Neurophysiologically Meaningful Motor Imagery EEG Simulation With Applications to Data Augmentation.

Motor imagery-based Brain-Computer Interfaces (MI-BCIs) have gained a lot of attention due to their potential usability in neurorehabilitation and neuroprosthetics. However, the accurate recognition of MI patterns in electroencephalography signals (EEG) is hindered by several data-related limitations, which restrict the practical utilization of these systems. Moreover, leveraging deep learning (DL) models for MI decoding is challenged by the difficulty of accessing user-specific MI-EEG data on large scales. Simulated MI-EEG signals can be useful to address these issues, providing well-defined data for the validation of decoding models and serving as a data augmentation approach to improve the training of DL models. While substantial efforts have been dedicated to implementing effective data augmentation strategies and model-based EEG signal generation, the simulation of neurophysiologically plausible EEG-like signals has not yet been exploited in the context of data augmentation. Furthermore, none of the existing approaches have integrated user-specific neurophysiological information during the data generation process. Here, we present PySimMIBCI, a framework for generating realistic MI-EEG signals by integrating neurophysiologically meaningful activity into biophysical forward models. By means of PySimMIBCI, different user capabilities to control an MI-BCI can be simulated and fatigue effects can be included in the generated EEG. Results show that our simulated data closely resemble real data. Moreover, a proposed data augmentation strategy based on our simulated user-specific data significantly outperforms other state-of-the-art augmentation approaches, enhancing DL models performance by up to 15%.

Invasive neurophysiology and whole brain connectomics for neural decoding in patients with brain implants.

Brain computer interfaces (BCI) provide unprecedented spatiotemporal precision that will enable significant expansion in how numerous brain disorders are treated. Decoding dynamic patient states from brain signals with machine learning is required to leverage this precision, but a standardized framework for identifying and advancing novel clinical BCI approaches does not exist. Here, we developed a platform that integrates brain signal decoding with connectomics and demonstrate its utility across 123 hours of invasively recorded brain data from 73 neurosurgical patients treated for movement disorders, depression and epilepsy. First, we introduce connectomics-informed movement decoders that generalize across cohorts with Parkinson's disease and epilepsy from the US, Europe and China. Next, we reveal network targets for emotion decoding in left prefrontal and cingulate circuits in DBS patients with major depression. Finally, we showcase opportunities to improve seizure detection in responsive neurostimulation for epilepsy. Our platform provides rapid, high-accuracy decoding for precision medicine approaches that can dynamically adapt neuromodulation therapies in response to the individual needs of patients.

Deep net detection and onset prediction of electrographic seizure patterns in responsive neurostimulation.

OBJECTIVE: Managing the progress of drug-resistant epilepsy patients implanted with the Responsive Neurostimulation (RNS) System requires the manual evaluation of hundreds of hours of intracranial recordings. The generation of these large amounts of data and the scarcity of experts' time for evaluation necessitate the development of automatic tools to detect intracranial electroencephalographic (iEEG) seizure patterns (iESPs) with expert-level accuracy. We developed an intelligent system for identifying the presence and onset time of iESPs in iEEG recordings from the RNS device. METHODS: An iEEG dataset from 24 patients (36 293 recordings) recorded by the RNS System was used for training and evaluating a neural network model (iESPnet). The model was trained to identify the probability of seizure onset at each sample point of the iEEG. The reliability of the net was assessed and compared to baseline methods, including detections made by the device. iESPnet performance was measured using balanced accuracy and the F1 score for iESP detection. The prediction time was assessed via both the error and the mean absolute error. The model was evaluated following a hold-one-out strategy, and then validated in a separate cohort of 26 patients from a different medical center. RESULTS: iESPnet detected the presence of an iESP with a mean accuracy value of 90% and an onset time prediction error of approximately 3.4 s. There was no relationship between electrode location and prediction outcome. Model outputs were well calibrated and unbiased by the RNS detections. Validation on a separate cohort further supported iESPnet applicability in real clinical scenarios. Importantly, RNS device detections were found to be less accurate and delayed in nonresponders; therefore, tools to improve the accuracy of seizure detection are critical for increasing therapeutic efficacy. SIGNIFICANCE: iESPnet is a reliable and accurate tool with the potential to alleviate the time-consuming manual inspection of iESPs and facilitate the evaluation of therapeutic response in RNS-implanted patients.

