Iyad Obeid

Modular particle filtering FPGA hardware architecture for brain machine interfaces

As the computational complexities of neural decoding algorithms for brain machine interfaces (BMI) increase, their implementation through sequential processors becomes prohibitive for real-time applications. This work presents the field programmable gate array (FPGA) as an alternative to sequential processors for BMIs. The reprogrammable hardware architecture of the FPGA provides a near optimal platform for performing parallel computations in real-time. The scalability and reconfigurability of the FPGA accommodates diverse sets of neural ensembles and a variety of decoding algorithms. Throughput is significantly increased by decomposing computations into independent parallel hardware modules on the FPGA. This increase in throughput is demonstrated through a parallel hardware implementation of the auxiliary particle filtering signal processing algorithm.

Understanding the temporal evolution of neuronal connectivity in cultured networks using statistical analysis

BackgroundMicro-Electrode Array (MEA) technology allows researchers to perform long-term non-invasive neuronal recordings in-vitro while actively interacting with the cultured neurons. Despite numerous studies carried out using MEAs, many functional, chemical and structural mechanisms of how dissociated cortical neurons develop and respond to external stimuli are not yet well understood because of the lack of quantitative studies that assess how their development can be affected by chronic external stimulation.MethodsTo investigate network changes, we analyzed a large MEA data set composed of neuron spikes recorded from cultures of dissociated rat cortical neurons plated on MEA dishes with 59 recording electrodes each. Neural network activity was recorded during the first five weeks of each culture’s in-vitro development. Stimulation sessions were delivered to each of the 59 electrodes. The False Discovery Rate technique was used to quantify the temporal evolution of dissociated cortical neurons. Our analysis focused on network responses that occurred within selected time window durations, namely 50 ms, 100 ms and 150 ms after stimulus onset.ResultsOur results show an evolution in dissociated cortical neuronal network activity over time, that reflects the network synaptic evolution. Furthermore, we tested the sensitivity of our technique to different observation time windows and found that varying the time windows, allows us to capture different dynamics of the observed responses. In addition, when selecting a 150 ms observation time window, our findings indicate that cultures dissociated from the same brain tissue display trends in their temporal evolution that are more similar than those obtained from different brains.ConclusionOur results emphasize that the FDR technique can be implemented without the need to make any particular assumptions about the data a priori. The proposed technique was able to capture the well-known dissociated cortical neuron networks’ temporal evolution, that has been previously observed in in-vivo and in intact brain tissue studies. Furthermore, our findings suggest that the time window that is used to capture the stimulus-evoked network responses is a critical parameter to analyze the electrical behavioral and temporal evolution of dissociated cortical neurons.

Comparative Analysis of Human and Rodent Brain Primary Neuronal Culture Spontaneous Activity Using Micro-Electrode Array Technology.

Electrical activity in embryonic brain tissue has typically been studied using Micro Electrode Array (MEA) technology to make dozens of simultaneous recordings from dissociated neuronal cultures, brain stem cell progenitors, or brain slices from fetal rodents. Although these rodent neuronal primary culture electrical properties are mostly investigated, it has not been yet established to what extent the electrical characteristics of rodent brain neuronal cultures can be generalized to those of humans. A direct comparison of spontaneous spiking activity between rodent and human primary neurons grown under the same in vitro conditions using MEA technology has never been carried out before and will be described in the present study. Human and rodent dissociated fetal brain neuronal cultures were established in‐vitro by culturing on a glass grid of 60 planar microelectrodes neurons under identical conditions. Three different cultures of human neurons were produced from tissue sourced from a single aborted fetus (at 16–18 gestational weeks) and these were compared with seven different cultures of embryonic rat neurons (at 18 gestational days) originally isolated from a single rat. The results show that the human and rodent cultures behaved significantly differently. Whereas the rodent cultures demonstrated robust spontaneous activation and network activity after only 10 days, the human cultures required nearly 40 days to achieve a substantially weaker level of electrical function. These results suggest that rat neuron preparations may yield inferences that do not necessarily transfer to humans. J. Cell. Biochem. 117: 559–565, 2016.

