Localizing epileptogenic regions using high-frequency oscillations and machine learning

Networks through the lens of high-frequency oscillations

To date, there is no neurophysiologic or neuroimaging biomarker that can accurately delineate the epileptogenic network. High-frequency oscillations (HFO) have been proposed as biomarkers for epileptogenesis and the epileptogenic network. The pathological HFO have been associated with areas of seizure onset and epileptogenic tissue. Several studies have demonstrated that the resection of areas with high rates of pathological HFO is associated with favorable postoperative outcomes. Recent studies have demonstrated the spatiotemporal organization of HFO into networks and their potential role in defining epileptogenic networks. Our review will present the existing literature on HFO-associated networks, specifically focusing on their role in defining epileptogenic networks and their potential significance in surgical planning.

Practical measurements distinguishing physiological and pathological stereoelectroencephalography channels based on high-frequency oscillations in the human brain

OBJECTIVE

The present study aimed to identify various distinguishing features for use in the accurate classification of stereoelectroencephalography (SEEG) channels based on high-frequency oscillations (HFOs) inside and outside the epileptogenic zone (EZ).

METHODS

HFOs were detected in patients with focal epilepsy who underwent SEEG. Subsequently, HFOs within the seizure-onset and early spread zones were defined as pathological HFOs, whereas others were defined as physiological. Three features of HFOs were identified at the channel level, namely, morphological repetition, rhythmicity, and phase-amplitude coupling (PAC). A machine-learning (ML) classifier was then built to distinguish two HFO types at the channel level by application of the above-mentioned features, and the contributions were quantified. Further verification of the characteristics and classifier performance was performed in relation to various conscious states, imaging results, EZ location, and surgical outcomes.

RESULTS

Thirty-five patients were included in this study, from whom 166  104 pathological HFOs in 255 channels and 53 374 physiological HFOs in 282 channels were entered into the analysis pipeline. The results revealed that the morphological repetitions of pathological HFOs were markedly higher than those of the physiological HFOs; this was also observed for rhythmicity and PAC. The classifier exhibited high accuracy in differentiating between the two forms of HFOs, as indicated by an area under the curve (AUC) of 0.89. Both PAC and rhythmicity contributed significantly to this distinction. The subgroup analyses supported these findings.

SIGNIFICANCE

The suggested HFO features can accurately distinguish between pathological and physiological channels substantially improving its usefulness in clinical localization.

PLAIN LANGUAGE SUMMARY

In this study, we computed three quantitative features associated with HFOs in each SEEG channel and then constructed a machine learning-based classifier for the classification of pathological and physiological channels. The classifier performed well in distinguishing the two channel types under different levels of consciousness as well as in terms of imaging results, EZ location, and patient surgical outcomes.

A Review of EEG-based Localization of Epileptic Seizure Foci: Common Points with Multimodal Fusion of Brain Data

Unexpected seizures significantly decrease the quality of life in epileptic patients. Seizure attacks are caused by hyperexcitability and anatomical lesions of special regions of the brain, and cognitive impairments and memory deficits are their most common concomitant effects. In addition to seizure reduction treatments, medical rehabilitation involving brain-computer interfaces and neurofeedback can improve cognition and quality of life in patients with focal epilepsy in most cases, in particular when resective epilepsy surgery has been considered treatment in drug-resistant epilepsy. Source estimation and precise localization of epileptic foci can improve such rehabilitation and treatment. Electroencephalography (EEG) monitoring and multimodal noninvasive neuroimaging techniques such as ictal/interictal single-photon emission computerized tomography (SPECT) imaging and structural magnetic resonance imaging are common practices for the localization of epileptic foci and have been studied in several kinds of researches. In this article, we review the most recent research on EEG-based localization of seizure foci and discuss various methods, their advantages, limitations, and challenges with a focus on model-based data processing and machine learning algorithms. In addition, we survey whether combined analysis of EEG monitoring and neuroimaging techniques, which is known as multimodal brain data fusion, can potentially increase the precision of the seizure foci localization. To this end, we further review and summarize the key parameters and challenges of processing, fusion, and analysis of multiple source data, in the framework of model-based signal processing, for the development of a multimodal brain data analyzing system. This article has the potential to be used as a valuable resource for neuroscience researchers for the development of EEG-based rehabilitation systems based on multimodal data analysis related to focal epilepsy.