A supervised data-driven spatial filter denoising method for speech artifacts in intracranial electrophysiological recordings.

Neurosurgical procedures that enable direct brain recordings in awake patients offer unique opportunities to explore the neurophysiology of human speech. The scarcity of these opportunities and the altruism of participating patients compel us to apply the highest rigor to signal analysis. Intracranial electroencephalography (iEEG) signals recorded during overt speech can contain a speech artifact that tracks the fundamental frequency (F0) of the participant's voice, involving the same high-gamma frequencies that are modulated during speech production and perception. To address this artifact, we developed a spatial-filtering approach to identify and remove acoustic-induced contaminations of the recorded signal. We found that traditional reference schemes jeopardized signal quality, whereas our data-driven method denoised the recordings while preserving underlying neural activity.

Movement decoding using spatio-spectral features of cortical and subcortical local field potentials.

The first commercially sensing enabled deep brain stimulation (DBS) devices for the treatment of movement disorders have recently become available. In the future, such devices could leverage machine learning based brain signal decoding strategies to individualize and adapt therapy in real-time. As multi-channel recordings become available, spatial information may provide an additional advantage for informing machine learning models. To investigate this concept, we compared decoding performances from single channels vs. spatial filtering techniques using intracerebral multitarget electrophysiology in Parkinson's disease patients undergoing DBS implantation. We investigated the feasibility of spatial filtering in invasive neurophysiology and the putative utility of combined cortical ECoG and subthalamic local field potential signals for decoding grip-force, a well-defined and continuous motor readout. We found that adding spatial information to the model can improve decoding (6% gain in decoding), but the spatial patterns and additional benefit was highly individual. Beyond decoding performance results, spatial filters and patterns can be used to obtain meaningful neurophysiological information about the brain networks involved in target behavior. Our results highlight the importance of individualized approaches for brain signal decoding, for which multielectrode recordings and spatial filtering can improve precision medicine approaches for clinical brain computer interfaces.

A motor imagery vs. rest dataset with low-cost consumer grade EEG hardware.

The data consist of electroencephalography (EEG) signals acquired by means of low-cost consumer-grade devices from 10 participants (four females, right-handed, mean age ± SD = 26.1 ± 4.0 years) without any previous experience in Brain-Computer Interfaces (BCIs) usage. The BCI protocol consisted of two conditions, namely the kinesthetic imagination of grasping movement (motor imagery, MI) of the dominant hand and a rest/idle condition. Five protocol runs were required to be performed by each participant in a single-day session, of about 1.5 h. The first run, called RUN0, involved 5 trials of real grasping movement together with the same number of trials in a rest condition. This first run was done to both better explain the protocol and to encourage the participant to focus on the sensation of executing the movement. The rest of the runs (RUN1-RUN4) were identical, consisting of 20 trials for each condition presented in a random order. The electrical brain activity was registered from 15 electrodes covering the sensorimotor area, at a sampling frequency of 125 Hz. Muscle activity of the dominant hand was controlled via the electromyography (EMG) activity by two electrodes placed at two antagonist muscles involved in the flexion/extension of the wrist. The recordings were performed in a non-shielded office, by means of low-cost consumer grade devices and free multi-platform open source software. The EMG corruption level was analyzed and EEG trials for which the EMG activity was higher than a prescribed threshold value, were discarded. During acquisition, EEG data was digitally band-pass filtered between 0.5 and 45 Hz. These data provide a motor imagery vs. rest EEG dataset, relevant for BCI for motor rehabilitation applications. Since the recordings were performed by means of low-cost consumer grade devices in a non-controlled environment, this dataset provides an excellent source for exploring robust brain decoding techniques for future in-home BCI usage.

Electrocorticography is superior to subthalamic local field potentials for movement decoding in Parkinson's disease.