The Temple University Hospital EEG Data Corpus

The electroencephalogram (EEG) is an excellent tool for probing neural function, both in clinical and research environments, due to its low cost, non-invasive nature, and pervasiveness. In the clinic, the EEG is the standard test for diagnosing and characterizing epilepsy and stroke, as well as a host of other trauma and pathology related conditions (Tatum et al., 2007; Yamada and Meng, 2009). In research laboratories, EEG is used to study neural responses to external stimuli, motor planning and execution, and brain-computer interfaces (Lebedev and Nicolelis, 2006; Wang et al., 2013). While human interpretation is still the gold standard for EEG analysis in the clinic, a host of software tools exist to facilitate the process or to make predictive analyses such as seizure prediction. Recently, a confluence of events has underscored the need for robust EEG tools. First, there has been a renewed push via the White House BRAIN initiative to understand neural function and disease (Weiss, 2013). Secondly, there is an increased awareness on brain injury owing to both the influx of injured warfighters and numerous high-profile athletes found to have chronic brain damage (McKee et al., 2009; Stern et al., 2011). And thirdly, a wave of consumer grade scalp sensors has entered the market, allowing end users to monitor sleep, arousal, and mood (Liao et al., 2012). In all these applications, there is a need for robust signal processing tools to analyze the EEG data. Historically, EEG signal processing tools have been devised using either ad hoc heuristic methods, or by training pattern recognition engines on small data sets (Gotman, 1982). These methods have yielded limited results, owing mostly to the fact that brain signals (and EEG in particular) are characterized by great variability, which can only be properly interpreted by building statistical models using massive amounts of data (Alotaiby et al., 2014; Ramgopal et al., 2014). Unfortunately, despite EEG being perhaps the most pervasive modality for acquiring brain signals, there is a severe lack of data in the public domain. For example, the “EEG Motor Movement/Imagery Dataset” (http://www.physionet.org/pn4/eegmmidb/) contains ~1500 recordings of 1 or 2 min duration apiece from 109 subjects (Goldberger et al., 2000; Schalk et al., 2004). The CHB-MIT database contains data from 22 subjects, mostly pediatric (Shoeb, 2009). A database from Karunya University contains 175 16-channel EEGs of duration 10 s (Selvaraj et al., 2014). One of the most extensive databases for supporting epilepsy research is the European Epilepsy Database (http://epilepsy-database.eu/), which contains 250 datasets from 30 unique patients, but sells for €3000. Other databases, such as ieee.org, contain a wealth of data from more invasive modalities such as electrocorticogram, but little or no EEG. This lack of publically available data is ironic considering that hundreds of thousands of EEGs are administered annually in clinical settings around the world. Relatively little of this data is publicly available to the research community in a form that is useful to machine learning research. Massive amounts of EEG data would allow the use of state-of-the-art machine learning algorithms to discover new diagnostics and validate clinical practice. Furthermore, it is desirable that such data be collected in clinical settings, as opposed to tightly controlled research environments, since “clinical-grade” data is inherently more variable with respect to parameters such as electrode location, clinical environment, equipment, and noise. Capturing this variability is critical to the development of robust, high performance technology that has real-world impact. In this work, we describe a new corpus, the TUH-EEG Corpus, which is an ongoing data collection effort that has recently released 14 years of clinical EEG data collected at Temple University Hospital. The records have been curated, organized, and paired with textual clinician reports that describe the patients and scans. The corpus is publicly available from the Neural Engineering Data Consortium (www.nedcdata.org) (Picone and Obeid, 2016).

