Neural Spike Sorting Research Articles

A fully automatic multichannel neural spike sorting algorithm with spike reduction and positional feature.

Objective: The sorting of neural spike data recorded by multichannel and high channel neural probes such as Neuropixels, especially in real-time, remains a significant technical challenge. Most neural spike sorting algorithms focus on sorting neural spikes post-hoc for high sorting accuracy-but reducing the processing delay for fast sorting, potentially even live sorting, is generally not possible with these algorithms.Approach: Here we report our Graph nEtwork Multichannel sorting (GEMsort) algorithm, which is largely based on graph network, to allow rapid neural spike sorting for multiple neural recording channels. This was accomplished by two innovations: In GEMsort, duplicated neural spikes recorded from multiple channels were eliminated from duplicate channels by only selecting the highest amplitude neural spike in any channel for subsequent processing. In addition, the channel from which the representative neural spike was recorded was used as an additional feature to differentiate between neural spikes recorded from different neurons having similar temporal features.Main results: Synthetic and experimentally recorded multichannel neural recordings were used to evaluate the sorting performance of GEMsort. The sorting results of GEMsort were also compared with two other state-of-the-art sorting algorithms (Kilosort and Mountainsort) in sorting time and sorting agreements.Significance: GEMsort allows rapidly sort neural spikes and is highly suitable to be implemented with digital circuitry for high processing speed and channel scalability.

68-channel neural signal processing system-on-chip with integrated feature extraction, compression, and hardware accelerators for neuroprosthetics in 22 nm FDSOI.

Multi-channel electrophysiology systems for recording of neuronal activity face significant data throughput limitations, hampering real-time, data-informed experiments. These limitations impact both experimental neurobiology research and next-generation neuroprosthetics. We present a novel solution that leverages the high integration density of 22nm fully-depleted silicon-on-insulator technology to address these challenges. The proposed highly integrated programmable System-on-Chip (SoC) comprises 68-channel 0.41 μW/Ch recording frontends, spike detectors, 16-channel 0.87-4.39 μW/Ch action potentials and 8-channel 0.32 μW/Ch local field potential codecs, as well as a multiply-accumulate-assisted power-efficient processor operating at 25 MHz (5.19 μW/MHz). The system supports on-chip training processes for compression, training, and inference for neural spike sorting. The spike sorting achieves an average accuracy of 91.48 or 94.12% depending on the utilized features. The proposed programmable SoC is optimized for reduced area (9 mm2) and power. On-chip processing and compression capabilities free up the data bottlenecks in data transmission (up to 91% space saving ratio), and moreover enable a fully autonomous yet flexible processor-driven operation. Combined, these design considerations overcome data-bottlenecks by allowing on-chip feature extraction and subsequent compression.

A Deep Neural Network-Based Spike Sorting With Improved Channel Selection and Artefact Removal

In order to implement highly efficient brain-machine interface (BMI) systems, high-channel count sensing is often used to record extracellular action potentials. However, the extracellular recordings are typically severely contaminated by artefacts and various noise sources, rendering the separation of multi-unit neural recordings an immensely challenging task. Removing artefact and noise from neural events can improve the spike sorting performance and classification accuracy. This paper presents a deep learning technique called deep spike detection (DSD) with a strong learning ability of high-dimensional vectors for neural channel selection and artefacts removal from the selected neural channel. The proposed method significantly improves spike detection compared to the conventional methods by sequentially diminishing the noise level and discarding the active artefacts in the recording channels. The simulated and experimental results show that there is considerably better performance when the extracellular raw recordings are cleaned prior to assigning individual spikes to the neurons that generated them. The DSD achieves an overall classification accuracy of 91.53% and outperformes Wave_clus by 3.38% on the simulated dataset with various noise levels and artefacts.

Partially binarized neural networks for efficient spike sorting.

