Ewan S. Nurse

Minimally invasive endovascular stent-electrode array for high-fidelity, chronic recordings of cortical neural activity

High-fidelity intracranial electrode arrays for recording and stimulating brain activity have facilitated major advances in the treatment of neurological conditions over the past decade. Traditional arrays require direct implantation into the brain via open craniotomy, which can lead to inflammatory tissue responses, necessitating development of minimally invasive approaches that avoid brain trauma. Here we demonstrate the feasibility of chronically recording brain activity from within a vein using a passive stent-electrode recording array (stentrode). We achieved implantation into a superficial cortical vein overlying the motor cortex via catheter angiography and demonstrate neural recordings in freely moving sheep for up to 190 d. Spectral content and bandwidth of vascular electrocorticography were comparable to those of recordings from epidural surface arrays. Venous internal lumen patency was maintained for the duration of implantation. Stentrodes may have wide ranging applications as a neural interface for treatment of a range of neurological conditions.

Decoding EEG and LFP signals using deep learning: heading TrueNorth

Deep learning technology is uniquely suited to analyse neurophysiological signals such as the electroencephalogram (EEG) and local field potentials (LFP) and promises to outperform traditional machine-learning based classification and feature extraction algorithms. Furthermore, novel cognitive computing platforms such as IBMs recently introduced neuromorphic TrueNorth chip allow for deploying deep learning techniques in an ultra-low power environment with a minimum device footprint. Merging deep learning and TrueNorth technologies for real-time analysis of brain-activity data at the point of sensing will create the next generation of wearables at the intersection of neurobionics and artificial intelligence.

A Generalizable Brain-Computer Interface (BCI) Using Machine Learning for Feature Discovery

This work describes a generalized method for classifying motor-related neural signals for a brain-computer interface (BCI), based on a stochastic machine learning method. The method differs from the various feature extraction and selection techniques employed in many other BCI systems. The classifier does not use extensive a-priori information, resulting in reduced reliance on highly specific domain knowledge. Instead of pre-defining features, the time-domain signal is input to a population of multi-layer perceptrons (MLPs) in order to perform a stochastic search for the best structure. The results showed that the average performance of the new algorithm outperformed other published methods using the Berlin BCI IV (2008) competition dataset and was comparable to the best results in the Berlin BCI II (2002–3) competition dataset. The new method was also applied to electroencephalography (EEG) data recorded from five subjects undertaking a hand squeeze task and demonstrated high levels of accuracy with a mean classification accuracy of 78.9% after five-fold cross-validation. Our new approach has been shown to give accurate results across different motor tasks and signal types as well as between subjects.

Epileptic Seizure Prediction Using Big Data and Deep Learning: Toward a Mobile System

Background Seizure prediction can increase independence and allow preventative treatment for patients with epilepsy. We present a proof-of-concept for a seizure prediction system that is accurate, fully automated, patient-specific, and tunable to an individuals needs. Methods Intracranial electroencephalography (iEEG) data of ten patients obtained from a seizure advisory system were analyzed as part of a pseudoprospective seizure prediction study. First, a deep learning classifier was trained to distinguish between preictal and interictal signals. Second, classifier performance was tested on held-out iEEG data from all patients and benchmarked against the performance of a random predictor. Third, the prediction system was tuned so sensitivity or time in warning could be prioritized by the patient. Finally, a demonstration of the feasibility of deployment of the prediction system onto an ultra-low power neuromorphic chip for autonomous operation on a wearable device is provided. Results The prediction system achieved mean sensitivity of 69% and mean time in warning of 27%, significantly surpassing an equivalent random predictor for all patients by 42%. Conclusion This study demonstrates that deep learning in combination with neuromorphic hardware can provide the basis for a wearable, real-time, always-on, patient-specific seizure warning system with low power consumption and reliable long-term performance.