Pathological and Physiological High-frequency Oscillations on Electroencephalography in Patients with Epilepsy

High-frequency oscillations (HFOs) encompass ripples (80 Hz-200 Hz) and fast ripples (200 Hz-600 Hz), serving as a promising biomarker for localizing the epileptogenic zone in epilepsy. Spontaneous fast ripples are always pathological, while ripples may be physiological or pathological. Distinguishing physiological from pathological ripples is important not only for designating epileptogenic brain regions, but also for investigations that study ripples in the context of memory encoding, consolidation, and recall in patients with epilepsy. Many studies have sought to identify distinguishing features between pathological and physiological ripples over the past two decades. Physiological and pathological ripples differ with respect to their spatial location, cellular mechanisms, morphology, and coupling with background electroencephalographic activity. Retrospective studies have demonstrated that differentiating between pathological and physiological ripples can improve surgical outcome prediction. In this review, we summarize the characteristics, differences, and applications of pathological and physiological HFOs and discuss strategies for their clinical translation.

Epilepsy and Encephalopathy

BACKGROUND

Epilepsy encompasses more than the predisposition to unprovoked seizures. In children, epileptic activity during (ictal) and between (interictal) seizures has the potential to disrupt normal brain development. The term "epileptic encephalopathy (EE)" refers to the concept that such abnormal activity may contribute to cognitive and behavioral impairments beyond that expected from the underlying cause of the epileptic activity.

METHODS

In this review, we survey the concept of EE across a diverse selection of syndromes to illustrate its broad applicability in pediatric epilepsy. We review experimental evidence that provides mechanistic insights into how epileptic activity has the potential to impact normal brain processes and the development of neural networks. We then discuss opportunities to improve developmental outcomes in epilepsy now and in the future.

RESULTS

Epileptic activity in the brain poses a threat to normal physiology and brain development.

CONCLUSION

Until we have treatments that reliably target and effectively treat the underlying causes of epilepsy, a major goal of management is to prevent epileptic activity from worsening developmental outcomes.

Improving the accuracy of epileptogenic zone localization in stereo EEG with machine learning algorithms

The precise identification of the epileptogenic zone (EZ) is paramount in the presurgical evaluation of epilepsy patients to ensure successful surgical outcomes. The analysis of Stereo EEG, an instrumental tool for EZ localization, poses considerable challenges even for experienced epileptologists. Consequently, the development of machine learning (ML)-based computational tools for enhanced EZ localization is imperative. In this investigation, we developed ML models utilizing Stereo EEG from 15 patients, who remained seizure-free (Engel 1 a-d) following EZ resection, over an average follow-up period of 44.4 months. Utilizing Delphos and MNI detectors, spikes and High Frequency Oscillations (HFOs) were identified from Stereo EEG in Resected Zone (RZ) and non-Resected Zone (non-RZ). Linear and non-linear features were estimated from each modality using MATLAB. A total of 27,744 spikes, 7,790 ripples, and 7,632 fast ripples, along with their combinations, were employed to train the ML models. The Gradient Boosting classifier demonstrated the highest prediction accuracy of 98.5% for EZ localization in Mesial Temporal Lobe Epilepsy (MTLE) when trained with features derived from the spike-ripple combination. In the case of Neocortical Epilepsy (NE), the Extra Trees classifier achieved an accuracy of 87.6% when utilizing features from fast ripples. The Random Forest, Extra Trees, and Gradient Boosting algorithms were the most effective for predicting the RZ. Linear features outperformed non-linear features in predicting epileptogenic zones within the epileptic brain. Our study establishes the capability of ML methodologies in localizing epileptogenic zones with high accuracy. Future studies that focus on increasing the training sample size and incorporating more advanced machine learning (ML) algorithms have the potential to significantly improve the accuracy of these models in pinpointing epileptogenic networks. Additionally, implementing this ML approach across multiple research centers would contribute to the broader validation and generalizability of this technique.

Capturing the power of seizures: an empirical mode decomposition analysis of epileptic activity in the mouse hippocampus

Introduction

Various methods have been used to determine the frequency components of seizures in scalp electroencephalography (EEG) and in intracortical recordings. Most of these methods rely on subjective or trial-and-error criteria for choosing the appropriate bandwidth for filtering the EEG or local field potential (LFP) signals to establish the frequency components that contribute most to the initiation and maintenance of seizure activity. The empirical mode decomposition (EMD) with the Hilbert-Huang transform is an unbiased method to decompose a time and frequency variant signal into its component non-stationary frequencies. The resulting components, i.e., the intrinsic mode functions (IMFs) objectively reflect the various non-stationary frequencies making up the original signal.

