EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

Leveraging interictal multimodal features and graph neural networks for automated planning of epilepsy surgery

Petr Nejedly, Valentina Hrtonova, Martin Pail, Jan Cimbalnik, Pavel Daniel, Vojtech Travnicek, Irena Dolezalova, Filip Mivalt iD, Vaclav Kremen iD, Pavel Jurak, Gregory A Worrell, Birgit Frauscher and 2 more

Brain Communications · 2025-04-30 · 7 (3)

DOI: 10.1093/braincomms/fcaf140 ↗

At a glance

Journal article in Brain Communications, published online on 2025-04-16. Written by Petr Nejedly and 13 co-authors. Institution: Brno Epilepsy Center, Department of Neurology, Member of ERN-EpiCARE, St. Anne's University Hospital, Faculty of Medicine, Masaryk University, Brno 6…. Cited 17 times so far (Crossref); 36 references. The full text is freely available (open access, CC BY 4.0). Funded by: Ministry of Education, Youth and Sports of the Czech Republic, European Union – Next Generation EU, Ministry of Health of the Czech Republic.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Precise localization of the epileptogenic zone is pivotal for planning minimally invasive surgeries in drug-resistant epilepsy. Here, we present a graph neural network (GNN) framework that integrates interictal intracranial EEG features, electrode topology, and MRI features to automate epilepsy surgery planning. We retrospectively evaluated the model using leave-one-patient-out cross-validation on a dataset of 80 drug-resistant epilepsy patients treated at St. Anne's University Hospital (Brno, Czech Republic), comprising 31 patients with good postsurgical outcomes (Engel I) and 49 with poor outcomes (Engel II–IV). The GNN predictions demonstrated a significantly better (P < 0.05, Mann–Whitney-U test) area under the precision-recall curve in patients with good outcomes (area under the precision-recall curve: 0.69) compared with those with poor outcomes (area under the precision-recall curve: 0.33), indicating that the model captures clinically relevant targets in successful cases. In patients with poor outcomes, the graph neural network proposed alternative intervention sites that diverged from the original clinical plans, highlighting its potential to identify alternative therapeutic targets. We show that topology-aware GNNs significantly outperformed (P < 0.05, Wilcoxon signed-rank test) traditional neural networks while using the same intracranial EEG features, emphasizing the importance of incorporating implantation topology into predictive models. These findings uncover the potential of GNNs to automatically suggest targets for epilepsy surgery, which can assist the clinical team during the planning process.

Subjects

Author keywords

MRIepilepsygraph neural networksiEEGsurgery

Authors and institutions

  • Brno Epilepsy Center, Department of Neurology, Member of ERN-EpiCARE, St. Anne's University Hospital, Faculty of Medicine, Masaryk University, Brno 625 00, Czech Republic.
  • Institute of Scientific Instruments, The Czech Academy of Sciences, Brno 612 00, Czech Republic.
  • Department of Neurology, Duke University Medical Center, Durham, NC 27705, USA.
  • International Clinical Research Center, St. Anne's University Hospital, Brno 602 00, Czech Republic.
  • Department of Neurology, Mayo Clinic, Rochester, MN 55905, USA.
  • Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, MN 55905, USA.

ORCID profiles: Filip Mivalt, Vaclav Kremen

Funding

  • Ministry of Education, Youth and Sports of the Czech Republic
  • European Union – Next Generation EU
  • Ministry of Health of the Czech Republic
  • Czech Academy of Sciences
  • Ministry of Education, Youth and Sport of the Czech Republic

Cite

APA

Nejedly, P., Hrtonova, V., Pail, M., Cimbalnik, J., Daniel, P., Travnicek, V., Dolezalova, I., Mivalt, F., Kremen, V., Jurak, P., Worrell, G. A., Frauscher, B., Klimes, P., & Brazdil, M. (2025). Leveraging interictal multimodal features and graph neural networks for automated planning of epilepsy surgery. Brain Communications, 7(3). https://doi.org/10.1093/braincomms/fcaf140

Vancouver

Nejedly P, Hrtonova V, Pail M, Cimbalnik J, Daniel P, Travnicek V, et al. Leveraging interictal multimodal features and graph neural networks for automated planning of epilepsy surgery. Brain Communications. 2025;7(3). doi:10.1093/braincomms/fcaf140

BibTeX
@article{Nejedly2025,
  author = {Nejedly, Petr and Hrtonova, Valentina and Pail, Martin and Cimbalnik, Jan and Daniel, Pavel and Travnicek, Vojtech and Dolezalova, Irena and Mivalt, Filip and Kremen, Vaclav and Jurak, Pavel and Worrell, Gregory A and Frauscher, Birgit and Klimes, Petr and Brazdil, Milan},
  title = {Leveraging interictal multimodal features and graph neural networks for automated planning of epilepsy surgery},
  journal = {Brain Communications},
  year = {2025},
  volume = {7},
  number = {3},
  doi = {10.1093/braincomms/fcaf140}
}
Start for free →