Intracranial EEG fluctuates over months after implanting electrodes in human brain

OBJECTIVE Implanting subdural and penetrating electrodes in the brain causes acute trauma and inflammation that affect intracranial electroencephalographic (iEEG) recordings. This behavior and its potential impact on clinical decision-making and algorithms for implanted devices have not been assessed in detail. In this study we aim to characterize the temporal and spatial variability of continuous, prolonged human iEEG recordings. APPROACH Intracranial electroencephalography from 15 patients with drug-refractory epilepsy, each implanted with 16 subdural electrodes and continuously monitored for an average of 18 months, was included in this study. Time and spectral domain features were computed each day for each channel for the duration of each patients recording. Metrics to capture post-implantation feature changes and inflexion points were computed on group and individual levels. A linear mixed model was used to characterize transient group-level changes in feature values post-implantation and independent linear models were used to describe individual variability. MAIN RESULTS A significant decline in features important to seizure detection and prediction algorithms (mean line length, energy, and half-wave), as well as mean power in the Berger and high gamma bands, was observed in many patients over 100 d following implantation. In addition, spatial variability across electrodes declines post-implantation following a similar timeframe. All selected features decreased by 14-50% in the initial 75 d of recording on the group level, and at least one feature demonstrated this pattern in 13 of the 15 patients. Our findings indicate that iEEG signal features demonstrate increased variability following implantation, most notably in the weeks immediately post-implant. SIGNIFICANCE These findings suggest that conclusions drawn from iEEG, both clinically and for research, should account for spatiotemporal signal variability and that properly assessing the iEEG in patients, depending upon the application, may require extended monitoring.

Postictal suppression and seizure durations: A patient-specific, long-term iEEG analysis

We report on patient‐specific durations of postictal periods in long‐term intracranial electroencephalography (iEEG) recordings. The objective was to investigate the relationship between seizure duration and postictal suppression duration.

PROBING TO OBSERVE NEURAL DYNAMICS INVESTIGATED WITH NETWORKED KURAMOTO OSCILLATORS

The expansion of frontiers in neural engineering is dependent on the ability to track, detect and predict dynamics in neural tissue. Recent innovations to elucidate information from electrical recordings of brain dynamics, such as epileptic seizure prediction, have involved switching to an active probing paradigm using electrically evoked recordings rather than traditional passive measurements. This paper positions the advantage of probing in terms of information extraction, by using a coupled oscillator Kuramoto model to represent brain dynamics. While active probing performs better at observing underlying system synchrony in Kuramoto networks, especially in non-Gaussian measurement environments, the benefits diminish with increasing relative size of electrode spatial resolution compared to synchrony area. This suggests probing will be useful for improved characterization of synchrony for suitably dense electrode recordings.

Consistency of Long-Term of Subdural Electrocorticography in Humans

Objective: Subdural electrocorticography (ECoG) can provide a robust control signal for a brain–computer interface (BCI). However, the long-term recording properties of ECoG are poorly understood as most ECoG studies in the BCI field have only used signals recorded for less than 28 days. We assessed human ECoG recordings over durations of many months to investigate changes to recording quality that occur with long-term implantation. Methods: We examined changes in signal properties over time from 15 ambulatory humans who had continuous subdural ECoG monitoring for 184–766 days. Results: Individual electrodes demonstrated varying changes in frequency power characteristics over time within individual patients and between patients. Group level analyses demonstrated that there were only small changes in effective signal bandwidth and spectral band power across months. High-gamma signals could be recorded throughout the study, though there was a decline in signal power for some electrodes. Conclusion: ECoG-based BCI systems can robustly record high-frequency activity over multiple years, albeit with marked intersubject variability. Significance: Group level results demonstrated that ECoG is a promising modality for long-term BCI and neural prosthesis applications.

Bursts of seizures in long-term recordings of human focal epilepsy.

We report on temporally clustered seizures detected from continuous long‐term ambulatory human electroencephalographic data. The objective was to investigate short‐term seizure clustering, which we have termed bursting, and consider implications for patient care, seizure prediction, and evaluating therapies.

Movement related directional tuning from broadband electrocorticography in humans

Directional tuning is the tendency for cortical neurons to exhibit a peak firing rate when a limb is moved in a preferred direction. This phenomenon has been used to underpin decoding strategies in many brain-machine interface (BMI) systems. Although it is well established that individual motor neurons can be decoded using directional tuning, this is not as well understood at the scale of cortical local field potentials (LFPs). This study investigates the directional tuning properties of broadband electrocorticography (ECoG) recorded during a center-out task from two human participants. Selected bipolar ECoG channels demonstrated directional tuning in signal power from 85 - 250 Hz for both subjects. Directional tuning was observed across sensorimotor cortex, as well as frontal areas of cortex. The presence of directional tuning in broadband ECoG suggests the potential use of tuning curves as the basis of a LFP based BMI system.