Brain signal decoding promises significant advances in the development of clinical brain computer interfaces (BCI). In Parkinson's disease (PD), first bidirectional BCI implants for adaptive deep brain stimulation (DBS) are now available. Brain signal decoding can extend the clinical utility of adaptive DBS but the impact of neural source, computational methods and PD pathophysiology on decoding performance are unknown. This represents an unmet need for the development of future neurotechnology. To address this, we developed an invasive brain-signal decoding approach based on intraoperative sensorimotor electrocorticography (ECoG) and subthalamic LFP to predict grip-force, a representative movement decoding application, in 11 PD patients undergoing DBS. We demonstrate that ECoG is superior to subthalamic LFP for accurate grip-force decoding. Gradient boosted decision trees (XGBOOST) outperformed other model architectures. ECoG based decoding performance negatively correlated with motor impairment, which could be attributed to subthalamic beta bursts in the motor preparation and movement period. This highlights the impact of PD pathophysiology on the neural capacity to encode movement vigor. Finally, we developed a connectomic analysis that could predict grip-force decoding performance of individual ECoG channels across patients by using their connectomic fingerprints. Our study provides a neurophysiological and computational framework for invasive brain signal decoding to aid the development of an individualized precision-medicine approach to intelligent adaptive DBS.

Differentiation of speech-induced artifacts from physiological high gamma activity in intracranial recordings.

There is great interest in identifying the neurophysiological underpinnings of speech production. Deep brain stimulation (DBS) surgery is unique in that it allows intracranial recordings from both cortical and subcortical regions in patients who are awake and speaking. The quality of these recordings, however, may be affected to various degrees by mechanical forces resulting from speech itself. Here we describe the presence of speech-induced artifacts in local-field potential (LFP) recordings obtained from mapping electrodes, DBS leads, and cortical electrodes. In addition to expected physiological increases in high gamma (60-200 Hz) activity during speech production, time-frequency analysis in many channels revealed a narrowband gamma component that exhibited a pattern similar to that observed in the speech audio spectrogram. This component was present to different degrees in multiple types of neural recordings. We show that this component tracks the fundamental frequency of the participant's voice, correlates with the power spectrum of speech and has coherence with the produced speech audio. A vibration sensor attached to the stereotactic frame recorded speech-induced vibrations with the same pattern observed in the LFPs. No corresponding component was identified in any neural channel during the listening epoch of a syllable repetition task. These observations demonstrate how speech-induced vibrations can create artifacts in the primary frequency band of interest. Identifying and accounting for these artifacts is crucial for establishing the validity and reproducibility of speech-related data obtained from intracranial recordings during DBS surgery.

Machine learning based brain signal decoding for intelligent adaptive deep brain stimulation.

Sensing enabled implantable devices and next-generation neurotechnology allow real-time adjustments of invasive neuromodulation. The identification of symptom and disease-specific biomarkers in invasive brain signal recordings has inspired the idea of demand dependent adaptive deep brain stimulation (aDBS). Expanding the clinical utility of aDBS with machine learning may hold the potential for the next breakthrough in the therapeutic success of clinical brain computer interfaces. To this end, sophisticated machine learning algorithms optimized for decoding of brain states from neural time-series must be developed. To support this venture, this review summarizes the current state of machine learning studies for invasive neurophysiology. After a brief introduction to the machine learning terminology, the transformation of brain recordings into meaningful features for decoding of symptoms and behavior is described. Commonly used machine learning models are explained and analyzed from the perspective of utility for aDBS. This is followed by a critical review on good practices for training and testing to ensure conceptual and practical generalizability for real-time adaptation in clinical settings. Finally, first studies combining machine learning with aDBS are highlighted. This review takes a glimpse into the promising future of intelligent adaptive DBS (iDBS) and concludes by identifying four key ingredients on the road for successful clinical adoption: i) multidisciplinary research teams, ii) publicly available datasets, iii) open-source algorithmic solutions and iv) strong world-wide research collaborations.

Thinking out loud, an open-access EEG-based BCI dataset for inner speech recognition.

