Neural interfaces advance neuroscience research and therapeutic innovations by accurately measuring neuronal activity. However, recording raw data from numerous neurons results in substantial amount of data and poses challenges for wireless transmission. While conventional neural recorders consume energy to digitize and process the full neural signal, only a fraction of this data carries essential spiking information. Leveraging on this signal sparsity, this paper introduces a neural recording integrated circuit in TSMC 28nm CMOS. It features an event-driven ramp analog-to-digital converter, and a spike compression module based on principal component analysis. The circuit consists of 49 channels, each occupying an on-chip area of 50 $\times$ 60 $\mu$m$^2$. The circuit measures 1370 $\times$ 1370 $\mu$m$^2$ and consumes 534 $\mu$W. Compression testing on a synthetic dataset demonstrated an 8.8-fold reduction compared to raw spikes and a 328-fold reduction relative to the raw signal. This compression approach maintained a spike sorting accuracy of 74.9%, compared to the 79.5% accuracy obtained with the raw signal. The paper details the architecture and performance outcomes of the neural recording circuit and its compression module.
Spike sorting is a valuable tool in understanding brain regions. It assigns detected spike waveforms to their origins, helping to research the mechanism of the human brain and the development of implantable brain-machine interfaces (iBMIs). The presence of noise and artefacts will adversely affect the efficacy of spike sorting. This paper proposes a framework for low-cost and real-time implementation of deep spike detection, which consists of two one-dimensional (1-D) convolutional neural network (CNN) model for channel selection and artefact removal. The framework utilizes simulation and hardware layers, and it applies several low-power techniques to optimise the implementation cost of a 1-D CNN model. A compact CNN model with 210 bytes memory size is achieved using structured pruning, network projection and quantization in the simulation layer. The hardware layer also accommodates various techniques including a customized multiply-accumulate (MAC) engine, novel fused layers in the convolution pipeline and proposing flexible resource allocation for a power-efficient and low-delay design. The optimized 1-D CNN significantly decreases both computational complexity and model size, with only a minimal reduction in accuracy. Classification of 1-D CNN on the Cyclone V 5CSEMA5F31C6 FPGA evaluation platform is accomplished in just 16.8 microseconds at a frequency of 2.5 MHz. The FPGA prototype achieves an accuracy rate of 97.14% on a standard dataset and operates with a power consumption of 2.67mW from a supply voltage of 1.1 volts. An accuracy of 95.05% is achieved with a power of 5.6mW when deep spike detection is implemented using two optimized 1-D CNNs on an FPGA board.
Objective: Spike sorting is a fundamental step in analysing extracellular recordings, enabling the isolation of single-neuron activity. However, it remains a challenging problem because extracellular traces mix overlapping spikes from neighbouring cells and are marred by recording instabilities such as electrode drift. Numerous algorithms have been proposed, yet many struggle to balance accuracy and computational efficiency, limiting their practicality for todays large-scale datasets. Approach: In response, we introduce SpikeSift, a spike-sorting algorithm expressly designed to mitigate drift while running on standard CPUs. SpikeSift (i) partitions long recordings into shorter, relatively stationary segments, (ii) carries out spike detection and clustering simultaneously through an iterative detect-and-subtract scheme within each segment, and (iii) preserves neuronal identity across segments via a fast template alignment stage that dispenses with continuous trajectory estimation. Main results: Extensive validation on paired intracellularly validated datasets and on biophysically realistic MEArec simulations covering elevated noise, diverse drift profiles, ultra short recordings and bursting activity, demonstrates that SpikeSift matches or exceeds the accuracy of state of the art methods while completing sorting an order of magnitude faster on a single desktop core. Significance: The combination of high fidelity, drift resilience, and modest computational demand renders SpikeSift broadly accessible while preserving data quality for downstream neurophysiological analysis
There is a need for fast adaptation in spike sorting algorithms to implement brain-machine interface (BMIs) in different applications. Learning and adapting the functionality of the sorting process in real-time can significantly improve the performance. However, deep neural networks (DNNs) depend on large amounts of data for training models and their performance sustainability decreases when data is limited. Inspired by meta-learning, this paper proposes a few-shot spike sorting framework (FS-SS) with variable network model size that requires minimal learning training and supervision. The framework is not only compatible with few-shot adaptations, but also it uses attention mechanism and dilated convolutional neural networks. This allows scaling the network parameters to learn the important features of spike signals and to quickly generalize the learning ability to new spike waveforms in recording channels after few observations. The FS-SS was evaluated by using freely accessible datasets, also compared with the other state-of-the-art algorithms. The average classification accuracy of the proposed method is 99.28%, which shows extreme robustness to background noise and similarity of the spike waveforms. When the number of training samples is reduced by 90%, the parameter scale is reduced by 68.2%, while the accuracy only decreased by 0.55%. The paper also visualizes the model's attention distribution under spike sorting tasks of different difficulty levels. The attention distribution results show that the proposed model has clear interpretability and high robustness.
