EUVIMEDEUVIMED entdecken
Crossref

An Efficient Deep Learning Framework for Automated Epileptic Seizure Detection: Toward Scalable and Clinically Applicable Solutions

Dezan Ji, Haozhou Cui, Haotian Li, Guoyang Liu, Zhen Liu, Wei Shang, Yi Li, Weidong Zhou

Developmental Neurobiology · 2025-07 · 85 (3)

DOI: 10.1002/dneu.22983 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Developmental Neurobiology, online erschienen am 07.07.2025. Verfasst von Dezan Ji und 7 weiteren Autor:innen. Beteiligte Einrichtung: Shenzhen Institute of Shandong University, Shenzhen, P. R. China. Hauptthemen laut MEDLINE: Deep Learning, Electroencephalography, Epilepsy, Seizures. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Shenzhen Science and Technology Innovation Program, Key Program of the Natural Science Foundation of Shandong Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In this study, we present an efficient epileptic seizure detection framework driven by a graph convolutional neural network (GCNN). Unlike conventional methods that primarily rely on local features or complex feature engineering, our GCNN‐based approach explicitly encodes the spatial dependencies among electroencephalogram (EEG) electrodes, thereby capturing more comprehensive spatiotemporal features. A minimal preprocessing pipeline, consisting only of bandpass filtering and segmenting, reduces system complexity and computational overhead. On the CHB‐MIT scalp EEG database, our method achieved an average accuracy of 98.64%, sensitivity of 99.49%, and specificity of 98.64% at the segment‐based level and sensitivity of 96.81% with FDR of 0.27/h at the event‐based level. On the SH‐SDU database we collected, the method yielded segment‐based accuracy of 95.23%, sensitivity of 92.42%, and specificity of 95.25%, along with event‐based sensitivity of 94.11%. The average testing time for 1 h of multi‐channel EEG signals is 3.89 s. These excellent results and low‐computation design make the framework especially suited for clinical applications, advancing EEG‐based epilepsy diagnostics and improving patient outcomes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningElectroencephalographyEpilepsySeizuresHumansNeural Networks, ComputerSignal Processing, Computer-AssistedSensitivity and Specificity

Stichwörter der Autor:innen

deep learningelectroencephalography (EEG)epileptic seizuregraph convolutional neural network (GCNN)

Autor:innen und Institutionen

  • Shenzhen Institute of Shandong University, Shenzhen, P. R. China.
  • School of Integrated Circuits, Shandong University, Jinan, P.R. China.
  • Second Hospital of Shandong University, Jinan, China.
  • Weill Cornell Medicine, Cornell University, New York, New York, USA.

Förderung

  • Shenzhen Science and Technology Innovation Program
  • Key Program of the Natural Science Foundation of Shandong Province
  • National Natural Science Foundation of China

Zitieren

APA

Ji, D., Cui, H., Li, H., Liu, G., Liu, Z., Shang, W., Li, Y., & Zhou, W. (2025). An Efficient Deep Learning Framework for Automated Epileptic Seizure Detection: Toward Scalable and Clinically Applicable Solutions. Developmental Neurobiology, 85(3). https://doi.org/10.1002/dneu.22983

Vancouver

Ji D, Cui H, Li H, Liu G, Liu Z, Shang W, et al. An Efficient Deep Learning Framework for Automated Epileptic Seizure Detection: Toward Scalable and Clinically Applicable Solutions. Developmental Neurobiology. 2025;85(3). doi:10.1002/dneu.22983

BibTeX
@article{Ji2025,
  author = {Ji, Dezan and Cui, Haozhou and Li, Haotian and Liu, Guoyang and Liu, Zhen and Shang, Wei and Li, Yi and Zhou, Weidong},
  title = {An Efficient Deep Learning Framework for Automated Epileptic Seizure Detection: Toward Scalable and Clinically Applicable Solutions},
  journal = {Developmental Neurobiology},
  year = {2025},
  volume = {85},
  number = {3},
  doi = {10.1002/dneu.22983}
}
Kostenlos starten →