EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cortico-cortical evoked potentials: Automated localization and classification of early and late responses

Sahaj A Patel, Helen Brinyark, Caila Coyne, Noshin Tasnia, Rebekah Chatfield, Erin C Conrad, Benjamin Cox, Arie Nakhmani, Rachel J Smith

Journal of Neuroscience Methods · 2025-12 · 424 · 110571

DOI: 10.1016/j.jneumeth.2025.110571 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Neuroscience Methods, 2025-12. Verfasst von Sahaj A Patel und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, University of Alabama at Birmingham, Birmingham, AL, USA. Electronic address: sahaj432@uab.edu. Hauptthemen laut MEDLINE: Cerebral Cortex, Deep Learning, Evoked Potentials, Electrocorticography. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institutes of Health, American Epilepsy Society.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Cortico-cortical evoked potentials (CCEPs), elicited via single-pulse electrical stimulation, are used to map brain networks. These responses comprise early (N1) and late (N2) components, which reflect direct and indirect cortical connectivity. Reliable identification of these components remains difficult due to substantial variability in amplitude, phase, and timing. Traditional statistical methods often struggle to localize N1 and N2 peaks under such conditions. NEW METHOD: A deep learning framework based on You Only Look Once (YOLO v10) was developed. Each CCEP epoch was converted into a two-dimensional image using Matplotlib and subsequently analyzed by the YOLO model to localize and classify N1 and N2 components. Detected image coordinates were mapped back to corresponding time-series indices for clinical interpretation. RESULTS: The framework was trained and validated on intracranial EEG data from 9 patients with drug-resistant epilepsy (DRE) at the University of Alabama at Birmingham (UAB), achieving a mean average precision (mAP) of 0.928 at an Intersection over Union (IoU) threshold of 0.5 on the test dataset. Generalizability was assessed on more than 4000 unannotated epochs obtained from 5 additional UAB patients and 10 patients at the Hospital of the University of Pennsylvania. COMPARISON WITH EXISTING METHODS: To our knowledge, no existing deep learning methods localize and classify both N1 and N2 components, limiting comparison. Current approaches rely on manual identification within fixed windows, introducing inter-rater variability and often missing inter-individual differences. CONCLUSION: The proposed framework accurately detects and classifies CCEP components, offering a robust, automated alternative to manual analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cerebral CortexDeep LearningEvoked PotentialsElectrocorticographyDrug Resistant EpilepsyBrain MappingHumansFemaleMaleAdultYoung AdultElectroencephalographySignal Processing, Computer-Assisted

Stichwörter der Autor:innen

Cortico-cortical evoked potentialsDeep learningIntracranial EEGN1 and N2 componentsYOLO object detection

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, University of Alabama at Birmingham, Birmingham, AL, USA. Electronic address: sahaj432@uab.edu.
  • Department of Biomedical Engineering, University of Alabama at Birmingham, Birmingham, AL, USA.
  • Department of Neuroengineering, University of Alabama at Birmingham, Birmingham, AL, USA.
  • Department of Electrical and Computer Engineering, University of Alabama at Birmingham, Birmingham, AL, USA.
  • Department of Neurology, University of Alabama at Birmingham, Birmingham, AL, USA.
  • Department of Neurology, University of Pennsylvania, Perelman School of Medicine, Philadelphia, PA, USA.

Förderung

  • National Institutes of Health
  • American Epilepsy Society

Zitieren

APA

Patel, S. A., Brinyark, H., Coyne, C., Tasnia, N., Chatfield, R., Conrad, E. C., Cox, B., Nakhmani, A., & Smith, R. J. (2025). Cortico-cortical evoked potentials: Automated localization and classification of early and late responses. Journal of Neuroscience Methods, 424, 110571. https://doi.org/10.1016/j.jneumeth.2025.110571

Vancouver

Patel SA, Brinyark H, Coyne C, Tasnia N, Chatfield R, Conrad EC, et al. Cortico-cortical evoked potentials: Automated localization and classification of early and late responses. Journal of Neuroscience Methods. 2025;424:110571. doi:10.1016/j.jneumeth.2025.110571

BibTeX
@article{Patel2025,
  author = {Patel, Sahaj A and Brinyark, Helen and Coyne, Caila and Tasnia, Noshin and Chatfield, Rebekah and Conrad, Erin C and Cox, Benjamin and Nakhmani, Arie and Smith, Rachel J},
  title = {Cortico-cortical evoked potentials: Automated localization and classification of early and late responses},
  journal = {Journal of Neuroscience Methods},
  year = {2025},
  volume = {424},
  pages = {110571},
  doi = {10.1016/j.jneumeth.2025.110571}
}
Kostenlos starten →