EUVIMEDEUVIMED entdecken
Crossref

Attention-based deep convolutional neural network for classification of generalized and focal epileptic seizures

Taimur Shahzad Gill, Syed Sajjad Haider Zaidi, Muhammad Ayaz Shirazi

Epilepsy & Behavior · 2024

DOI: 10.1016/j.yebeh.2024.109732 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Epilepsy & Behavior, 2024. Verfasst von Taimur Shahzad Gill und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics and Power Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan. Electronic address: taimu…. Hauptthemen laut MEDLINE: Electroencephalography, Neural Networks, Computer, Seizures, Epilepsies, Partial. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 83 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Epilepsy affects over 50 million people globally. Electroencephalography is critical for epilepsy diagnosis, but manual seizure classification is time-consuming and requires extensive expertise. This paper presents an automated multi-class seizure classification model using EEG signals from the Temple University Hospital Seizure Corpus ver. 1.5.2. 11 features including time-based correlation, time-based eigenvalues, power spectral density, frequency-based correlation, frequency-based eigenvalues, sample entropy, spectral entropy, logarithmic sum, standard deviation, absolute mean, and ratio of Daubechies D4 wavelet transformed coefficients were extracted from 10-second sliding windows across channels. The model combines multi-head self-attention mechanism with a deep convolutional neural network (CNN) to classify seven subtypes of generalized and focal epileptic seizures. The model achieved 0.921 weighted accuracy and 0.902 weighted F1 score in classifying focal onset non-motor, generalized onset non-motor, simple partial, complex partial, absence, tonic, and tonic-clonic seizures. In comparison, a CNN model without multi-head attention achieved 0.767 weighted accuracy. Ablation studies were conducted to validate the importance of transformer encoders and attention. The promising classification results demonstrate the potential of deep learning for handling EEG complexity and improving epilepsy diagnosis. This seizure classification model could enable timely interventions when translated into clinical practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyNeural Networks, ComputerSeizuresEpilepsies, PartialHumansDeep LearningAttentionMaleAdultFemaleEpilepsy, GeneralizedYoung Adult

Stichwörter der Autor:innen

Convolution Neural NetworkElectroencephalogramEpilepsyEpileptic SeizuresMulti-Headed Attention Mechanism

Autor:innen und Institutionen

  • Department of Electronics and Power Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan. Electronic address: taimur.beee19pnec@student.nust.edu.pk.
  • Department of Electronics and Power Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan. Electronic address: sajjadzaidi@pnec.nust.edu.pk.
  • Department of Electronics and Power Engineering, National University of Sciences and Technology, Islamabad 44000, Pakistan. Electronic address: ayaz.shirazi@pnec.nust.edu.pk.

Zitieren

APA

Gill, T. S., Zaidi, S. S. H., & Shirazi, M. A. (2024). Attention-based deep convolutional neural network for classification of generalized and focal epileptic seizures. Epilepsy & Behavior. https://doi.org/10.1016/j.yebeh.2024.109732

Vancouver

Gill TS, Zaidi SSH, Shirazi MA. Attention-based deep convolutional neural network for classification of generalized and focal epileptic seizures. Epilepsy & Behavior. 2024. doi:10.1016/j.yebeh.2024.109732

BibTeX
@article{Gill2024,
  author = {Gill, Taimur Shahzad and Zaidi, Syed Sajjad Haider and Shirazi, Muhammad Ayaz},
  title = {Attention-based deep convolutional neural network for classification of generalized and focal epileptic seizures},
  journal = {Epilepsy & Behavior},
  year = {2024},
  doi = {10.1016/j.yebeh.2024.109732}
}
Kostenlos starten →