Ensemble Deep Neural Network for Automatic Classification of EEG Independent Components

Lopes, Fábio; Leal, Adriana; Medeiros, Julio; Pinto, Mauro F; Dourado, António; Dümpelmann, Matthias; Teixeira, César

doi:10.1109/tnsre.2022.3154891

Cited by 9 publications

(7 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One important step is to remove artefacts naturally occurring in the non-controlled environment of presurgical monitoring. This step was performed using the algorithm developed by Lopes et al 33 described below. First, the scalp EEG signals were filtered using a 0.5–100 Hz bandpass 4th-order Butterworth filter and a 50 Hz 2nd-order notch filter.…”

Section: Methodsmentioning

confidence: 99%

Unsupervised EEG preictal interval identification in patients with drug-resistant epilepsy

Leal

Curty

Lopes

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

Typical seizure prediction models aim at discriminating interictal brain activity from pre-seizure electrographic patterns. Given the lack of a preictal clinical definition, a fixed interval is widely used to develop these models. Recent studies reporting preictal interval selection among a range of fixed intervals show inter- and intra-patient preictal interval variability, possibly reflecting the heterogeneity of the seizure generation process. Obtaining accurate labels of the preictal interval can be used to train supervised prediction models and, hence, avoid setting a fixed preictal interval for all seizures within the same patient. Unsupervised learning methods hold great promise for exploring preictal alterations on a seizure-specific scale. Multivariate and univariate linear and nonlinear features were extracted from scalp electroencephalography (EEG) signals collected from 41 patients with drug-resistant epilepsy undergoing presurgical monitoring. Nonlinear dimensionality reduction was performed for each group of features and each of the 226 seizures. We applied different clustering methods in searching for preictal clusters located until 2 h before the seizure onset. We identified preictal patterns in 90% of patients and 51% of the visually inspected seizures. The preictal clusters manifested a seizure-specific profile with varying duration (22.9 ± 21.0 min) and starting time before seizure onset (47.6 ± 27.3 min). Searching for preictal patterns on the EEG trace using unsupervised methods showed that it is possible to identify seizure-specific preictal signatures for some patients and some seizures within the same patient.

show abstract

Section: Methodsmentioning

confidence: 99%

Unsupervised EEG preictal interval identification in patients with drug-resistant epilepsy

Leal

Curty

Lopes

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although this process usually performs well in removing noise from EEG signals, it requires visual inspection of data, making it difficult when experts are not available. Consequently, several researchers have developed classifiers to automatically perform this task 12 , 16 – 27 .…”

Section: Background and Summarymentioning

confidence: 99%

“…Training set contains 43,038 (70.44%) brain ICs and 18,054 (29.56%) artifact ICs whereas testing set contains 11,437 (70.02%) brain ICs and 4,897 (29.98%) artifact ICs. These data were already used in a previous study 27 . In that study, authors concluded that using the three sources of information improved the IC classifiers’ performance.…”

Section: Background and Summarymentioning

confidence: 99%

See 1 more Smart Citation

EPIC: Annotated epileptic EEG independent components for artifact reduction

et al. 2022

Self Cite

View full text Add to dashboard Cite

Scalp electroencephalogram is a non-invasive multi-channel biosignal that records the brain’s electrical activity. It is highly susceptible to noise that might overshadow important data. Independent component analysis is one of the most used artifact removal methods. Independent component analysis separates data into different components, although it can not automatically reject the noisy ones. Therefore, experts are needed to decide which components must be removed before reconstructing the data. To automate this method, researchers have developed classifiers to identify noisy components. However, to build these classifiers, they need annotated data. Manually classifying independent components is a time-consuming task. Furthermore, few labelled data are publicly available. This paper presents a source of annotated electroencephalogram independent components acquired from patients with epilepsy (EPIC Dataset). This dataset contains 77,426 independent components obtained from approximately 613 hours of electroencephalogram, visually inspected by two experts, which was already successfully utilised to develop independent component classifiers.

show abstract

“…One important step is to remove artifacts naturally occurring in the non-controlled environment of presurgical monitoring. This step was performed using the algorithm developed by Lopes et al 33 . First, the scalp EEG signals were filtered using a 0.5-100 Hz bandpass 4th-order Butterworth filter and a 50 Hz 2nd-order notch filter.…”

Section: Eeg Signal Preprocessingmentioning

confidence: 99%

Unsupervised EEG Preictal Interval Identification in Patients with Drug-resistant Epilepsy

Leal

Curty

Lopes

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Typical seizure prediction models aim at discriminating interictal brain activity from pre-seizure electrographic patterns. Given the lack of a preictal clinical definition, a fixed interval is widely used to develop these models. Recent studies reporting preictal interval selection among a range of fixed intervals show inter- and intra-patient preictal interval variability, possibly reflecting the heterogeneity of the seizure generation process. Obtaining accurate labels of the preictal interval can be used to train supervised prediction models and, hence, avoid setting a fixed preictal interval for all seizures within the same patient. Unsupervised learning methods hold great promise for exploring preictal alterations on a seizure-specific scale. Multivariate and univariate linear and nonlinear features were extracted from scalp electroencephalography (EEG) signals collected from 41 patients with drug-resistant epilepsy undergoing presurgical monitoring. Nonlinear dimensionality reduction was performed for each group of features and each of the 226 seizures. We applied different clustering methods in searching for preictal clusters located until two hours before the seizure onset. We identified preictal patterns in 90% of patients and 51% of the visually inspected seizures. The preictal clusters manifested a seizure-specific profile with varying duration (22.9±21.0 minutes) and starting time before seizure onset (47.6±27.3 minutes). Searching for preictal patterns on the EEG trace using unsupervised methods showed that it is possible to identify seizure-speciﬁc preictal signatures for some patients and some seizures within the same patient.

show abstract

Ensemble Deep Neural Network for Automatic Classification of EEG Independent Components

Cited by 9 publications

References 61 publications

Unsupervised EEG preictal interval identification in patients with drug-resistant epilepsy

Unsupervised EEG preictal interval identification in patients with drug-resistant epilepsy

EPIC: Annotated epileptic EEG independent components for artifact reduction

Unsupervised EEG Preictal Interval Identification in Patients with Drug-resistant Epilepsy

Contact Info

Product

Resources

About