While brain-implantable neural spike sorting can be realized using efficient algorithms, the presence of noise may make it difficult to maintain high-peformance sorting using conventional techniques. In this article, we explore the use of partially binarized neural networks (PBNNs), to the best of our knowledge for the first time, for sorting of neural spike feature vectors. It is shown that compared to the waveform template-based methods, PBNNs offer robust spike sorting over various datasets and noise levels. The ASIC implementation of the PBNN-based spike sorting system in a standard 180-nm CMOS process is presented. The post place and route simulations results show that the synthesized PBNN consumes only 0.59 W of power from a 1.8 V supply while operating at 24 kHz and occupies 0.15 mm of silicon area. It is shown that the designed PBNN-based spike sorting system not only offers comparable accuracy to the state-of-the-art spike sorting systems over various noise levels and datasets, it also occupies a smaller silicon area and consumes less power and energy. This makes PBNNs a viable alternative towards the implementation of brain-implantable spike sorting systems.

Objective evaluation of stimulation artefact removal techniques in the context of neural spike sorting

Objective. We present a framework to objectively test and compare stimulation artefact removal techniques in the context of neural spike sorting. Approach. To this end, we used realistic hybrid ground-truth spiking data, with superimposed artefacts from in vivo recordings. We used the framework to evaluate and compare several techniques: blanking, template subtraction by averaging, linear regression, and a multi-channel Wiener filter (MWF). Main results. Our study demonstrates that blanking and template subtraction result in a poorer spike sorting performance than linear regression and MWF, while the latter two perform similarly. Finally, to validate the conclusions found from the hybrid evaluation framework, we also performed a qualitative analysis on in vivo recordings without artificial manipulations. Significance. Our framework allows direct quantification of the impact of the residual artefact on the spike sorting accuracy, thereby allowing for a more objective and more relevant comparison compared to indirect signal quality metrics that are estimated from the signal statistics. Furthermore, the availability of a ground truth in the form of single-unit spiking activity also facilitates a better estimation of such signal quality metrics.

Multichannel Many-Class Real-Time Neural Spike Sorting With Convolutional Neural Networks

Multichannel Many-Class Real-Time Neural Spike Sorting With Convolutional Neural Networks

Characteristic of Neural Signal Feature for Spike Sorting and Detection

Neural spike plays an important role in understanding brain activities, and in neural spike sorting, the features of signal are of great importance. This paper aims to have a review on features used to discriminate different originated spikes. The features are divided into three categories: features in the time domain, features in the transformation domain, and features of dimensional reduction. For each kind of feature, the basic principle, advantages, and disadvantages are described and discussed. Results showed that features in the time domain are suitable for on-chip or real-time spike sorting, while features in the transformation domain can be used in offline spike sorting aiming at high performance. For features of dimensional reduction, it makes a large number of features available in spike sorting. In conclusion, researchers need to determine features by balancing the minimization of calculation complexity and maximizing sorting performance according to different occasions and demands. Expectations are also made for future directions of spike feature studies. The article may guide both the physiologists who want to determine features in neural spike sorting and researchers who want to work on feature extracting algorithms further to achieve better performance in experimental challenges.

Efficient neural spike sorting using data subdivision and unification.

Neural spike sorting is prerequisite to deciphering useful information from electrophysiological data recorded from the brain, in vitro and/or in vivo. Significant advancements in nanotechnology and nanofabrication has enabled neuroscientists and engineers to capture the electrophysiological activities of the brain at very high resolution, data rate and fidelity. However, the evolution in spike sorting algorithms to deal with the aforementioned technological advancement and capability to quantify higher density data sets is somewhat limited. Both supervised and unsupervised clustering algorithms do perform well when the data to quantify is small, however, their efficiency degrades with the increase in the data size in terms of processing time and quality of spike clusters being formed. This makes neural spike sorting an inefficient process to deal with large and dense electrophysiological data recorded from brain. The presented work aims to address this challenge by providing a novel data pre-processing framework, which can enhance the efficiency of the conventional spike sorting algorithms significantly. The proposed framework is validated by applying on ten widely used algorithms and six large feature sets. Feature sets are calculated by employing PCA and Haar wavelet features on three widely adopted large electrophysiological datasets for consistency during the clustering process. A MATLAB software of the proposed mechanism is also developed and provided to assist the researchers, active in this domain.

