Automatic detection of generalized paroxysmal fast activity in interictal EEG using time-frequency analysis

vEpiNet: A multimodal interictal epileptiform discharge detection method based on video and electroencephalogram data

To enhance deep learning-based automated interictal epileptiform discharge (IED) detection, this study proposes a multimodal method, vEpiNet, that leverages video and electroencephalogram (EEG) data. Datasets comprise 24 931 IED (from 484 patients) and 166 094 non-IED 4-second video-EEG segments. The video data is processed by the proposed patient detection method, with frame difference and Simple Keypoints (SKPS) capturing patients' movements. EEG data is processed with EfficientNetV2. The video and EEG features are fused via a multilayer perceptron. We developed a comparative model, termed nEpiNet, to test the effectiveness of the video feature in vEpiNet. The 10-fold cross-validation was used for testing. The 10-fold cross-validation showed high areas under the receiver operating characteristic curve (AUROC) in both models, with a slightly superior AUROC (0.9902) in vEpiNet compared to nEpiNet (0.9878). Moreover, to test the model performance in real-world scenarios, we set a prospective test dataset, containing 215 h of raw video-EEG data from 50 patients. The result shows that the vEpiNet achieves an area under the precision-recall curve (AUPRC) of 0.8623, surpassing nEpiNet's 0.8316. Incorporating video data raises precision from 70% (95% CI, 69.8%-70.2%) to 76.6% (95% CI, 74.9%-78.2%) at 80% sensitivity and reduces false positives by nearly a third, with vEpiNet processing one-hour video-EEG data in 5.7 min on average. Our findings indicate that video data can significantly improve the performance and precision of IED detection, especially in prospective real clinic testing. It suggests that vEpiNet is a clinically viable and effective tool for IED analysis in real-world applications.

Interrater reliability of interictal EEG waveforms in Lennox-Gastaut Syndrome

OBJECTIVE

Identification of EEG waveforms is critical for diagnosing Lennox-Gastaut Syndrome (LGS) but is complicated by the progressive nature of the disease. Here, we assess the interrater reliability (IRR) among pediatric epileptologists for classifying EEG waveforms associated with LGS.

METHODS

A novel automated algorithm was used to objectively identify epochs of EEG with transient high power, which were termed events of interest (EOIs). The algorithm was applied to EEG from 20 LGS subjects and 20 healthy controls during NREM sleep, and 1350 EOIs were identified. Three raters independently reviewed the EOIs within isolated 15-second EEG segments in a randomized, blinded fashion. For each EOI, the raters assigned a waveform label (spike and slow wave, generalized paroxysmal fast activity, seizure, spindle, vertex, muscle, artifact, nothing, or other) and indicated the perceived subject type (LGS or control).

RESULTS

Labeling of subject type had 85% accuracy across all EOIs and an IRR of κ =0.790, suggesting that brief segments of EEG containing high-power waveforms can be reliably classified as pathological or normal. Waveform labels were less consistent, with κ =0.558, and the results were highly variable for different categories of waveforms. Label mismatches typically occurred when one reviewer selected "nothing," suggesting that reviewers had different thresholds for applying named labels.

SIGNIFICANCE

Classification of EEG waveforms associated with LGS has weak IRR, due in part to varying thresholds applied during visual review. Computational methods to objectively define EEG biomarkers of LGS may improve IRR and aid clinical decision-making.

Deep learning for automated detection of generalized paroxysmal fast activity in Lennox-Gastaut syndrome

OBJECTIVES

Generalized paroxysmal fast activity (GPFA) is a key electroencephalographic (EEG) feature of Lennox-Gastaut Syndrome (LGS). Automated analysis of scalp EEG has been successful in detecting more typical abnormalities. Automatic detection of GPFA has been more challenging, due to its variability from patient to patient and similarity to normal brain rhythms. In this work, a deep learning model is investigated for detection of GPFA events and estimating their overall burden from scalp EEG.

METHODS

Data from 10 patients recorded during four ambulatory EEG monitoring sessions are used to generate and validate the model. All patients had confirmed LGS and were recruited into a trial for thalamic deep-brain stimulation therapy (ESTEL Trial).

RESULTS

The correlation coefficient between manual and model estimates of event counts was r2 = 0.87, and for total burden was r2 = 0.91. The average GPFA detection sensitivity was 0.876, with an average false-positive rate of 3.35 per minute. There was no significant difference found between patients with early or delayed deep brain stimulation (DBS) treatment, or those with active vagal nerve stimulation (VNS).

CONCLUSIONS

Overall, the deep learning model was able to accurately detect GPFA and provide accurate estimates of the overall GPFA burden and electrographic event counts, albeit with a high false-positive rate.

SIGNIFICANCE

Automated GPFA detection may enable automated calculation of EEG biomarkers of burden of disease in LGS.

