Seizure Sources Can Be Imaged from Scalp EEG by Means of Biophysically Constrained Deep Neural Networks

Abstract: Seizure localization is important for managing drug‐resistant focal epilepsy. Here, the capability of a novel deep learning‐based source imaging framework (DeepSIF) for imaging seizure activities from electroencephalogram (EEG) recordings in drug‐resistant focal epilepsy patients is investigated. The neural mass model of ictal oscillations is adopted to generate synthetic training data with spatio‐temporal‐spectra features similar to ictal dynamics. The trained DeepSIF model is rigorously validated using computer simulations and in a cohort of 33 drug‐resistant focal epilepsy patients with high‐density (76‐channel) EEG seizure recordings, by comparing DeepSIF estimates with surgical resection outcome and seizure onset zone (SOZ). These findings show that the trained DeepSIF model outperforms other methods in estimating the spatial and temporal information of origins of ictal activities. It achieves a high spatial specificity of 96% and a low spatial dispersion of 3.80 ± 5.74 mm when compared to the resection region. The source imaging results also demonstrate good coverage of SOZ, with an average distance of 10.89 ± 10.14 mm (from the SOZ to the reconstruction). These promising results suggest that DeepSIF has significant potential for advancing noninvasive imaging of the origins of ictal activities in patients with focal epilepsy, aiding management of intractable epilepsy.

Standort
Deutsche Nationalbibliothek Frankfurt am Main
Umfang
Online-Ressource
Sprache
Englisch

Erschienen in
Seizure Sources Can Be Imaged from Scalp EEG by Means of Biophysically Constrained Deep Neural Networks ; day:29 ; month:10 ; year:2024 ; extent:12
Advanced science ; (29.10.2024) (gesamt 12)

Urheber
Sun, Rui
Sohrabpour, Abbas
Joseph, Boney
Worrell, Gregory
He, Bin

DOI
10.1002/advs.202405246
URN
urn:nbn:de:101:1-2410301328588.626768199164
Rechteinformation
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Letzte Aktualisierung
15.08.2025, 07:36 MESZ

Datenpartner

Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.

Beteiligte

  • Sun, Rui
  • Sohrabpour, Abbas
  • Joseph, Boney
  • Worrell, Gregory
  • He, Bin

Ähnliche Objekte (12)