HFO Detection in Epilepsy: A Stacked Denoising Autoencoder and Sample Weight Adjusting Factors-Based Method

Identification of epileptic networks with graph convolutional network incorporating oscillatory activities and evoked synaptic responses

Stereoelectroencephalography (SEEG) offers unique neural data from in-depth brain structures with fine temporal resolutions to better investigate the origin of epileptic brain activities. Although oscillatory patterns from different frequency bands and functional connectivity computed from the SEEG datasets are employed to study the epileptic zones, direct electrical stimulation-evoked electrophysiological recordings of synaptic responses, namely cortical-cortical evoked potentials (CCEPs), from the same SEEG electrodes are not explored for the localization of epileptic zones. Here we proposed a two-stream model with unsupervised learning and graph convolutional network tailored to the SEEG and CCEP datasets in individual patients to perform localization of epileptic zones. We compared our localization results with the clinically marked electrode sites determined for surgical resections. Our model had good classification capability when compared to other state-of-the-art methods. Furthermore, based on our prediction results we performed group-level brain-area mapping analysis for temporal, frontal and parietal epilepsy patients and found that epileptic and non-epileptic brain networks were distinct in patients with different types of focal epilepsy. Our unsupervised data-driven model provides personalized localization analysis for the epileptic zones. The epileptic and non-epileptic brain areas disclosed by the prediction model provide novel insights into the network-level pathological characteristics of epilepsy.

Implementation of a Morphological Filter for Removing Spikes from the Epileptic Brain Signals to Improve Identification Ripples

Epilepsy is a very common disease affecting at least 1% of the population, comprising a number of over 50 million people. As many patients suffer from the drug-resistant version, the number of potential treatment methods is very small. However, since not only the treatment of epilepsy, but also its proper diagnosis or observation of brain signals from recordings are important research areas, in this paper, we address this very problem by developing a reliable technique for removing spikes and sharp transients from the baseline of the brain signal using a morphological filter. This allows much more precise identification of the so-called epileptic zone, which can then be resected, which is one of the methods of epilepsy treatment. We used eight patients with 5 KHz data set and depended upon the Staba 2002 algorithm as a reference to detect the ripples. We found that the average sensitivity and false detection rate of our technique are significant, and they are ∼94% and ∼14%, respectively.

An approach for reliably identifying high-frequency oscillations and reducing false-positive detections

OBJECTIVE

Aiming to improve the feasibility and reliability of using high-frequency oscillations (HFOs) for translational studies of epilepsy, we present a pipeline with features specifically designed to reject false positives for HFOs to improve the automatic HFO detector.

METHODS

We presented an integrated, multi-layered procedure capable of automatically rejecting HFOs from a variety of common false positives, such as motion, background signals, and sharp transients. This method utilizes a time-frequency contour approach that embeds three different layers including peak constraints, power thresholds, and morphological identification to discard false positives. Four experts were involved in rating detected HFO events that were randomly selected from different posttraumatic epilepsy (PTE) animals for a comprehensive evaluation.

RESULTS

The algorithm was run on 768-h recordings of intracranial electrodes in 48 PTE animals. A total of 453 917 HFOs were identified by initial HFO detection, of which 450 917 were implemented for HFO refinement and 203 531 events were retained. Random sampling was used to evaluate the performance of the detector. The HFO detection yielded an overall accuracy of 0.95 ± 0.03 , with precision, recall, and F1 scores of 0.92 ± 0.05 , 0.99 ± 0.01 , and 0.94 ± 0.03 , respectively. For the HFO classification, our algorithm obtained an accuracy of 0.97 ± 0.02 . For the inter-rater reliability of algorithm evaluation, the agreement among four experts was 0.94 ± 0.03 for HFO detection and 0.85 ± 0.04 for HFO classification.

SIGNIFICANCE

Our approach shows that a segregated pipeline design with a focus on false-positive rejection can improve the detection efficiency and provide reliable results. This pipeline does not require customization and uses fixed parameters, making it highly feasible and translatable for basic and clinical applications of epilepsy.

