Learning Robust Features using Deep Learning for Automatic Seizure Detection
This work addresses the need for reliable seizure detection in medical diagnostics, representing an incremental improvement in domain-specific deep learning applications.
The authors tackled the problem of automatic seizure detection from EEG data, which is challenging due to high variability in seizure manifestations, and achieved significantly improved sensitivity and false positive rates compared to previous cross-patient classifiers.
We present and evaluate the capacity of a deep neural network to learn robust features from EEG to automatically detect seizures. This is a challenging problem because seizure manifestations on EEG are extremely variable both inter- and intra-patient. By simultaneously capturing spectral, temporal and spatial information our recurrent convolutional neural network learns a general spatially invariant representation of a seizure. The proposed approach exceeds significantly previous results obtained on cross-patient classifiers both in terms of sensitivity and false positive rate. Furthermore, our model proves to be robust to missing channel and variable electrode montage.