SCFNet:A Transferable IIIC EEG Classification Network

TL;DR

This paper introduces SCFNet, a neural network architecture for EEG classification that effectively transfers across different channel configurations, improving accuracy and robustness in practical epilepsy monitoring applications.

Contribution

The paper proposes a novel single-channel feature extraction network (SCFNet) that enhances transferability and adaptability of EEG classification models across varying channel setups.

Findings

EEG-SCFNet improves accuracy by 4% over baseline.

It maintains performance with minimal fine-tuning.

It demonstrates robustness across different datasets and channel configurations.

Abstract

Epilepsy and epileptiform discharges are common harmful brain activities, and electroencephalogram (EEG) signals are widely used to monitor the onset status of patients. However, due to the lack of unified EEG signal acquisition standards, there are many obstacles in practical applications, especially the difficulty in transferring and using models trained on different numbers of channels. To address this issue, we proposes a neural network architecture with a single-channel feature extraction (Singal Channel Feature) model backend fusion (SCFNet). The feature extractor of the model is an RCNN network with single-channel input, which does not depend on other channels, thereby enabling easier migration to data with different numbers of channels. Experimental results show that on the IIIC-Seizure dataset, the accuracy of EEG-SCFNet has improved by 4% compared to the baseline model and also increased by 1.3% compared to the original RCNN neural network model. Even with only fine-tuning the classification head, its performance can still maintain a level comparable to the baseline. In addition, in terms of cross-dataset transfer, EEG-SCFNet can still maintain certain performance even if the channel leads are different.