Materials and methods

We employed the EMD method to analyze the frequency components and relative power of spontaneous electrographic seizures recorded in the dentate gyri of mice during the epileptogenic period. Epilepsy was induced in mice following status epilepticus induced by suprahippocampal injection of kainic acid. The seizures were recorded as local field potentials (LFP) with electrodes implanted in the dentate gyrus. We analyzed recording segments that included a seizure (mean duration 28 s) and an equivalent time period both before and after the seizure. Each segment was divided into non-overlapping 1 s long epochs which were then analyzed to obtain their IMFs (usually 8-10), the center frequencies of the respective IMF and their spectral root-mean-squared (RMS) power.

Results

Our analysis yielded unbiased identification of the spectral components of seizures, and the relative power of these components during this pathological brain activity. During seizures, the power of the mid frequency components increased while the center frequency of the first IMF (with the highest frequency) dramatically decreased, providing mechanistic insights into how local seizures are generated.

Discussion

We expect this type of analysis to provide further insights into the mechanisms of seizure generation and potentially better seizure detection.

Epileptogenic high-frequency oscillations present larger amplitude both in mesial temporal and neocortical regions

High-frequency oscillations (HFO) are a promising biomarker for the identification of epileptogenic tissue. While HFO rates have been shown to predict seizure outcome, it is not yet clear whether their morphological features might improve this prediction. We validated HFO rates against seizure outcome and delineated the distribution of HFO morphological features. We collected stereo-EEG recordings from 20 patients (231 electrodes; 1,943 contacts). We computed HFO rates (the co-occurrence of ripples and fast ripples) through a validated automated detector during non-rapid eye movement sleep. Applying machine learning, we delineated HFO morphological features within and outside epileptogenic tissue across mesial temporal lobe (MTL) and Neocortex. HFO rates predicted seizure outcome with 85% accuracy, 79% specificity, 100% sensitivity, 100% negative predictive value, and 67% positive predictive value. The analysis of HFO features showed larger amplitude in the epileptogenic tissue, similar morphology for epileptogenic HFO in MTL and Neocortex, and larger amplitude for physiological HFO in MTL. We confirmed HFO rates as a reliable biomarker for epilepsy surgery and characterized the potential clinical relevance of HFO morphological features. Our results support the prospective use of HFO in epilepsy surgery and contribute to the anatomical mapping of HFO morphology.

Decoding Intracranial EEG With Machine Learning: A Systematic Review

Advances in intracranial electroencephalography (iEEG) and neurophysiology have enabled the study of previously inaccessible brain regions with high fidelity temporal and spatial resolution. Studies of iEEG have revealed a rich neural code subserving healthy brain function and which fails in disease states. Machine learning (ML), a form of artificial intelligence, is a modern tool that may be able to better decode complex neural signals and enhance interpretation of these data. To date, a number of publications have applied ML to iEEG, but clinician awareness of these techniques and their relevance to neurosurgery, has been limited. The present work presents a review of existing applications of ML techniques in iEEG data, discusses the relative merits and limitations of the various approaches, and examines potential avenues for clinical translation in neurosurgery. One-hundred-seven articles examining artificial intelligence applications to iEEG were identified from 3 databases. Clinical applications of ML from these articles were categorized into 4 domains: i) seizure analysis, ii) motor tasks, iii) cognitive assessment, and iv) sleep staging. The review revealed that supervised algorithms were most commonly used across studies and often leveraged publicly available timeseries datasets. We conclude with recommendations for future work and potential clinical applications.

Transformer-Based High-Frequency Oscillation Signal Detection on Magnetoencephalography From Epileptic Patients

High-frequency oscillations (HFOs), observed within 80–500 Hz of magnetoencephalography (MEG) data, are putative biomarkers to localize epileptogenic zones that are critical for the success of surgical epilepsy treatment. It is crucial to accurately detect HFOs for improving the surgical outcome of patients with epilepsy. However, in clinical practices, detecting HFOs in MEG signals mainly depends on visual inspection by clinicians, which is very time-consuming, labor-intensive, subjective, and error-prone. To accurately and automatically detect HFOs, machine learning approaches have been developed and have demonstrated the promising results of automated HFO detection. More recently, the transformer-based model has attracted wide attention and achieved state-of-the-art performance on many machine learning tasks. In this paper, we are investigating the suitability of transformer-based models on the detection of HFOs. Specifically, we propose a transformer-based HFO detection framework for biomedical MEG one-dimensional signal data. For signal classification, we develop a transformer-based HFO (TransHFO) classification model. Then, we investigate the relationship between depth of deep learning models and classification performance. The experimental results show that the proposed framework outperforms the state-of-the-art HFO classifiers, increasing classification accuracy by 7%. Furthermore, we find that shallow TransHFO (< 10 layers) outperforms deep TransHFO models (≥10 layers) on most data augmented factors.

