Automatic seizure detection based on imaged-EEG signals through fully convolutional networks

Abstract

Seizure detection is a routine process in epilepsy units requiring manual intervention of well-trained specialists. This process could be extensive, inefficient and time-consuming, especially for long term recordings. We proposed an automatic method to detect epileptic seizures using an imaged-EEG representation of brain signals. To accomplish this, we analyzed EEG signals from two different datasets: the CHB-MIT Scalp EEG database and the EPILEPSIAE project that includes scalp and intracranial recordings. We used fully convolutional neural networks to automatically detect seizures. For our best model, we reached average accuracy and specificity values of 99.3% and 99.6%, respectively, for the CHB-MIT dataset, and corresponding values of 98.0% and 98.3% for the EPILEPSIAE patients. For these patients, the inclusion of intracranial electrodes together with scalp ones increased the average accuracy and specificity values to 99.6% and 58.3%, respectively. Regarding the other metrics, our best model reached average precision of 62.7%, recall of 58.3%, F-measure of 59.0% and AP of 54.5% on the CHB-MIT recordings, and comparatively lowers performances for the EPILEPSIAE dataset. For both databases, the number of false alarms per hour reached values less than 0.5/h for 92% of the CHB-MIT patients and less than 1.0/h for 80% of the EPILEPSIAE patients. Compared to recent studies, our lightweight approach does not need any estimation of pre-selected features and demonstrates high performances with promising possibilities for the introduction of such automatic methods in the clinical practice.

Prediction of epileptic seizures based on multivariate multiscale modified-distribution entropy

“…A summary of the performance comparison between the existing prediction methods that have used the same dataset and the proposed method is shown in Table 1. The proposed method obtains a higher accuracy score among these methods, excluding the method using a convolutional neural network (CNN) (Gómez et al, 2020), while the training time is shorter than that of the other methods such as M-mDistEn with an ANN, PE with an ANN, a deep convolutional neural network (DCNN) with MLP and MLP (Daoud & Bayoumi, 2019). The sensitivity of the proposed method obtains a better score than other methods, but it is slightly lower than DCNN with MLP and CNN with SVM.…”

Engineering Nonlinear Epileptic Biomarkers Using Deep Learning and Benford’s Law

“…There are many other seizure identi cation experiments using neural networks and engineered features 10,23 , but direct comparison to many of the models is di cult because of inconsistencies between the performance metrics chosen, how the models are trained, how the scores are reported (maximum achieved vs average score), and the composition of the dataset. Data composition matters because most projects report the accuracy, which has recently been shown to be inconsistent, due to its dependency on the data composition and the model architecture.…”

“…Such properties make them useful for real time perceptual applications, as demonstrated in numerous studies. 5,7,8,10,12,17,20,21,23 However, DNNs are essentially a "black box" approach, making them di cult to approve for clinical use because clinicians cannot interpret how the network generates its predictions. Our goal was to address shortcomings in interpretability by creating an encoder for learning seizure-speci c features and selecting the most relevant for a particular task.…”

Early Detection of Pediatric Seizures in the High Gamma Band

“…As the presence or absence of other spectral components distinguishes them, expert visual marking combined with EEGLAB's event detector denoted the start of each ictal event. Although the current the gold standard for seizure onset is expert visual marking, the LOO (Leave-One-Patient-Out) or First Seizures models of Gomez et al [33] may supersede this standard.…”