEG) is a key tool for non-invasive recording of brain activity and the diagnosis of epilepsy. EEG monitoring is also widely employed in rodent models to track epilepsy development and evaluate experimental therapies and interventions. Whereas automated seizure detection algorithms have been developed for clinical EEG, preclinical versions face challenges of inter-model differences and lack of EEG standardization, leaving researchers relying on time-consuming visual annotation of signals. Approach. In this study, a machine learning-based seizure detection approach, ‘Epi-AI’, which can semi-automate EEG analysis in multiple mouse models of epilepsy was developed. Twenty-six mice with a total EEG recording duration of 6451 h were used to develop and test the Epi-AI approach. EEG recordings were obtained from two mouse models of kainic acid-induced epilepsy (Models I and III), a genetic model of Dravet syndrome (Model II) and a pilocarpine mouse model of epilepsy (Model IV). The Epi-AI algorithm was compared against two threshold-based approaches for seizure detection, a local Teager-Kaiser energy operator (TKEO) approach and a global Teager-Kaiser energy operator-discrete wavelet transform (TKEO-DWT) combination approach. Main results. Epi-AI demonstrated a superior sensitivity, 91.4%–98.8%, and specificity, 93.1%–98.8%, in Models I–III, to both of the threshold-based approaches which performed well on individual mouse models but did not generalise well across models. The performance of the TKEO approach in Models I–III ranged from 66.9%–91.3% sensitivity and 60.8%–97.5% specificity to detect spontaneous seizures when compared with expert annotations. The sensitivity and specificity of the TKEO-DWT approach were marginally better than the TKEO approach in Models I–III at 73.2%–80.1% and 75.8%–98.1%, respectively. When tested on EEG from Model IV which was not used in developing the Epi-AI approach, Epi-AI was able to identify seizures with 76.3% sensitivity and 98.1% specificity. Significance. Epi-AI has the potential to provide fast, objective and reproducible semi-automated analysis of multiple types of seizure in long-duration EEG recordings in rodents.

show abstract

Detection of seizure onset in childhood absence epilepsy

Aud'hui,

Kachenoura,

Yochum

et al. 2024

Clinical Neurophysiology

View full text Add to dashboard Cite

A new method for automatic marking epileptic spike-wave discharges in local field potential signals

Cited by 4 publications

References 17 publications

Detection Of Spike-Wave Discharge Restarts In Genetic Rat Model Based On Frequency Dynamics

Detection Of Spike-Wave Discharge Restarts In Genetic Rat Model Based On Frequency Dynamics

Detection of spontaneous seizures in EEGs in multiple experimental mouse models of epilepsy

Detection of seizure onset in childhood absence epilepsy

Contact Info

Product

Resources

About