Data Augmentation Effects on Highly Imbalanced EEG Datasets for Automatic Detection of Photoparoxysmal Responses

Photosensitivity is a neurological disorder in which a person's brain produces epileptic discharges, known as Photoparoxysmal Responses (PPRs), when it receives certain visual stimuli. The current standardized diagnosis process used in hospitals consists of submitting the subject to the Intermittent Photic Stimulation process and attempting to trigger these phenomena. The brain activity is measured by an Electroencephalogram (EEG), and the clinical specialists manually look for the PPRs that were provoked during the session. Due to the nature of this disorder, long EEG recordings may contain very few PPR segments, meaning that a highly imbalanced dataset is available. To tackle this problem, this research focused on applying Data Augmentation (DA) to create synthetic PPR segments from the real ones, improving the balance of the dataset and, thus, the global performance of the Machine Learning techniques applied for automatic PPR detection. K-Nearest Neighbors and a One-Hidden-Dense-Layer Neural Network were employed to evaluate the performance of this DA stage. The results showed that DA is able to improve the models, making them more robust and more able to generalize. A comparison with the results obtained from a previous experiment also showed a performance improvement of around 20% for the Accuracy and Specificity measurements without Sensitivity suffering any losses. This project is currently being carried out with subjects at Burgos University Hospital, Spain.

Data-driven approach for the delineation of the irritative zone in epilepsy in MEG

The reliable identification of the irritative zone (IZ) is a prerequisite for the correct clinical evaluation of medically refractory patients affected by epilepsy. Given the complexity of MEG data, visual analysis of epileptiform neurophysiological activity is highly time consuming and might leave clinically relevant information undetected. We recorded and analyzed the interictal activity from seven patients affected by epilepsy (Vectorview Neuromag), who successfully underwent epilepsy surgery (Engel > = II). We visually marked and localized characteristic epileptiform activity (VIS). We implemented a two-stage pipeline for the detection of interictal spikes and the delineation of the IZ. First, we detected candidate events from peaky ICA components, and then clustered events around spatio-temporal patterns identified by convolutional sparse coding. We used the average of clustered events to create IZ maps computed at the amplitude peak (PEAK), and at the 50% of the peak ascending slope (SLOPE). We validated our approach by computing the distance of the estimated IZ (VIS, SLOPE and PEAK) from the border of the surgically resected area (RA). We identified 25 spatiotemporal patterns mimicking the underlying interictal activity (3.6 clusters/patient). Each cluster was populated on average by 22.1 [15.0–31.0] spikes. The predicted IZ maps had an average distance from the resection margin of 8.4 ± 9.3 mm for visual analysis, 12.0 ± 16.5 mm for SLOPE and 22.7 ±. 16.4 mm for PEAK. The consideration of the source spread at the ascending slope provided an IZ closer to RA and resembled the analysis of an expert observer. We validated here the performance of a data-driven approach for the automated detection of interictal spikes and delineation of the IZ. This computational framework provides the basis for reproducible and bias-free analysis of MEG recordings in epilepsy.

EEG Markers of Treatment Resistance in Idiopathic Generalized Epilepsy: From Standard EEG Findings to Advanced Signal Analysis

Idiopathic generalized epilepsy (IGE) represents a common form of epilepsy in both adult and pediatric epilepsy units. Although IGE has been long considered a relatively benign epilepsy syndrome, a remarkable proportion of patients could be refractory to treatment. While some clinical prognostic factors have been largely validated among IGE patients, the impact of routine electroencephalography (EEG) findings in predicting drug resistance is still controversial and a growing number of authors highlighted the potential importance of capturing the sleep state in this setting. In addition, the development of advanced computational techniques to analyze EEG data has opened new opportunities in the identification of reliable and reproducible biomarkers of drug resistance in IGE patients. In this manuscript, we summarize the EEG findings associated with treatment resistance in IGE by reviewing the results of studies considering standard EEGs, 24-h EEG recordings, and resting-state protocols. We discuss the role of 24-h EEG recordings in assessing seizure recurrence in light of the potential prognostic relevance of generalized fast discharges occurring during sleep. In addition, we highlight new and promising biomarkers as identified by advanced EEG analysis, including hypothesis-driven functional connectivity measures of background activity and data-driven quantitative findings revealed by machine learning approaches. Finally, we thoroughly discuss the methodological limitations observed in existing studies and briefly outline future directions to identify reliable and replicable EEG biomarkers in IGE patients.

Virtual reality and machine learning in the automatic photoparoxysmal response detection

Photosensitivity, in relation to epilepsy, is a genetically determined condition in which patients have epileptic seizures of different severity provoked by visual stimuli. It can be diagnosed by detecting epileptiform discharges in their electroencephalogram (EEG), known as photoparoxysmal responses (PPR). The most accepted PPR detection method—a manual method—considered as the standard one, consists in submitting the subject to intermittent photic stimulation (IPS), i.e. a flashing light stimulation at increasing and decreasing flickering frequencies in a hospital room under controlled ambient conditions, while at the same time recording her/his brain response by means of EEG signals. This research focuses on introducing virtual reality (VR) in this context, adding, to the conventional infrastructure a more flexible one that can be programmed and that will allow developing a much wider and richer set of experiments in order to detect neurological illnesses, and to study subjects’ behaviours automatically. The loop includes the subject, the VR device, the EEG infrastructure and a computer to analyse and monitor the EEG signal and, in some cases, provide feedback to the VR. As will be shown, AI modelling will be needed in the automatic detection of PPR, but it would also be used in extending the functionality of this system with more advanced features. This system is currently in study with subjects at Burgos University Hospital, Spain.