Surface electroencephalography is a standard and noninvasive way to measure electrical brain activity. Recent advances in artificial intelligence led to significant improvements in the automatic detection of brain patterns, allowing increasingly faster, more reliable and accessible Brain-Computer Interfaces. Different paradigms have been used to enable the human-machine interaction and the last few years have broad a mark increase in the interest for interpreting and characterizing the "inner voice" phenomenon. This paradigm, called inner speech, raises the possibility of executing an order just by thinking about it, allowing a "natural" way of controlling external devices. Unfortunately, the lack of publicly available electroencephalography datasets, restricts the development of new techniques for inner speech recognition. A ten-participant dataset acquired under this and two others related paradigms, recorded with an acquisition system of 136 channels, is presented. The main purpose of this work is to provide the scientific community with an open-access multiclass electroencephalography database of inner speech commands that could be used for better understanding of the related brain mechanisms.

Transfer Learning Based on Optimal Transport for Motor Imagery Brain-Computer Interfaces.

OBJECTIVE: This paper tackles the cross-sessions variability of electroencephalography-based brain-computer interfaces (BCIs) in order to avoid the lengthy recalibration step of the decoding method before every use. METHODS: We develop a new approach of domain adaptation based on optimal transport to tackle brain signal variability between sessions of motor imagery BCIs. We propose a backward method where, unlike the original formulation, the data from a new session are transported to a calibration session, and thereby avoiding model retraining. Several domain adaptation approaches are evaluated and compared. We simulated two possible online scenarios: i) block-wise adaptation and ii) sample-wise adaptation. In this study, we collect a dataset of 10 subjects performing a hand motor imagery task in 2 sessions. A publicly available dataset is also used. RESULTS: For the first scenario, results indicate that classifier retraining can be avoided by means of our backward formulation yielding to equivalent classification performance as compared to retraining solutions. In the second scenario, classification performance rises up to 90.23% overall accuracy when the label of the indicated mental task is used to learn the transport. Adaptive time is between 10 and 80 times faster than the other methods. CONCLUSIONS: The proposed method is able to mitigate the cross-session variability in motor imagery BCIs. SIGNIFICANCE: The backward formulation is an efficient retraining-free approach built to avoid lengthy calibration times. Thus, the BCI can be actively used after just a few minutes of setup. This is important for practical applications such as BCI-based motor rehabilitation.

Extreme Learning Machine Design for Dealing with Unrepresentative Features.

Extreme Learning Machines (ELMs) have become a popular tool for the classification of electroencephalography (EEG) signals for Brain Computer Interfaces. This is so mainly due to their very high training speed and generalization capabilities. Another important advantage is that they have only one hyperparameter that must be calibrated: the number of hidden nodes. While most traditional approaches dictate that this parameter should be chosen smaller than the number of available training examples, in this article we argue that, in the case of problems in which the data contain unrepresentative features, such as in EEG classification problems, it is beneficial to choose a much larger number of hidden nodes. We characterize this phenomenon, explain why this happens and exhibit several concrete examples to illustrate how ELMs behave. Furthermore, as searching for the optimal number of hidden nodes could be time consuming in enlarged ELMs, we propose a new training scheme, including a novel pruning method. This scheme provides an efficient way of finding the optimal number of nodes, making ELMs more suitable for dealing with real time EEG classification problems. Experimental results using synthetic data and real EEG data show a major improvement in the training time with respect to most traditional and state of the art ELM approaches, without jeopardising classification performance and resulting in more compact networks.

On the relationship between research parasites and fairness in machine learning: challenges and opportunities.

Machine learning systems influence our daily lives in many different ways. Hence, it is crucial to ensure that the decisions and recommendations made by these systems are fair, equitable, and free of unintended biases. Over the past few years, the field of fairness in machine learning has grown rapidly, investigating how, when, and why these models capture, and even potentiate, biases that are deeply rooted not only in the training data but also in our society. In this Commentary, we discuss challenges and opportunities for rigorous posterior analyses of publicly available data to build fair and equitable machine learning systems, focusing on the importance of training data, model construction, and diversity in the team of developers. The thoughts presented here have grown out of the work we did, which resulted in our winning the annual Research Parasite Award that GigaSciencesponsors.

A regularized functional method to determine the hip joint center of rotation in subjects with limited range of motion.