The TUH EEG CORPUS: A big data resource for automated EEG interpretation

The Neural Engineering Data Consortium (NEDC) is releasing its first major big data corpus - the Temple University Hospital EEG Corpus. This corpus consists of over 25,000 EEG studies, and includes a neurologists interpretation of the test, a brief patient medical history and demographic information about the patient such as gender and age. For the first time, there is a sufficient amount of data to support the application of state of the art machine learning algorithms. In this paper, we present pilot results of experiments on the prediction of some basic attributes of an EEG from the raw EEG signal data using a 3,762 session subset of the corpus. Standard machine learning approaches are shown to be capable of predicting commonly occurring events from simple features with high accuracy on closed-loop testing, and can deliver error rates below 50% on a 6-way open set classification problem. This is very promising performance since commercial technology fails on this data.

Reconfigurable embedded system architecture for next-generation Neural Signal Processing

This work presents a new architectural framework for next generation Neural Signal Processing (NSP). The essential features of the NSP hardware platform include scalability, reconfigurability, real-time processing ability and data storage. This proposed framework has been implemented in a proof-of-concept NSP prototype using an embedded system architecture synthesized in a Xilinx®Virtex®5 development board. The prototype includes a threshold-based spike detector and a fuzzy logic-based spike sorter.

Bayesian auxiliary particle filters for estimating neural tuning parameters

A common challenge in neural engineering is to track the dynamic parameters of neural tuning functions. This work introduces the application of Bayesian auxiliary particle filters for this purpose. Based on Monte-Carlo filtering, Bayesian auxiliary particle filters use adaptive methods to model the prior densities of the state parameters being tracked. The observations used are the neural firing times, modeled here as a Poisson process, and the biological driving signal. The Bayesian auxiliary particle filter was evaluated by simultaneously tracking the three parameters of a hippocampal place cell and compared to a stochastic state point process filter. It is shown that Bayesian auxiliary particle filters are substantially more accurate and robust than alternative methods of state parameter estimation. The effects of time-averaging on parameter estimation are also evaluated.

Improved EEG event classification using differential energy

Feature extraction for automatic classification of EEG signals typically relies on time frequency representations of the signal. Techniques such as cepstral-based filter banks or wavelets are popular analysis techniques in many signal processing applications including EEG classification. In this paper, we present a comparison of a variety of approaches to estimating and postprocessing features. To further aid in discrimination of periodic signals from aperiodic signals, we add a differential energy term. We evaluate our approaches on the TUH EEG Corpus, which is the largest publicly available EEG corpus and an exceedingly challenging task due to the clinical nature of the data. We demonstrate that a variant of a standard filter bank-based approach, coupled with first and second derivatives, provides a substantial reduction in the overall error rate. The combination of differential energy and derivatives produces a 24% absolute reduction in the error rate and improves our ability to discriminate between signal events and background noise. This relatively simple approach proves to be comparable to other popular feature extraction approaches such as wavelets, but is much more computationally efficient.

The Temple University Hospital EEG corpus

The recently established Neural Engineering Data Consortium (NEDC) is in the process of developing its first large-scale corpus. This corpus, known as the Temple University Hospital EEG Corpus, upon completion, will total over 20,000 EEG studies, and include patient information, medical histories and physician assessments, making it the largest and most comprehensive publicly released EEG corpus. For the first time, there will be sufficient data to support the application of state of the art machine learning algorithms. In this paper, we present pilot results of experiments in which we attempted to predict some basic attributes of an EEG from the raw EEG data using a pilot database of 100 EEGs. Standard machine learning approaches are shown to be capable of predicting commonly occurring events from simple features with high accuracy on closed-loop testing, and can deliver error rates slightly below 50% on a 12-way open set classification problem.

Parallel field programmable gate array particle filtering architecture for real-time neural signal processing

Both linear and nonlinear estimation algorithms have been successfully applied as neural decoding techniques in brain machine interfaces. Nonlinear approaches such as Bayesian auxiliary particle filters offer improved estimates over other methodologies seemingly at the expense of computational complexity. Real-time implementation of particle filtering algorithms for neural signal processing may become prohibitive when the number of neurons in the observed ensemble becomes large. By implementing a parallel hardware architecture, filter performance can be improved in terms of throughput over conventional sequential processing. Such an architecture is presented here and its FPGA resource utilization is reported.