LV-CadeNet: A Long-View Feature Convolution-Attention Fusion Encoder-Decoder Network for EEG/MEG Spike Analysis

TL;DR

LV-CadeNet is a novel deep learning model that improves EEG/MEG spike detection by capturing long-term contextual features and dipole patterns, outperforming existing methods on public and clinical datasets.

Contribution

The paper introduces LV-CadeNet, a deep learning framework that combines long-view feature representation with hierarchical encoder-decoder architecture for enhanced spike analysis.

Findings

Outperforms six state-of-the-art methods on EEG spike classification.

Achieves 13.58% higher balanced accuracy on clinical MEG data.

Effectively captures extended contextual and dipole pattern features.

Abstract

The analysis of interictal epileptiform discharges (IEDs) in magnetoencephalography (MEG) or electroencephalogram (EEG) recordings represents a critical component in the diagnosis of epilepsy. However, manual analysis of these IEDs, which appear as epileptic spikes, from the large amount of MEG/EEG data is labor intensive and requires high expertise. Although automated methods have been developed to address this challenge, current approaches fail to fully emulate clinical experts' diagnostic intelligence in two key aspects: (1) their analysis on the input signals is limited to short temporal windows matching individual spike durations, missing the extended contextual patterns clinicians use to assess significance; and (2) they fail to adequately capture the dipole patterns with simultaneous positive-negative potential distributions across adjacent sensors that serve as clinicians' key diagnostic criterion for IED identification. To bridge this artificial-human intelligence gap, we propose a novel deep learning framework LV-CadeNet that integrates two key innovations: (1) a Long-View morphological feature representation that mimics expert clinicians' comprehensive assessment of both local spike characteristics and long-view contextual information, and (2) a hierarchical Encoder-Decoder NETwork that employs Convolution-Attention blocks for multi-scale spatiotemporal feature learning with progressive abstraction. Extensive evaluations confirm the superior performance of LV-CadeNet, which outperforms six state-of-the-art methods in EEG spike classification on TUEV, the largest public EEG spike dataset. Additionally, LV-CadeNet attains a significant improvement of 13.58% in balanced accuracy over the leading baseline for MEG spike detection on a clinical MEG dataset from Sanbo Brain Hospital, Capital Medical University.