Neural Spike Sorting Using Binarized Neural Networks

This article presents the design and efficient hardware implementation of binarized neural networks (BNNs) for brain-implantable neural spike sorting. In contrast to the conventional artificial neural networks (ANNs), in which the weights and activation functions of neurons are represented using real values, the BNNs utilize binarized weights and activation functions to dramatically reduce the memory requirement and computational complexity of the ANNs. The designed BNN is trained using several realistic neural datasets to verify its accuracy for neural spike sorting. The application-specific integrated circuit (ASIC) implementation of the designed BNN in a standard 0.18- [Formula: see text] CMOS process occupies 0.33 mm 2 of silicon area. Power consumption estimation of the ASIC layout shows that the BNN dissipates [Formula: see text] of power from a 1.8 V supply while operating at 24 kHz. The designed BNN-based spike sorting system is also implemented on a field-programmable gate array and is shown to reduce the required on-chip memory by 89% compared to those of the alternative state-of-the-art spike sorting systems. To the best of our knowledge, this is the first work employing BNNs for real-time in vivo neural spike sorting.

Neural Spike Sorting And Classification

Spike sorting is the process of separating the extracellular recording of the brain signal into one unit activity. There are a number of proposed algorithms for this purpose, but there is still no acceptable solution. In this paper a spike sorting method has been proposed based on the Euclidean distance of the most effective features of spikes represented by principle components (PCs) of the detected and aligned spikes. The assessments of the method, based on signal-to-noise ratio (SNR) representing background noise, showed that the method performed spike sorting to a high level of accuracy.

Parallel architecture to accelerate superparamagnetic clustering algorithm

Superparamagnetic clustering (SPC) is an unsupervised classification technique in which clusters are self-organised based on data density and mutual interaction energy. Traditional SPC algorithm uses the Swendsen–Wang Monte Carlo approximation technique to significantly reduce the search space for reasonable clustering. However, Swendsen–Wang approximation is a Markov process which limits the conventional superparamagnetic technique to process data clustering in a sequential manner. Here the authors propose a parallel approach to replace the conventional appropriation to allow the algorithm to perform clustering in parallel. One synthetic and one open-source dataset were used to validate the accuracy of this parallel approach in which comparable clustering results were obtained as compared to the conventional implementation. The parallel method has an increase of clustering speed at least 8.7 times over the conventional approach, and the larger the sample size, the more increase in speed was observed. This can be explained by the higher degree of parallelism utilised for the increased data points. In addition, a hardware architecture was proposed to implement the parallel superparamagnetic algorithm using digital electronic technologies suitable for rapid or real-time neural spike sorting.

Compatibility Evaluation of Clustering Algorithms for Contemporary Extracellular Neural Spike Sorting.

Deciphering useful information from electrophysiological data recorded from the brain, in-vivo or in-vitro, is dependent on the capability to analyse spike patterns efficiently and accurately. The spike analysis mechanisms are heavily reliant on the clustering algorithms that enable separation of spike trends based on their spatio-temporal behaviors. Literature review report several clustering algorithms over decades focused on different applications. Although spike analysis algorithms employ only a small subset of clustering algorithms, however, not much work has been reported on the compliance and suitability of such clustering algorithms for spike analysis. In our study, we have attempted to comment on the suitability of available clustering algorithms and performance capacity when exposed to spike analysis. In this regard, the study reports a compatibility evaluation on algorithms previously employed in spike sorting as well as the algorithms yet to be investigated for application in sorting neural spikes. The performance of the algorithms is compared in terms of their accuracy, confusion matrix and accepted validation indices. Three data sets comprising of easy, difficult, and real spike similarity with known ground-truth are chosen for assessment, ensuring a uniform testbed. The procedure also employs two feature-sets, principal component analysis and wavelets. The report also presents a statistical score scheme to evaluate the performance individually and overall. The open nature of the data sets, the clustering algorithms and the evaluation criteria make the proposed evaluation framework widely accessible to the research community. We believe that the study presents a reference guide for emerging neuroscientists to select the most suitable algorithms for their spike analysis requirements.