The detection of irregularly spaced pulses of non-negligible width is a fascinating yet under-explored topic in signal processing. It sits adjacent to other core topics such as radar and symbol detection yet has its own distinctive challenges. Even modern techniques such as compressed sensing perform worse than may be expected on pulse processing problems. Real-world applications include nuclear spectroscopy, flow cytometry, seismic signal processing and neural spike sorting, and these in turn have applications to environmental radiation monitoring, surveying, diagnostic medicine, industrial imaging, biomedical imaging, top-down proteomics, and security screening, to name just a few. This overview paper endeavours to position the pulse processing problem in the context of signal processing. It also describes some current challenges in the field.
Spike sorting is an essential process in neural recording, which identifies and separates electrical signals from individual neurons recorded by electrodes in the brain, enabling researchers to study how specific neurons communicate and process information. Although there exist a number of spike sorting methods which have contributed to significant neuroscientific breakthroughs, many are heuristically designed, making it challenging to verify their correctness due to the difficulty of obtaining ground truth labels from real-world neural recordings. In this work, we explore a data-driven, deep learning-based approach. We begin by creating a large-scale dataset through electrophysiology simulations using biologically realistic computational models. We then present SimSort, a pretraining framework for spike sorting. Trained solely on simulated data, SimSort demonstrates zero-shot generalizability to real-world spike sorting tasks, yielding consistent improvements over existing methods across multiple benchmarks. These results highlight the potential of simulation-driven pretraining to enhance the robustness and scalability of spike sorting in experimental neuroscience.
Spike sorting is a critical process for decoding large-scale neural activity from extracellular recordings. The advancement of neural probes facilitates the recording of a high number of neurons with an increase in channel counts, arising a higher data volume and challenging the current on-chip spike sorters. This paper introduces L-Sort, a novel on-chip spike sorting solution featuring median-of-median spike detection and localization-based clustering. By combining the median-of-median approximation and the proposed incremental median calculation scheme, our detection module achieves a reduction in memory consumption. Moreover, the localization-based clustering utilizes geometric features instead of morphological features, thus eliminating the memory-consuming buffer for containing the spike waveform during feature extraction. Evaluation using Neuropixels datasets demonstrates that L-Sort achieves competitive sorting accuracy with reduced hardware resource consumption. Implementations on FPGA and ASIC (180 nm technology) demonstrate significant improvements in area and power efficiency compared to state-of-the-art designs while maintaining comparable accuracy. If normalized to 22 nm technology, our design can achieve roughly $\times 10$ area and power efficiency with similar accuracy, compared with the state-of-the-art design evaluated with the same dataset. Therefore, L-Sort is a promising solution for real-time, high-channel-count neural processing in implantable devices.
We tackle a quantification of synchrony in a large ensemble of interacting neurons from the observation of spiking events. In a simulation study, we efficiently infer the synchrony level in a neuronal population from a point process reflecting spiking of a small number of units and even from a single neuron. We introduce a synchrony measure (order parameter) based on the Bartlett covariance density; this quantity can be easily computed from the recorded point process. This measure is robust concerning missed spikes and, if computed from observing several neurons, does not require spike sorting. We illustrate the approach by modeling populations of spiking or bursting neurons, including the case of sparse synchrony.
