Spreading Depolarization Detection in Electrocorticogram Spectrogram Imaging by Deep Learning: Is It Just About Delta Band?

TL;DR

This paper investigates multi-frequency spectrogram analysis combined with deep learning to improve detection of spreading depolarizations in electrocorticogram signals, addressing limitations of delta-only approaches.

Contribution

It introduces a multi-band spectrogram approach that captures SD features across various frequencies, enhancing detection accuracy over delta-only methods.

Findings

Multi-frequency spectrograms reveal SD features beyond delta band.

Integrating alpha and delta bands improves deep learning detection accuracy.

Multi-band analysis outperforms delta-only methods in SD detection.

Abstract

Prevention of secondary brain injury is a core aim of neurocritical care, with Spreading Depolarizations (SDs) recognized as a significant independent cause. SDs are typically monitored through invasive, high-frequency electrocorticography (ECoG); however, detection remains challenging due to signal artifacts that obscure critical SD-related electrophysiological changes, such as power attenuation and DC drifting. Recent studies suggest spectrogram analysis could improve SD detection; however, brain injury patients often show power reduction across all bands except delta, causing class imbalance. Previous methods focusing solely on delta mitigates imbalance but overlooks features in other frequencies, limiting detection performance. This study explores using multi-frequency spectrogram analysis, revealing that essential SD-related features span multiple frequency bands beyond the most active delta band. This study demonstrated that further integration of both alpha and delta bands could result in enhanced SD detection accuracy by a deep learning model.