Beyond rates: time-varying dynamics of high frequency oscillations as a biomarker of the seizure onset zone

Objective. High frequency oscillations (HFOs) recorded by intracranial electrodes have generated excitement for their potential to help localize epileptic tissue for surgical resection. However, the number of HFOs per minute (i.e. the HFO 'rate') is not stable over the duration of intracranial recordings; for example, the rate of HFOs increases during periods of slow-wave sleep. Moreover, HFOs that are predictive of epileptic tissue may occur in oscillatory patterns due to phase coupling with lower frequencies. Therefore, we sought to further characterize between-seizure (i.e. 'interictal') HFO dynamics both within and outside the seizure onset zone (SOZ).Approach. Using long-term intracranial EEG (mean duration 10.3 h) from 16 patients, we automatically detected HFOs using a new algorithm. We then fit a hierarchical negative binomial model to the HFO counts. To account for differences in HFO dynamics and rates between sleep and wakefulness, we also fit a mixture model to the same data that included the ability to switch between two discrete brain states that were automatically determined during the fitting process. The ability to predict the SOZ by model parameters describing HFO dynamics (i.e. clumping coefficients and coefficients of variation) was assessed using receiver operating characteristic curves.Main results. Parameters that described HFO dynamics were predictive of SOZ. In fact, these parameters were found to be more consistently predictive than HFO rate. Using concurrent scalp EEG in two patients, we show that the model-found brain states corresponded to (1) non-REM sleep and (2) awake and rapid eye movement sleep. However the brain state most likely corresponding to slow-wave sleep in the second model improved SOZ prediction compared to the first model for only some patients.Significance. This work suggests that delineation of SOZ with interictal data can be improved by the inclusion of time-varying HFO dynamics.

Three dimensional microelectrodes enable high signal and spatial resolution for neural seizure recordings in brain slices and freely behaving animals

Neural recordings made to date through various approaches—both in-vitro or in-vivo—lack high spatial resolution and a high signal-to-noise ratio (SNR) required for detailed understanding of brain function, synaptic plasticity, and dysfunction. These shortcomings in turn deter the ability to further design diagnostic, therapeutic strategies and the fabrication of neuro-modulatory devices with various feedback loop systems. We report here on the simulation and fabrication of fully configurable neural micro-electrodes that can be used for both in vitro and in vivo applications, with three-dimensional semi-insulated structures patterned onto custom, fine-pitch, high density arrays. These microelectrodes were interfaced with isolated brain slices as well as implanted in brains of freely behaving rats to demonstrate their ability to maintain a high SNR. Moreover, the electrodes enabled the detection of epileptiform events and high frequency oscillations in an epilepsy model thus offering a diagnostic potential for neurological disorders such as epilepsy. These microelectrodes provide unique opportunities to study brain activity under normal and various pathological conditions, both in-vivo and in in-vitro, thus furthering the ability to develop drug screening and neuromodulation systems that could accurately record and map the activity of large neural networks over an extended time period.

Epileptic High-Frequency Oscillations in Intracranial EEG Are Not Confounded by Cognitive Tasks

Rationale: High-frequency oscillations (HFOs) in intracranial EEG (iEEG) are used to delineate the epileptogenic zone during presurgical diagnostic assessment in patients with epilepsy. HFOs are historically divided into ripples (80-250 Hz), fast ripples (FR, >250 Hz), and their co-occurrence (FRandR). In a previous study, we had validated the rate of FRandRs during deep sleep to predict seizure outcome. Here, we ask whether epileptic FRandRs might be confounded by physiological FRandRs that are unrelated to epilepsy. Methods: We recorded iEEG in the medial temporal lobe MTL (hippocampus, entorhinal cortex, and amygdala) in 17 patients while they performed cognitive tasks. The three cognitive tasks addressed verbal working memory, visual working memory, and emotional processing. In our previous studies, these tasks activated the MTL. We re-analyzed the data of these studies with the automated detector that focuses on the co-occurrence of ripples and FRs (FRandR). Results: For each task, we identified those channels in which the HFO rate was modulated during the task condition compared to the control condition. However, the number of these channels did not exceed the chance level. Interestingly, even during wakefulness, the HFO rate was higher for channels within the seizure onset zone (SOZ) than for channels outside the SOZ. Conclusion: Our prospective definition of an epileptic HFO, the FRandR, is not confounded by physiological HFOs that might be elicited by our cognitive tasks. This is reassuring for the clinical use of FRandR as a biomarker of the EZ.