Decoding extracellular recordings is a crucial task in electrophysiology and brain-computer interfaces. Spike sorting, which distinguishes spikes and their putative neurons from extracellular recordings, becomes computationally demanding with the increasing number of channels in modern neural probes. To address the intensive workload and complex neuron interactions, we propose E-Sort, an end-to-end neural network-based spike sorter with transfer learning and parallelizable post-processing. Our framework reduces the required number of annotated spikes for training by 44% compared to training from scratch, achieving up to 25.68% higher accuracy. Additionally, our novel post-processing algorithm is compatible with deep learning frameworks, making E-Sort significantly faster than state-of-the-art spike sorters. On synthesized Neuropixels recordings, E-Sort achieves comparable accuracy with Kilosort4 while sorting 50 seconds of data in only 1.32 seconds. Our method demonstrates robustness across various probe geometries, noise levels, and drift conditions, offering a substantial improvement in both accuracy and runtime efficiency compared to existing spike sorters.
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 FDSOI CMOS technology to address these challenges. The proposed highly integrated programmable System-on-Chip comprises 68-channel 0.41 \textmu W/Ch recording frontends, spike detectors, 16-channel 0.87-4.39 \textmu W/Ch action potential and 8-channel 0.32 \textmu W/Ch local field potential codecs, as well as a MAC-assisted power-efficient processor operating at 25 MHz (5.19 \textmu W/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 PSoC 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.
Spike sorting is essential for extracting neuronal information from neural signals and understanding brain function. With the advent of high-density microelectrode arrays (HDMEAs), the challenges and opportunities in multi-channel spike sorting have intensified. Real-time spike sorting is particularly crucial for closed-loop brain computer interface (BCI) applications, demanding efficient hardware implementations. This paper introduces L-Sort, an hardware design for real-time multi-channel spike sorting. Leveraging spike localization techniques, L-Sort achieves efficient spike detection and clustering without the need to store raw signals during detection. By incorporating median thresholding and geometric features, L-Sort demonstrates promising results in terms of accuracy and hardware efficiency. We assessed the detection and clustering accuracy of our design with publicly available datasets recorded using high-density neural probes (Neuropixel). We implemented our design on an FPGA and compared the results with state of the art. Results show that our designs consume less hardware resource comparing with other FPGA-based spike sorting hardware.
The bottom two layers of a neuromorphic architecture are designed and shown to be capable of online clustering and supervised classification. An active spiking dendrite model is used, and a single dendritic segment performs essentially the same function as a classic integrate-and-fire point neuron. A single dendrite is then composed of multiple segments and is capable of online clustering. Although this work focuses primarily on dendrite functionality, a multi-point neuron can be formed by combining multiple dendrites. To demonstrate its clustering capability, a dendrite is applied to spike sorting, an important component of brain-computer interface applications. Supervised online classification is implemented as a network composed of multiple dendrites and a simple voting mechanism. The dendrites operate independently and in parallel. The network learns in an online fashion and can adapt to macro-level changes in the input stream. Achieving brain-like capabilities, efficiencies, and adaptability will require a significantly different approach than conventional deep networks that learn via compute-intensive back propagation. The model described herein may serve as the foundation for such an approach.
Objective. Spike sorting, a critical step in neural data processing, aims to classify spiking events from single electrode recordings based on different waveforms. This study aims to develop a novel online spike sorter, NeuSort, using neuromorphic models, with the ability to adaptively adjust to changes in neural signals, including waveform deformations and the appearance of new neurons. Approach. NeuSort leverages a neuromorphic model to emulate template-matching processes. This model incorporates plasticity learning mechanisms inspired by biological neural systems, facilitating real-time adjustments to online parameters. Results. Experimental findings demonstrate NeuSort's ability to track neuron activities amidst waveform deformations and identify new neurons in real-time. NeuSort excels in handling non-stationary neural signals, significantly enhancing its applicability for long-term spike sorting tasks. Moreover, its implementation on neuromorphic chips guarantees ultra-low energy consumption during computation. Significance. NeuSort caters to the demand for real-time spike sorting in brain-machine interfaces through a neuromorphic approach. Its unsupervised, automated spike sorting process makes it a plug-and-play solution for online spike sorting.
