EUVIMEDEUVIMED entdecken
Open Access

Deep learning on brief interictal intracranial recordings can accurately characterize seizure onset zones

Sameer Sundrani iD, Graham W Johnson, Derek J Doss iD, Ghassan S Makhoul, Bruno Hidalgo Monroy Lerma iD, Anas Reda, Addison C Cavender, Emily Liao, Baxter P Rogers, Shawniqua Williams Roberson, Sarah K Bick, Victoria L Morgan iD und 1 weitere

Epilepsia · 2025

DOI: 10.1111/epi.18478 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Epilepsia, 2025. Verfasst von Sameer Sundrani und 12 weiteren Autor:innen. Beteiligte Einrichtung: Vanderbilt University School of Medicine, Nashville, Tennessee, USA. Hauptthemen laut MEDLINE: Deep Learning, Seizures, Electrocorticography, Brain. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, NINDS NIH HHS, NIBIB NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Epilepsy is a debilitating disorder affecting more than 50 million people worldwide, and one third of patients continue to have seizures despite maximal medical management. If patients' seizures localize to a discrete brain region, termed a seizure onset zone, resection may be curative. Localization is often confirmed with stereotactic electroencephalography; however, this may require patients to stay in the hospital for weeks to capture spontaneous seizures. Automated localization of seizure onset zones could therefore improve presurgical evaluation and decrease morbidity.

Methods

Using more than 1 000 000 interictal stereotactic electroencephalography segments collected from 78 patients, we performed five‐fold cross‐validation and testing on a multichannel, multiscale, one‐dimensional convolutional neural network to classify seizure onset zones.

Results

Across held‐out test sets, our models achieved a seizure onset zone classification sensitivity of .702 (95% confidence interval [CI] = .549–.805), specificity of .741 (95% CI = .652–.835), and accuracy of .738 (95% CI = .687–.795), which was significantly better than models trained on random labels. The models performed well across the entire brain, with top five region performance demonstrating accuracies between 70.0% and 88.4%. When split by outcomes, the models performed significantly better on patients with favorable Engel outcomes after resection or who were responsive neurostimulation responders. Finally, SHAP (Shapley Additive Explanation) value analysis on median‐normalized input data assigned consistently high feature importance to interictal spikes and large deflections, whereas similar analyses on histogram‐equalized data revealed differences in feature importance assignments to low‐amplitude segments. Significance This work serves as evidence that deep learning on brief interictal intracranial data can classify seizure onset zones across the brain. Furthermore, our findings corroborate current understandings of interictal epileptiform discharges and may help uncover novel interictal morphologies. Clinical application of our models may reduce dependence on recorded seizures for localization and shorten presurgical evaluation time for drug‐resistant epilepsy patients, reducing patient morbidity and hospital costs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSeizuresElectrocorticographyBrainEpilepsyHumansMaleFemaleAdultAdolescentElectroencephalographyYoung AdultMiddle AgedDrug Resistant EpilepsyStereotaxic TechniquesNeural Networks, Computer

Stichwörter der Autor:innen

SHAP analysisconvolutional neural networkpresurgical evaluationseizure onset zone localization

Autor:innen und Institutionen

  • Vanderbilt University School of Medicine, Nashville, Tennessee, USA.
  • Department of Neurological Surgery, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
  • Department of Neurological Surgery, Mayo Clinic, Rochester, Minnesota, USA.
  • Department of Radiology, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
  • Department of Neurology, Vanderbilt University Medical Center, Nashville, Tennessee, USA.

ORCID-Profile: Sameer Sundrani, Derek J Doss, Bruno Hidalgo Monroy Lerma, Victoria L Morgan

Förderung

  • NIGMS NIH HHS
  • NINDS NIH HHS
  • NIBIB NIH HHS
  • National Institute of General Medical Sciences
  • National Institute of Neurological Disorders and Stroke
  • National Institute of Biomedical Imaging and Bioengineering

Zitieren

APA

Sundrani, S., Johnson, G. W., Doss, D. J., Makhoul, G. S., Hidalgo Monroy Lerma, B., Reda, A., Cavender, A. C., Liao, E., Rogers, B. P., Williams Roberson, S., Bick, S. K., Morgan, V. L., & Englot, D. J. (2025). Deep learning on brief interictal intracranial recordings can accurately characterize seizure onset zones. Epilepsia. https://doi.org/10.1111/epi.18478

Vancouver

Sundrani S, Johnson GW, Doss DJ, Makhoul GS, Hidalgo Monroy Lerma B, Reda A, et al. Deep learning on brief interictal intracranial recordings can accurately characterize seizure onset zones. Epilepsia. 2025. doi:10.1111/epi.18478

BibTeX
@article{Sundrani2025,
  author = {Sundrani, Sameer and Johnson, Graham W and Doss, Derek J and Makhoul, Ghassan S and Hidalgo Monroy Lerma, Bruno and Reda, Anas and Cavender, Addison C and Liao, Emily and Rogers, Baxter P and Williams Roberson, Shawniqua and Bick, Sarah K and Morgan, Victoria L and Englot, Dario J},
  title = {Deep learning on brief interictal intracranial recordings can accurately characterize seizure onset zones},
  journal = {Epilepsia},
  year = {2025},
  doi = {10.1111/epi.18478}
}
Kostenlos starten →