Multi-Pattern Recognition Through Maximization of Signal-to-Peak-Interference Ratio With Application to Neural Spike Sorting

In this paper, we propose three novel linear filter design methods for use in a multi-pattern recognition task with overlapping patterns and strong peak interferers. The recognition is based on a linear filter-and-threshold approach, which is particularly interesting when the task has to be performed in a computationally constrained environment. The first method optimizes the signal-to-peak-interference ratio (SPIR) of the filter output, where the focus is on minimization of the post-filtering peak interference instead of the pre-filtering peak interference as in existing methods. The second and third method are convex approximations of the first method and are shown to be closely related to support vector machines, which establishes a natural link between SPIR-optimal filtering and the maximum margin matched filter. The proposed methods only require a template of the target patterns as prior knowledge and do not require the training data to be labelled. An extensive case study is presented in the context of neural spike sorting, in which the proposed approaches are shown to significantly outperform existing filter-and-threshold approaches for spike sorting.

Low-latency single channel real-time neural spike sorting system based on template matching.

Recent technical advancements in neural engineering allow for precise recording and control of neural circuits simultaneously, opening up new opportunities for closed-loop neural control. In this work, a rapid spike sorting system was developed based on template matching to rapidly calculate instantaneous firing rates for each neuron in a multi-unit extracellular recording setting. Cluster templates were first generated by a desktop computer using a non-parameter spike sorting algorithm (Super-paramagnetic clustering) and then transferred to a field-programmable gate array digital circuit for rapid sorting through template matching. Two different matching techniques–Euclidean distance (ED) and correlational matching (CM)–were compared for the accuracy of sorting and the performance of calculating firing rates. The performance of the system was first verified using publicly available artificial data and was further confirmed with pre-recorded neural spikes from an anesthetized Mongolian gerbil. Real-time recording and sorting from an awake mouse were also conducted to confirm the system performance in a typical behavioral neuroscience experimental setting. Experimental results indicated that high sorting accuracies were achieved for both template-matching methods, but CM can better handle spikes with non-Gaussian spike distributions, making it more robust for in vivo recording. The technique was also compared to several other off-line spike sorting algorithms and the results indicated that the sorting accuracy is comparable but sorting time is significantly shorter than these other techniques. A low sorting latency of under 2 ms and a maximum spike sorting rate of 941 spikes/second have been achieved with our hybrid hardware/software system. The low sorting latency and fast sorting rate allow future system developments of neural circuit modulation through analyzing neural activities in real-time.

Computationally efficient fully-automatic online neural spike detection and sorting in presence of multi-unit activity for implantable circuits

BackgroundSpike sorting is a basic step for implantable neural interfaces. With the growing number of channels, the process should be computationally efficient, automatic,robust and applicable on implantable circuits. New MethodThe proposed method is a combination of fully-automatic offline and online processes. It introduces a novel method for automatically determining a data-aware spike detection threshold, computationally efficient spike feature extraction, automatic optimal cluster number evaluation and verification coupled with Self-Organizing Maps to accurately determine cluster centroids. The system has the ability of unsupervised online operation after initial fully-automatic offline training. The prime focus of this paper is to fully-automate the complete spike detection and sorting pipeline, while keeping the accuracy high. ResultsThe proposed system is simulated on two well-known datasets. The automatic threshold improves detection accuracies significantly( > 15%) as compared to the most common detector. The system is able to effectively handle background multi-unit activity with improved performance. ComparisonMost of the existing methods are not fully-automatic; they require supervision and expert intervention at various stages of the pipeline. Secondly, existing works focus on foreground neural activity. Recent research has highlighted importance of background multi-unit activity, and this work is amongst the first efforts that proposes and verifies an automatic methodology to effectively handle them as well. ConclusionThis paper proposes a fully-automatic, computationally efficient system for spike sorting for both single-unit and multi-unit spikes. Although the scope of this work is design and verification through computer simulations, the system has been designed to be easily transferable into an integrated hardware form.