An intelligent epilepsy seizure detection system using adaptive mode decomposition of EEG signals

Epilepsy is a chronic neurological disorder that involves abnormal electrical signal patterns of the brain called seizures. The brain's electrical signals can be recorded using an electroencephalogram (EEG). EEG recordings can be used to monitor complex and non-stationary signals produced by the brain for detecting epilepsy seizures. Machine learning (ML) methods have been successfully applied in different domains to accurately classify the patterns based upon dataset features. However, ML methods are unable to analyze the raw EEG signals. Appropriate features must be extracted from EEG recordings for detecting epilepsy seizures using signal processing methods. This work proposes an intelligent system by integrating variational mode decomposition (VMD) and Hilbert transform (HT) method for extracting useful features from EEG signals and stacked neural network (NN) method for detecting epilepsy seizures. VMD method decomposers EEG signals into intrinsic mode functions, followed by the HT method for extracting features from EEG signals. The stacked-NN approach is applied for detecting epilepsy seizures using extracted features. The performance of the proposed system is validated using benchmark datasets for epilepsy seizure detection provided by Bonn University and, Neurology and Sleep Centre, New Delhi (NSC-ND). The performance of the proposed system is compared with other ML methods and state of the art approaches in the field. The reported results demonstrate that the proposed system can detect up to 100% accurate epilepsy seizures using NSC-ND data set and up to 99% accurate epilepsy seizures using Bonn university dataset. The comparative results also demonstrate the better performance of the proposed system over other ML methods and existing approaches for detecting epilepsy seizures. The remarkable performance of the proposed system can help neurological experts to detect epilepsy seizures accurately using EEG signals and can be embedded into the real-time diagnosis of the disease.

Review on Epileptic Seizure Prediction: Machine Learning and Deep Learning Approaches

Epileptic seizures occur due to brain abnormalities that can indirectly affect patient's health. It occurs abruptly without any symptoms and thus increases the mortality rate of humans. Almost 1% of world's population suffers from epileptic seizures. Prediction of seizures before the beginning of onset is beneficial for preventing seizures by medication. Nowadays, modern computational tools, machine learning, and deep learning methods have been used to predict seizures using EEG. However, EEG signals may get corrupted with background noise, and artifacts such as eye blinks and physical movements of muscles may lead to "pops" in the signal, resulting in electrical interference, which is cumbersome to detect through visual inspection for longer duration recordings. These limitations in automatic detection of interictal spikes and epileptic seizures are preferred, which is an essential tool for examining and scrutinizing the EEG recording more precisely. These restrictions bring our attention to present a review of automated schemes that will help neurologists categorize epileptic and nonepileptic signals. While preparing this review paper, it is observed that feature selection and classification are the main challenges in epilepsy prediction algorithms. This paper presents various techniques depending on various features and classifiers over the last few years. The methods presented will give a detailed understanding and ideas about seizure prediction and future research directions.

Automatic Detection of High-Frequency Oscillations Based on an End-to-End Bi-Branch Neural Network and Clinical Cross-Validation

Accurate identification of high-frequency oscillation (HFO) is an important prerequisite for precise localization of epileptic foci and good prognosis of drug-refractory epilepsy. Exploring a high-performance automatic detection method for HFOs can effectively help clinicians reduce the error rate and reduce manpower. Due to the limited analysis perspective and simple model design, it is difficult to meet the requirements of clinical application by the existing methods. Therefore, an end-to-end bi-branch fusion model is proposed to automatically detect HFOs. With the filtered band-pass signal (signal branch) and time-frequency image (TFpic branch) as the input of the model, two backbone networks for deep feature extraction are established, respectively. Specifically, a hybrid model based on ResNet1d and long short-term memory (LSTM) is designed for signal branch, which can focus on both the features in time and space dimension, while a ResNet2d with a Convolutional Block Attention Module (CBAM) is constructed for TFpic branch, by which more attention is paid to useful information of TF images. Then the outputs of two branches are fused to realize end-to-end automatic identification of HFOs. Our method is verified on 5 patients with intractable epilepsy. In intravalidation, the proposed method obtained high sensitivity of 94.62%, specificity of 92.7%, and F1-score of 93.33%, and in cross-validation, our method achieved high sensitivity of 92.00%, specificity of 88.26%, and F1-score of 89.11% on average. The results show that the proposed method outperforms the existing detection paradigms of either single signal or single time-frequency diagram strategy. In addition, the average kappa coefficient of visual analysis and automatic detection results is 0.795. The method shows strong generalization ability and high degree of consistency with the gold standard meanwhile. Therefore, it has great potential to be a clinical assistant tool.