The symmetrical center of rotation estimation (SCoRE) is probably one of the most used functional method for estimating the hip join center (HJC). However, it requires of complex multi-plane movements to find accurate estimations of HJC. Thus, using SCoRE for people with limited hip range of motion will lead to poor HJC estimation. In this work, we propose an anisotropic regularized version of the SCoRE formulation (RSCoRE), which is able to estimate the HJC location by using only standard gait trials, avoiding the need of recording complex multi-plane movements. RSCoRE is evaluated in both accuracy and repeatability of the estimation as compared to functional and predictive methods on a self-recorded cohort of fifteen young healthy adults with no hip joint pathologies or other disorders that could affect their gait. Given that, no medical images were available for this study, to quantify the global error of HJC the SCoRE residual was used. RSCoRE presents a global error of about 12 mm, similarly to the best performance of SCoRE. The comparison of the coordinate's errors at each coordinate indicates that HJC estimations from SCoRE with complex multi-plane movements and RSCoRE are not statistical significantly different. Finally, we show that the repeatability of RSCoRE is similar to the rest of the tested methods, yielding to repeatability values between 0.72 and 0.79. In conclusion, not only the RSCoRE yields similar estimation performance than SCoRE, but it also avoids the need of complex multi-plane movements to be performed by the subject of analysis. For this reason, RSCoRE has the potential to be a valuable approach for estimating the HJC location in people with limited hip ROM.

Unsuspected Pregnancies in Hysterosalpingography: Implementation and Review of a Multi-Institutional Pre-Procedural Pregnancy Screening Protocol.

PURPOSE: Owing to the increasing average age of first-time mothers, as well as advances in assistive reproductive technology, the number of hysterosalpingography (HSG) requests has continued to rise. This increases the likelihood of patients presenting with unsuspected early pregnancies prior to HSG. Currently, there is no standard of practice for the pre-procedural screening of pregnancy prior to HSG, with most institutions using patient-reported pregnancy status and unreliable menstrual cycle dating methods. We implemented a multi-institutional pre-procedural pregnancy screening protocol in order to determine the rate of unsuspected pregnancies prior to HSG and improve the quality and safety of these procedures. METHODS: Following multi-institutional and multidisciplinary input, a consensus protocol was formulated and implemented across 9 institutions in the Lower Mainland of British Columbia, Canada. Subsequent tracking of pregnancy testing was then performed over a period of 3 years. RESULTS: Pre-implementation review of protocols demonstrated large disparities between institutions. A total of 6333 HSG examinations were scheduled in the review period following implementation. Of these, 10 patients were found to have positive pregnancy tests (0.16%), despite self-reporting that they were not pregnant or had recent menstrual bleeding. DISCUSSION: Hysterosalpingography is contraindicated in pregnancy, yet we identified 10 unsuspected pregnancies in patients who would have otherwise undergone HSG examinations with existing guidelines. While there remains insufficient data on the deleterious effects of performing HSG on an unsuspected pregnancy, the potential physical, economical, and psychosocial consequences of performing an HSG during pregnancy are sufficient to merit consideration of relatively inexpensive routine pregnancy screening prior to HSG.

Percutaneous CT-guided epidural fibrin sealant injection for refractory pediatric post-dural puncture headache.

Post-dural puncture headache is an uncommon entity in young children and adolescents. Percutaneous epidural blood patching has been classically used to manage refractory post-dural puncture headaches. Injectable fibrin sealant has been shown in a few adult cases to relieve symptoms where blood patching has either failed or was not appropriate. We report a 10-year-old boy who experienced rapid relief of post-dural puncture headache symptoms following percutaneous lumbar epidural fibrin sealant injection under computed tomography guidance. Percutaneous epidural fibrin sealant injection may be an acceptable treatment for post-dural puncture headaches refractory to epidural blood patching, or when an epidural blood patch is otherwise contraindicated. The pediatric interventional radiologist should be aware of this off-label use of fibrin sealant.

Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis.

Artificial intelligence (AI) systems for computer-aided diagnosis and image-based screening are being adopted worldwide by medical institutions. In such a context, generating fair and unbiased classifiers becomes of paramount importance. The research community of medical image computing is making great efforts in developing more accurate algorithms to assist medical doctors in the difficult task of disease diagnosis. However, little attention is paid to the way databases are collected and how this may influence the performance of AI systems. Our study sheds light on the importance of gender balance in medical imaging datasets used to train AI systems for computer-assisted diagnosis. We provide empirical evidence supported by a large-scale study, based on three deep neural network architectures and two well-known publicly available X-ray image datasets used to diagnose various thoracic diseases under different gender imbalance conditions. We found a consistent decrease in performance for underrepresented genders when a minimum balance is not fulfilled. This raises the alarm for national agencies in charge of regulating and approving computer-assisted diagnosis systems, which should include explicit gender balance and diversity recommendations. We also establish an open problem for the academic medical image computing community which needs to be addressed by novel algorithms endowed with robustness to gender imbalance.