Smart, Secure, Yet Energy-Efficient, Internet-of-Things Sensors

The proliferation of Internet-of-Things (IoT) has led to the generation of zettabytes of sensitive data each year. The generated data are usually raw, requiring cloud resources for processing and decision-making operations to extract valuable information (i.e., distill smartness). Use of cloud resources raises serious design issues: limited bandwidth, insufficient energy, and security concerns. Edge-side computing and cryptographic techniques have been proposed to get around these problems. However, as a result of increased computational load and energy consumption, it is difficult to simultaneously achieve smartness, security, and energy efficiency. We propose a novel way out of this predicament by employing signal compression and machine learning inference on the IoT sensor node. An important sensor operation scenario is for the sensor to transmit data to the base station immediately when an event of interest occurs, e.g., arrhythmia is detected by a smart electrocardiogram sensor or seizure is detected by a smart electroencephalogram sensor, and transmit data on a less urgent basis otherwise. Since on-sensor compression and inference drastically reduce the amount of data that need to be transmitted, we actually end up with a dramatic energy bonus relative to the traditional sense-and-transmit IoT sensor. We use a part of this energy bonus to carry out encryption and hashing to ensure data confidentiality and integrity. We analyze the effectiveness of this approach on six different IoT applications with two data transmission scenarios: alert notification and continuous notification. The experimental results indicate that relative to the traditional sense-and-transmit sensor, IoT sensor energy is reduced by $57.1\times$ for electrocardiogram (ECG) sensor based arrhythmia detection, $379.8\times$ for freezing of gait detection in the context of Parkinson's disease, $139.7\times$ for electroencephalogram (EEG) sensor based seizure detection, $216.6\times$ for human activity classification, $162.8\times$ for neural prosthesis spike sorting, and $912.6\times$ for chemical gas classification. Our approach not only enables the IoT system to push signal processing and decision-making to the extreme of the edge-side (i.e., the sensor node), but also solves data security and energy efficiency problems simultaneously.

Sparse Coding and Compressive Sensing for Overlapping Neural Spike Sorting.

Spike sorting is one of the key techniques to understand brain activity. With the development of modern electrophysiology technology, some recent multi-electrode technologies have been able to record the activity of thousands of neuronal spikes simultaneously. In this scenario, however, the recorded activity may be the overlap of multi-neuron spikes, which will degrade the sorting performance of existing cluster-based algorithms. In this paper, we introduce methods for overlapping spike sorting. The introduced methods start from a convolution model, where a sparse vector could be obtained via sparse coding or compressive sensing. Then, we use a maximum a posteriori estimate to optimize the sparse vector, which makes the overlapped spike sorting completed successfully. The advantage of the introduced method is that it performs better than traditional methods when the waveforms of the spikes are similar. In experiments, some synthetic and real spike data are used to testify the methods. The experiment results show that the introduced methods' average sorting detection, defined as the ratio of successfully sorted spikes to the total spikes is nearly 4% higher than the traditional methods, under the condition of the experimental data with similar waveforms.

An Unsupervised Compressed Sensing Algorithm for Multi-Channel Neural Recording and Spike Sorting.

We propose an unsupervised compressed sensing (CS)-based framework to compress, recover, and cluster neural action potentials. This framework can be easily integrated into high-density multi-electrode neural recording VLSI systems. Embedding spectral clustering and group structures in dictionary learning, we extend the proposed framework to unsupervised spike sorting without prior label information. Additionally, we incorporate group sparsity concepts in the dictionary learning to enable the framework for multi-channel neural recordings, as in tetrodes. To further improve spike sorting success rates in the CS framework, we embed template matching in sparse coding to jointly predict clusters of spikes. Our experimental results demonstrate that the proposed CS-based framework can achieve a high compression ratio (8:1 to 20:1), with a high quality reconstruction performance (>8 dB) and a high spike sorting accuracy (>90%).