High-Frequency Oscillations in Epilepsy: What Have We Learned and What Needs to be Addressed

For the past 2 decades, high-frequency oscillations (HFOs) have been enthusiastically studied by the epilepsy community. Emerging evidence shows that HFOs harbor great promise to delineate epileptogenic brain areas and possibly predict the likelihood of seizures. Investigations into HFOs in clinical epilepsy have advanced from small retrospective studies relying on visual identification and correlation analysis to larger prospective assessments using automatic detection and prediction strategies. Although most studies have yielded promising results, some have revealed significant obstacles to clinical application of HFOs, thus raising debate about the reliability and practicality of HFOs as clinical biomarkers. In this review, we give an overview of the current state of HFO research and pinpoint the conceptual and methodological issues that have hampered HFO translation. We highlight recent insights gained from long-term data, high-density recordings, and multicenter collaborations and discuss the open questions that need to be addressed in future research.

HFO to Measure Seizure Propensity and Improve Prognostication in Patients With Epilepsy

The study of high frequency oscillations (HFO) in the electroencephalogram (EEG) as biomarkers of epileptic activity has merely focused on their spatial location and relationship to the epileptogenic zone. It has been suggested in several ways that the amount of HFO at a certain point in time may reflect the disease activity or severity. This could be clinically useful in several ways, especially as noninvasive recording of HFO appears feasible. We grouped the potential hypotheses into 4 categories: (1) HFO as biomarkers to predict the development of epilepsy; (2) HFO as biomarkers to predict the occurrence of seizures; (3) HFO as biomarkers linked to the severity of epilepsy, and (4) HFO as biomarkers to evaluate outcome of treatment. We will review the literature that addresses these 4 hypotheses and see to what extent HFO can be used to measure seizure propensity and help determine prognosis of this unpredictable disease.

Artificial intelligence for brain diseases: A systematic review

Artificial intelligence (AI) is a major branch of computer science that is fruitfully used for analyzing complex medical data and extracting meaningful relationships in datasets, for several clinical aims. Specifically, in the brain care domain, several innovative approaches have achieved remarkable results and open new perspectives in terms of diagnosis, planning, and outcome prediction. In this work, we present an overview of different artificial intelligent techniques used in the brain care domain, along with a review of important clinical applications. A systematic and careful literature search in major databases such as Pubmed, Scopus, and Web of Science was carried out using "artificial intelligence" and "brain" as main keywords. Further references were integrated by cross-referencing from key articles. 155 studies out of 2696 were identified, which actually made use of AI algorithms for different purposes (diagnosis, surgical treatment, intra-operative assistance, and postoperative assessment). Artificial neural networks have risen to prominent positions among the most widely used analytical tools. Classic machine learning approaches such as support vector machine and random forest are still widely used. Task-specific algorithms are designed for solving specific problems. Brain images are one of the most used data types. AI has the possibility to improve clinicians' decision-making ability in neuroscience applications. However, major issues still need to be addressed for a better practical use of AI in the brain. To this aim, it is important to both gather comprehensive data and build explainable AI algorithms.

Double-Step Machine Learning Based Procedure for HFOs Detection and Classification

The need for automatic detection and classification of high-frequency oscillations (HFOs) as biomarkers of the epileptogenic tissue is strongly felt in the clinical field. In this context, the employment of artificial intelligence methods could be the missing piece to achieve this goal. This work proposed a double-step procedure based on machine learning algorithms and tested it on an intracranial electroencephalogram (iEEG) dataset available online. The first step aimed to define the optimal length for signal segmentation, allowing for an optimal discrimination of segments with HFO relative to those without. In this case, binary classifiers have been tested on a set of energy features. The second step aimed to classify these segments into ripples, fast ripples and fast ripples occurring during ripples. Results suggest that LDA applied to 10 ms segmentation could provide the highest sensitivity (0.874) and 0.776 specificity for the discrimination of HFOs from no-HFO segments. Regarding the three-class classification, non-linear methods provided the highest values (around 90%) in terms of specificity and sensitivity, significantly different to the other three employed algorithms. Therefore, this machine-learning-based procedure could help clinicians to automatically reduce the quantity of irrelevant data.