Erratum to "A feasibility study of a complete low-cost consumer-grade brain-computer interface system" [Heliyon 6 (3) (March 2020) e03425].

[This corrects the article DOI: 10.1016/j.heliyon.2020.e03425.].

A feasibility study of a complete low-cost consumer-grade brain-computer interface system.

Brain-computer interfaces (BCIs) are technologies that provide the user with an alternative way of communication. A BCI measures brain activity (e.g. EEG) and converts it into output commands. Motor imagery (MI), the mental simulation of movements, can be used as a BCI paradigm, where the movement intention of the user can be translated into a real movement, helping patients in motor recovery rehabilitation. One of the main limitations for the broad use of such devices is the high cost associated with the high-quality equipment used for capturing the biomedical signals. Different low-cost consumer-grade alternatives have emerged with the objective of bringing these systems closer to the final users. The quality of the signals obtained with such equipments has already been evaluated and found to be competitive with those obtained with well-known clinical-grade devices. However, how these consumer-grade technologies can be integrated and used for practical MI-BCIs has not yet been explored. In this work, we provide a detailed description of the advantages and disadvantages of using OpenBCI boards, low-cost sensors and open-source software for constructing an entirely consumer-grade MI-BCI system. An analysis of the quality of the signals acquired and the MI detection ability is performed. Even though communication between the computer and the OpenBCI board is not always stable and the signal quality is sometimes affected by ambient noise, we find that by means of a filter-bank based method, similar classification performances can be achieved with an MI-BCI built under low-cost consumer-grade devices as compared to when clinical-grade systems are used. By means of this work we share with the BCI community our experience on working with emerging low-cost technologies, providing evidence that an entirely low-cost MI-BCI can be built. We believe that if communication stability and artifact rejection are improved, these technologies will become a valuable alternative to clinical-grade devices.

A penalized time-frequency band feature selection and classification procedure for improved motor intention decoding in multichannel EEG.

OBJECTIVE: Motor imagery brain-computer interfaces (MI-BCIs) based on electroencephalography (EEG), a promising technology to provide assistance and support rehabilitation of neurological patients with sensorimotor impairments, require a reliable and adaptable subject-specific model to efficiently decode motor intention. The most popular EEG feature extraction algorithm for MI-BCIs is the common spatial patterns (CSP) method, but its performance strongly depends on the predefined frequency band and time segment length for analyzing the EEG signal. APPROACH: In this work, a novel method for efficiently decoding motor intention for EEG-based BCIs performing multiple frequency band analysis in multiple EEG segments is presented. This decoding algorithm uses raw multichannel EEG data which are decomposed into specific [Formula: see text] temporal and [Formula: see text] frequency bands. Features are extracted at each [Formula: see text]-[Formula: see text] band by using CSP. Feature selection and classification are simultaneously performed by means of a fast procedure, based on elastic-net regression, which allows for the inclusion of a priori discriminative information into the model. The effectiveness of the proposed method is tested off-line on two public EEG-based MI-BCI datasets and on a self-acquired dataset in two configurations: multiple temporal windows and single temporal window. MAIN RESULTS: The experimental results show that the proposed multiple time-frequency band method yields overall accuracy improvements of up to [Formula: see text] (average accuracy of 84.8%) as compared to the best current state-of-the-art methods based on filter bank analysis and CSP for MI detection. Also, classification variability is reduced, making the proposed method more robust to intra-subject EEG fluctuations. SIGNIFICANCE: This paper presents a novel approach for improving motor intention detection by automatically selecting subject-specific spatio-temporal-spectral features, especially when MI has to be detected against rest condition. This technique contributes to the further advancement and application of EEG-based MI-BCIs for assistance and neurorehabilitation therapy.