Transformer Convolutional Neural Networks for Automated Artifact Detection in Scalp EEG

Peh, Wei Yan; Yao, Yuanyuan; Dauwels, Justin

doi:10.1109/embc48229.2022.9871916

Cited by 11 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thirdly, investigating statistical differences in individual features within each feature set and its contribution in epilepsy diagnosis is important that it merits its own separate study. Though the IED detector is robust against artifacts, as observed by Peh et al [48,49], a separate artifact rejection module may help to improve the overall performance of the system. We intend to explore this avenue in future studies.…”

Section: Classification Of Epileptic Eegs With and Without Ieds Vs No...mentioning

confidence: 96%

Improving automated diagnosis of epilepsy from EEGs beyond IEDs

Thangavel

Thomas²,

Sinha³

et al. 2022

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

Objective: Clinical diagnosis of epilepsy relies partially on identifying Interictal Epileptiform Discharges (IEDs) in scalp electroencephalograms (EEGs). This process is expert-biased, tedious, and can delay the diagnosis procedure. Beyond automatically detecting IEDs, there are far fewer studies on automated methods to differentiate epileptic EEGs (potentially without IEDs) from normal EEGs. In addition, the diagnosis of epilepsy based on a single EEG tends to be low. Consequently, there is a strong need for automated systems for EEG interpretation. Traditionally, epilepsy diagnosis relies heavily on IEDs. However, since not all epileptic EEGs exhibit IEDs, it is essential to explore IEDindependent EEG measures for epilepsy diagnosis. The main objective is to develop an automated system for detecting epileptic EEGs, both with or without IEDs. In order to detect epileptic EEGs without IEDs, it is crucial to include EEG features in the algorithm that are not directly related to IEDs. Approach: In this study, we explore the background characteristics of interictal EEG for automated and more reliable diagnosis of epilepsy. Specifically, we investigate features based on univariate temporal measures (UTM), spectral, wavelet, Stockwell, connectivity, and graph metrics of EEGs, besides patient-related information (age and vigilance state). The evaluation is performed on a sizeable cohort of routine scalp EEGs (685 epileptic EEGs and 1229 normal EEGs) from five centers across Singapore, USA, and India. Main results: In comparison with the current literature, we obtained an improved Leave-One-Subject-Out (LOSO) cross-validation (CV) area under the curve (AUC) of 0.871 (Balanced Accuracy (BAC) of 80.9%) with a combination of 3 features (IED rate, and Daubechies and Morlet wavelets) for the classification of EEGs with IEDs vs. normal EEGs. The IED-independent feature UTM achieved a LOSO CV AUC of 0.809 (BAC of 74.4%). The inclusion of IED-independent features also helps to improve the EEG-level classification of epileptic EEGs with and without IEDs vs. normal EEGs, achieving an AUC of 0.822 (BAC of 77.6%) compared to 0.688 (BAC of 59.6%) for classification only based on the IED rate. Specifically, the addition of IED-independent features improved the BAC by 21% in detecting epileptic EEGs that do not contain IEDs. Significance: These results pave the way towards automated detection of epilepsy. We are one of the first to analyse epileptic EEGs without IEDs, thereby opening up an underexplored option in epilepsy diagnosis.

show abstract

Section: Classification Of Epileptic Eegs With and Without Ieds Vs No...mentioning

confidence: 96%

Improving automated diagnosis of epilepsy from EEGs beyond IEDs

Thangavel

Thomas²,

Sinha³

et al. 2022

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Additionally, we will address the problem of detecting artifacts before seizure detection. 49 The artifact detector will be designed to reduce FPR/h and improve the PRE of the seizure detector. Con…”

Section: Discussionmentioning

confidence: 99%

“…The architecture is the same as in the CNN-BM model, but we insert an additional transformer encoder between the final convolutional layer and the flattening layer (see Ref. 49). We implemented a transformer in tandem with the CNN, as the CNN alone cannot model correlations between distant data points, such as seizure morphologies.…”

Section: Cnn-trf-bm Modelmentioning

confidence: 99%

Six-Center Assessment of CNN-Transformer with Belief Matching Loss for Patient-Independent Seizure Detection in EEG

Peh

Thangavel

Yao

et al. 2023

Int. J. Neur. Syst.

View full text Add to dashboard Cite

Neurologists typically identify epileptic seizures from electroencephalograms (EEGs) by visual inspection. This process is often time-consuming, especially for EEG recordings that last hours or days. To expedite the process, a reliable, automated, and patient-independent seizure detector is essential. However, developing a patient-independent seizure detector is challenging as seizures exhibit diverse characteristics across patients and recording devices. In this study, we propose a patient-independent seizure detector to automatically detect seizures in both scalp EEG and intracranial EEG (iEEG). First, we deploy a convolutional neural network with transformers and belief matching loss to detect seizures in single-channel EEG segments. Next, we extract regional features from the channel-level outputs to detect seizures in multi-channel EEG segments. At last, we apply post-processing filters to the segment-level outputs to determine seizures’ start and end points in multi-channel EEGs. Finally, we introduce the minimum overlap evaluation scoring as an evaluation metric that accounts for minimum overlap between the detection and seizure, improving upon existing assessment metrics. We trained the seizure detector on the Temple University Hospital Seizure (TUH-SZ) dataset and evaluated it on five independent EEG datasets. We evaluate the systems with the following metrics: sensitivity (SEN), precision (PRE), and average and median false positive rate per hour (aFPR/h and mFPR/h). Across four adult scalp EEG and iEEG datasets, we obtained SEN of 0.617–1.00, PRE of 0.534–1.00, aFPR/h of 0.425–2.002, and mFPR/h of 0–1.003. The proposed seizure detector can detect seizures in adult EEGs and takes less than 15[Formula: see text]s for a 30[Formula: see text]min EEG. Hence, this system could aid clinicians in reliably identifying seizures expeditiously, allocating more time for devising proper treatment.

show abstract

“…This may also be one of the main barriers to transferring the EEG technique to clinical practice. The convolutional neural network has recently been proposed to automatically discard motion artifacts from the EEG signal, with promising results (accuracy∼80%) [ [106] , [107] , [108] ]. Further benchmark studies of different network architectures are still needed to design a robust and generalizable real-time system for clinical use from a larger database without the assistance of technical staff.…”

Section: Discussionmentioning

confidence: 99%

Early detection of Parkinson's disease: Systematic analysis of the influence of the eyes on quantitative biomarkers in resting state electroencephalography

Gimenez-Aparisi,

Guijarro-Estelles,

Chornet-Lurbe

et al. 2023

Heliyon

View full text Add to dashboard Cite

Transformer Convolutional Neural Networks for Automated Artifact Detection in Scalp EEG

Cited by 11 publications

References 13 publications

Improving automated diagnosis of epilepsy from EEGs beyond IEDs

Improving automated diagnosis of epilepsy from EEGs beyond IEDs

Six-Center Assessment of CNN-Transformer with Belief Matching Loss for Patient-Independent Seizure Detection in EEG

Early detection of Parkinson's disease: Systematic analysis of the influence of the eyes on quantitative biomarkers in resting state electroencephalography

Contact Info

Product

Resources

About