Automated Classification of Seizures against Nonseizures: A Deep Learning Approach

TL;DR

This paper presents a deep learning approach using IndRNN with dense and attention mechanisms to improve automatic seizure detection from EEG signals, achieving higher accuracy than existing methods.

Contribution

It introduces a novel deep learning model combining IndRNN, dense connections, and attention mechanisms for seizure classification, addressing variability in EEG signals.

Findings

Achieved average sensitivity of 88.80% and specificity of 88.60%.

Segment length significantly impacts classification performance.

Model outperforms current state-of-the-art methods.

Abstract

In current clinical practice, electroencephalograms (EEG) are reviewed and analyzed by well-trained neurologists to provide supports for therapeutic decisions. The way of manual reviewing is labor-intensive and error prone. Automatic and accurate seizure/nonseizure classification methods are needed. One major problem is that the EEG signals for seizure state and nonseizure state exhibit considerable variations. In order to capture essential seizure features, this paper integrates an emerging deep learning model, the independently recurrent neural network (IndRNN), with a dense structure and an attention mechanism to exploit temporal and spatial discriminating features and overcome seizure variabilities. The dense structure is to ensure maximum information flow between layers. The attention mechanism is to capture spatial features. Evaluations are performed in cross-validation experiments over the noisy CHB-MIT data set. The obtained average sensitivity, specificity and precision of 88.80%, 88.60% and 88.69% are better than using the current state-of-the-art methods. In addition, we explore how the segment length affects the classification performance. Thirteen different segment lengths are assessed, showing that the classification performance varies over the segment lengths, and the maximal fluctuating margin is more than 4%. Thus, the segment length is an important factor influencing the classification performance.