A Lightweight Convolutional Neural Network-Reformer Model for Efficient Epileptic Seizure Detection

Sep 30, 2024International journal of neural systems

A Fast and Light Neural Network Model for Detecting Epileptic Seizures

AI simplified

Circadian Biology on OpenScience ↗PubMed ↗DOI ↗

Abstract

The CNN-Reformer model achieves an average sensitivity of 97.57% and accuracy of 98.09% for seizure detection using long-term EEG signals.

The CNN-Reformer model includes a Data Reshaping module for compressing and reshaping EEG data while preserving local features.
An Efficient Attention and Concentration module is used to extract global features for better categorization of seizures.
The method reduces the false detection rate to 0.27 per hour and has a latency of 17.81 seconds for event-based detection.
On the CHB-MIT dataset, the model also shows high specificity of 98.11% at the segment-based level.
For the SH-SDU dataset, segment-based sensitivity and specificity are 94.51% and 92.83%, respectively.
The average processing time for one hour of multi-channel EEG is 1.92 seconds.

AI simplified

A real-time and reliable automatic detection system for epileptic seizures holds significant value in assisting physicians with rapid diagnosis and treatment of epilepsy. Aiming to address this issue, a novel lightweight model called Convolutional Neural Network-Reformer (CNN-Reformer) is proposed for seizure detection on long-term EEG. The CNN-Reformer consists of two main parts: the Data Reshaping (DR) module and the Efficient Attention and Concentration (EAC) module. This framework reduces network parameters while retaining effective feature extraction of multi-channel EEGs, thereby improving model computational efficiency and real-time performance. Initially, the raw EEG signals undergo Discrete Wavelet Transform (DWT) for signal filtering, and then fed into the DR module for data compression and reshaping while preserving local features. Subsequently, these local features are sent to the EAC module to extract global features and perform categorization. Post-processing involving sliding window averaging, thresholding, and collar techniques is further deployed to reduce the false detection rate (FDR) and improve detection performance. On the CHB-MIT scalp EEG dataset, our method achieves an average sensitivity of 97.57%, accuracy of 98.09%, and specificity of 98.11% at segment-based level, and a sensitivity of 96.81%, along with FDR of 0.27/h, and latency of 17.81 s at the event-based level. On the SH-SDU dataset we collected, our method yielded segment-based sensitivity of 94.51%, specificity of 92.83%, and accuracy of 92.81%, along with event-based sensitivity of 94.11%. The average testing time for 1[Formula: see text]h of multi-channel EEG signals is 1.92[Formula: see text]s. The excellent results and fast computational speed of the CNN-Reformer model demonstrate its potential for efficient seizure detection.

Full Text

Full text is available at the source.

View full text ↗

A Lightweight Convolutional Neural Network-Reformer Model for Efficient Epileptic Seizure Detection

Abstract

Full Text

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief

Abstract

Full Text

Related papers

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief