EUVIMEDEUVIMED entdecken
Crossref

An Interpretability Framework for Convolutional Neural Network-Based Electroencephalography Analysis Discovers New Spatial and Spectral Epileptic Biomarkers

Vadim V Grubov iD, Oleg E Karpov iD, Sergei I Nazarikov iD, Semen A Kurkin iD, Nikita P Utyashev iD, Denis A Andrikov iD, Alexander E Hramov iD

International Journal of Neural Systems · 2026

DOI: 10.1142/s0129065726500334 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Neural Systems, 2026. Verfasst von Vadim V Grubov und 6 weiteren Autor:innen. Beteiligte Einrichtung: Research Institute of Applied Artificial Intelligence and Digital Solutions, Plekhanov Russian University of Economics, Stremyannyy Ln., 36, Moscow 2…. Hauptthemen laut MEDLINE: Convolutional Neural Networks, Electroencephalography, Epilepsy, Deep Learning. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 63 Literaturangaben. Gefördert von: Russian Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) models, particularly convolutional neural networks (CNNs), have shown promise in automated epileptic seizure detection from electroencephalogram (EEG). However, their “black-box” nature limits clinical adoption, as interpretability is critical for trust and validation in medical applications. A novel interpretability method for CNN-based seizure detection models, designed to uncover meaningful spatial and spectral EEG biomarkers, is proposed. The approach combines frequency- and spatial-domain interpretation to provide both global model behavior analysis and local, sample-specific explanations. It also accounts for the task-specific design, neurophysiological grounding and cross-framework validation — concepts often neglected by many state-of-the-art methods. Results are represented as heatmap matrices of feature importance (5 frequency bands * 5 brain regions) with important features determined through statistical testing. Interpretation is based on neurophysiological alignment of these features. The method is validated on three CNN architectures, demonstrating how each leverages distinct frequency bands and brain regions for seizure identification. Global interpretation reveals that the highest-performing model utilizes complementary biomarkers across multiple frequency bands, while local interpretation captures dynamic intra-seizure spectral shifts. The results align with known neurophysiological mechanisms, such as thalamocortical interactions (theta-band) and default mode network suppression (alpha/beta-bands), while also suggesting new biomarkers for seizure detection. The method bridges the gap between DL and clinical EEG analysis, offering a tool for model validation and discovery of electrophysiological signatures in epilepsy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Convolutional Neural NetworksElectroencephalographyEpilepsyDeep LearningNeural Networks, ComputerHumansBiomarkersSignal Processing, Computer-Assisted

Stichwörter der Autor:innen

Convolutional neural networkEEGcontinuous wavelet transformepileptic seizure detectionfrequency- and spatial-domain interpretationglobal and local interpretationmachine learning interpretability

Substanzen

Biomarkers

Autor:innen und Institutionen

  • Research Institute of Applied Artificial Intelligence and Digital Solutions, Plekhanov Russian University of Economics, Stremyannyy Ln., 36, Moscow 236041, Russia.
  • Pirogov National Medical and Surgical Center, 70, Nizhnyaya Pervomayskaya Str., Moscow 127051, Russia.
  • Bauman Moscow State Technical University, 5, 2nd Baumanskaya Str., Moscow 105005, Russia.

ORCID-Profile: Vadim V Grubov, Oleg E Karpov, Sergei I Nazarikov, Semen A Kurkin, Nikita P Utyashev, Denis A Andrikov, Alexander E Hramov

Förderung

  • Russian Science Foundation

Zitieren

APA

Grubov, V. V., Karpov, O. E., Nazarikov, S. I., Kurkin, S. A., Utyashev, N. P., Andrikov, D. A., & Hramov, A. E. (2026). An Interpretability Framework for Convolutional Neural Network-Based Electroencephalography Analysis Discovers New Spatial and Spectral Epileptic Biomarkers. International Journal of Neural Systems. https://doi.org/10.1142/s0129065726500334

Vancouver

Grubov VV, Karpov OE, Nazarikov SI, Kurkin SA, Utyashev NP, Andrikov DA, et al. An Interpretability Framework for Convolutional Neural Network-Based Electroencephalography Analysis Discovers New Spatial and Spectral Epileptic Biomarkers. International Journal of Neural Systems. 2026. doi:10.1142/s0129065726500334

BibTeX
@article{Grubov2026,
  author = {Grubov, Vadim V and Karpov, Oleg E and Nazarikov, Sergei I and Kurkin, Semen A and Utyashev, Nikita P and Andrikov, Denis A and Hramov, Alexander E},
  title = {An Interpretability Framework for Convolutional Neural Network-Based Electroencephalography Analysis Discovers New Spatial and Spectral Epileptic Biomarkers},
  journal = {International Journal of Neural Systems},
  year = {2026},
  doi = {10.1142/s0129065726500334}
}
Kostenlos starten →