Automated Classification of Seizures against Nonseizures: A Deep Learning Approach
This work addresses the need for accurate automated seizure detection in neurology, offering a practical improvement over manual review but is incremental as it builds on existing deep learning approaches.
The paper tackled the problem of automating seizure vs. nonseizure classification in EEG signals to reduce manual labor and errors in clinical practice, achieving average sensitivity, specificity, and precision of 88.80%, 88.60%, and 88.69% on the CHB-MIT dataset, outperforming state-of-the-art methods.
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.