S184. Sparse representation and classification of neural spikes using supervised dictionary learning

Neural spike sorting is curial for neuroscience applications. For example, spike sorting allows designing of efficient human-computer interfaces. Therefore, many investigations, aiming for accurate computer-aided algorithms for spike detection and classification, have emerged. However, many of the available algorithms require human intervention during the classification step. This study proposes decomposition and classification of spike waveforms using dictionary learning. In sparse decomposition, each spike is represented as a unique sparse combination of the dictionary basis vectors. This can lead to interesting sorting performance. Spiking activity was detected using amplitude thresholding and a 2.5-ms window around the peak value. Under the assumption that each neuron has a consistent waveform, the dictionary atoms were learned using training samples. This learned dictionary was used to get a sparse code representation for the test samples. These codes can be used to reconstruct the original spikes and therefore it provides data compression capability. Classification of the neural spikes was done using the sparse coefficients alongside with the reconstruction error. To ensure high discrimination, the dictionary was learned such that the resultant atoms have correspondence to class labels. In other words, the dictionary is structured of sub-dictionaries each corresponds to a different spiking pattern. Subsequently, an optimization problem was solved to make sure that (i) the sub-dictionaries accurately represent the training data, and (ii) the coding coefficients are sparse and minimize the reconstruction error. A testing sample was classified by sparsely coding it over each sub-dictionary. The reconstruction error for each sub-dictionary is computed. An error function is defined for each class as the summation of the reconstruction error and the difference between the sparse code and that class average. The testing sample was assigned to the class that gave the minimum error. The algorithm was tested on four simulated data sets, each contains spiking activities from three different neurons. Approximately 10% of each class data was used to construct the dictionary. The reconstruction mean-squared error for all the training samples was 3.49. This confirms the reconstruction power and accuracy of the learned dictionary. We measured the accuracy of our algorithm at different noise levels. The classification accuracy of the proposed method is 97% ± 5%. This accuracy outperforms the existing state-of-the-art algorithms. A dictionary learning based spike sorting algorithm has been developed. The results suggest that dictionary-based representation enables us to use the sparse representation of signals without a severe loss of data; besides that, this sparse representation can be also used for classification. This could also enable estimation of missing data points or clipped signals. The reconstruction error can be used to efficiently sort spikes.

Event-driven processing for hardware-efficient neural spike sorting

Objective. The prospect of real-time and on-node spike sorting provides a genuine opportunity to push the envelope of large-scale integrated neural recording systems. In such systems the hardware resources, power requirements and data bandwidth increase linearly with channel count. Event-based (or data-driven) processing can provide here a new efficient means for hardware implementation that is completely activity dependant. In this work, we investigate using continuous-time level-crossing sampling for efficient data representation and subsequent spike processing. Approach. (1) We first compare signals (synthetic neural datasets) encoded with this technique against conventional sampling. (2) We then show how such a representation can be directly exploited by extracting simple time domain features from the bitstream to perform neural spike sorting. (3) The proposed method is implemented in a low power FPGA platform to demonstrate its hardware viability. Main results. It is observed that considerably lower data rates are achievable when using 7 bits or less to represent the signals, whilst maintaining the signal fidelity. Results obtained using both MATLAB and reconfigurable logic hardware (FPGA) indicate that feature extraction and spike sorting accuracies can be achieved with comparable or better accuracy than reference methods whilst also requiring relatively low hardware resources. Significance. By effectively exploiting continuous-time data representation, neural signal processing can be achieved in a completely event-driven manner, reducing both the required resources (memory, complexity) and computations (operations). This will see future large-scale neural systems integrating on-node processing in real-time hardware.