Key result
A convolutional neural network combined with patient-specific autoencoders reduced the median false alarm rate for seizure detection to 0.034 h−1 compared to 0.17 h−1 with the original CNN.
Why the study?
Automatic seizure detection via convolutional neural networks processing EEG plot images demonstrated high performance, but still had room for reducing the false-positive alarm rate.
Does an autoencoder-assisted CNN reduce the false alarm rate in automatic seizure detection compared to a standard CNN?
Does an autoencoder-assisted CNN reduce the false alarm rate in automatic seizure detection compared to a standard CNN?
Answers are grounded in this paper and cite their sources.
Combining a CNN with patient-specific autoencoders significantly reduces the false-positive alarm rate in automatic seizure detection on scalp EEG.
In long-term video-monitoring, automatic seizure detection holds great promise as a means to reduce the workload of the epileptologist. A convolutional neural network (CNN) designed to process images of EEG plots demonstrated high performance for seizure detection, but still has room for reducing the false-positive alarm rate. We combined a CNN that processed images of EEG plots with patient-specific autoencoders (AE) of EEG signals to reduce the false alarms during seizure detection. The AE automatically logged abnormalities, i.e., both seizures and artifacts. Based on seizure logs compiled by expert epileptologists and errors made by AE, we constructed a CNN with 3 output classes: seizure, non-seizure-but-abnormal, and non-seizure. The accumulative measure of number of consecutive seizure labels was used to issue a seizure alarm. The second-by-second classification performance of AE-CNN was comparable to that of the original CNN. False-positive seizure labels in AE-CNN were more likely interleaved with “non-seizure-but-abnormal” labels than with true-positive seizure labels. Consequently, “non-seizure-but-abnormal” labels interrupted runs of false-positive seizure labels before triggering an alarm. The median false alarm rate with the AE-CNN was reduced to 0.034 h−1, which was one-fifth of that of the original CNN (0.17 h−1). A label of “non-seizure-but-abnormal” offers practical benefits for seizure detection. The modification of a CNN with an AE is worth considering because AEs can automatically assign “non-seizure-but-abnormal” labels in an unsupervised manner with no additional demands on the time of the epileptologist.
No takes yet. Share an insight, caveat, or question.
Takahashi et al. (2020) studied Seizures. Convolutional neural network with patient-specific autoencoders (AE-CNN) vs. Original CNN was evaluated on Median false alarm rate. A convolutional neural network combined with patient-specific autoencoders reduced the median false alarm rate for seizure detection to 0.034 h−1 compared to 0.17 h−1 with the original CNN.
Synapse has enriched 10 related papers. Consider them for comparative context: