Automated Adult Epilepsy Diagnostic Tool Based on Interictal Scalp Electroencephalogram Characteristics: A Six-Center Study

Abstract

The diagnosis of epilepsy often relies on a reading of routine scalp electroencephalograms (EEGs). Since seizures are highly unlikely to be detected in a routine scalp EEG, the primary diagnosis depends heavily on the visual evaluation of Interictal Epileptiform Discharges (IEDs). This process is tedious, expert-centered, and delays the treatment plan. Consequently, the development of an automated, fast, and reliable epileptic EEG diagnostic system is essential. In this study, we propose a system to classify EEG as epileptic or normal based on multiple modalities extracted from the interictal EEG. The ensemble system consists of three components: a Convolutional Neural Network (CNN)-based IED detector, a Template Matching (TM)-based IED detector, and a spectral feature-based classifier. We evaluate the system on datasets from six centers from the USA, Singapore, and India. The system yields a mean Leave-One-Institution-Out (LOIO) cross-validation (CV) area under curve (AUC) of 0.826 (balanced accuracy (BAC) of 76.1%) and Leave-One-Subject-Out (LOSO) CV AUC of 0.812 (BAC of 74.8%). The LOIO results are found to be similar to the interrater agreement (IRA) reported in the literature for epileptic EEG classification. Moreover, as the proposed system can process routine EEGs in a few seconds, it may aid the clinicians in diagnosing epilepsy efficiently.

Keywords: EEG classification; Epilepsy; convolutional neural networks; deep learning; interictal epileptiform discharges; multi-center study; spike detection.

Fig. 1.

Architecture of the CNN IED detector.

Fig. 2.

TM IED template library extraction procedure. We illustrate the different clusters generated by AP in conjunction with DTW as a 2D projection by applying t-Distributed Stochastic Neighbor Embedding (t-SNE).

Fig. 3.

Spectral feature-based EEG classifier.

Fig. 4.

Five-fold CV evaluation on MGH dataset. Folds 1, 2, and 3 are applied to train the IED detectors and the SVM. The fold four is applied to compute the IED rates for CNN and TM, optimize the thresholds, normalize features, and develop the threshold-based EEG classifier components. The same fold is applied to optimize the weights (w_CNN, w_TM, and w_S) of the ensemble EEG classifier. Finally, the testing is performed on fold five.

Fig. 5.

LOSO and LOIO CV methodology on the different datasets. Here, the IED detectors are trained on the three folds of the MGH dataset. The spectral feature SVM detector is trained on 50% of the training data, selected randomly. The remaining 50% of the training data is applied for EEG classifier training/calibration steps: designing the threshold based classifier for IED feature-based components (CNN and TM) and optimizing the weights (w_CNN, w_TM, and w_S) of the ensemble EEG classifier. For LOSO CV, in each iteration, one patient is evaluated by applying the system trained on the remaining EEGs. LOSO CV is performed on each dataset independently. In LOIO CV, in each iteration, the dataset from one center is evaluated from the combined dataset from other centers. In the above figure, the data from NUH is evaluated by applying the system trained on the dataset from the other centers.

Fig. 6.

Weight configurations for the three EEG classifier components (CNN, TM, and SVM) for the 20 configurations of MGH five-fold CV.

Fig. 7.

CNN IED rate per minute for epileptic EEGs with seizures, without seizures, and normal EEGs (NUH and TUH dataset). The IED rates are higher for EEGs with seizures in comparison with normal EEGs.

Fig. 8.

CNN, TM, and spectral features for 10 randomly selected epileptic and normal EEGs from each dataset.

Fig. 9.

LOSO and LOIO CV results for the different datasets and system combinations (AUC and BAC): (a) LOIO AUC, (b) LOSO AUC, (c) LOIO BAC, and (d) LOSO BAC.