Objective. Research on brain-computer interfaces (BCIs) is advancing towards rehabilitating severely disabled patients in the real world. Two key factors for successful decoding of user intentions are the size of implanted microelectrode arrays and a good online spike sorting algorithm. A small but dense microelectrode array with 3072 channels was recently developed for decoding user intentions. The process of spike sorting determines the spike activity (SA) of different sources (neurons) from recorded neural data. Unfortunately, current spike sorting algorithms are unable to handle the massively increasing amount of data from dense microelectrode arrays, making spike sorting a fragile component of the online BCI decoding framework. Approach. We proposed an adaptive and self-organized algorithm for online spike sorting, named Adaptive SpikeDeep-Classifier (Ada-SpikeDeepClassifier), which uses SpikeDeeptector for channel selection, an adaptive background activity rejector (Ada-BAR) for discarding background events, and an adaptive spike classifier (Ada-Spike classifier) for classifying the SA of different neural units. Results. Our algorithm outperformed our previously published SpikeDeep-Classifier and eight other spike sorting algorithms, as evaluated on a human dataset and a publicly available simulated dataset. Significance. The proposed algorithm is the first spike sorting algorithm that automatically learns the abrupt changes in the distribution of noise and SA. It is an artificial neural network-based algorithm that is well-suited for hardware implementation on neuromorphic chips that can be used for wearable invasive BCIs.
Brain Computer Interface (BCI) has great potential for solving many brain signal analysis limitations, mental disorder resolutions, and restoring missing limb functionality via neural-controlled implants. However, there is no single available, and safe implant for daily life usage exists yet. Most of the proposed implants have several implementation issues, such as infection hazards and heat dissipation, which limits their usability and makes it more challenging to pass regulations and quality control production. The wireless implant does not require a chronic wound in the skull. However, the current complex clustering neuron identification algorithms inside the implant chip consume a lot of power and bandwidth, causing higher heat dissipation issues and draining the implant's battery. The spike sorting is the core unit of an invasive BCI chip, which plays a significant role in power consumption, accuracy, and area. Therefore, in this study, we propose a low-power adaptive simplified VLSI architecture, "Zydeco-Style," for BCI spike sorting that is computationally less complex with higher accuracy that performs up to 93.5% in the worst-case scenario. The architecture uses a low-power Bluetooth Wireless communication module with external IoT medical ICU devices. The proposed architecture was implemented and simulated in Verilog. In addition, we are proposing an implant conceptual design.
Brain-computer interfaces (BCIs), is ways for electronic devices to communicate directly with the brain. For most medical-type brain-computer interface tasks, the activity of multiple units of neurons or local field potentials is sufficient for decoding. But for BCIs used in neuroscience research, it is important to separate out the activity of individual neurons. With the development of large-scale silicon technology and the increasing number of probe channels, artificially interpreting and labeling spikes is becoming increasingly impractical. In this paper, we propose a novel modeling framework: Adaptive Contrastive Learning Model that learns representations from spikes through contrastive learning based on the maximizing mutual information loss function as a theoretical basis. Based on the fact that data with similar features share the same labels whether they are multi-classified or binary-classified. With this theoretical support, we simplify the multi-classification problem into multiple binary-classification, improving both the accuracy and the runtime efficiency. Moreover, we also introduce a series of enhancements for the spikes, while solving the problem that the classification effect is affected because of the overlapping spikes.
Spike sorting algorithms are used to separate extracellular recordings of neuronal populations into single-unit spike activities. The development of customized hardware implementing spike sorting algorithms is burgeoning. However, there is a lack of a systematic approach and a set of standardized evaluation criteria to facilitate direct comparison of both software and hardware implementations. In this paper, we formalize a set of standardized criteria and a publicly available synthetic dataset entitled Synthetic Simulations Of Extracellular Recordings (SSOER), which was constructed by aggregating existing synthetic datasets with varying Signal-To-Noise Ratios (SNRs). Furthermore, we present a benchmark for future comparison, and use our criteria to evaluate a simulated Resistive Random-Access Memory (RRAM) In-Memory Computing (IMC) system using the Discrete Wavelet Transform (DWT) for feature extraction. Our system consumes approximately (per channel) 10.72mW and occupies an area of 0.66mm$^2$ in a 22nm FDSOI Complementary Metal-Oxide-Semiconductor (CMOS) process.
This paper presents a novel approximation unit added to the conventional spike processing chain which provides an appreciable reduction of complexity of the high-hardware cost feature extractors. The use of the Taylor polynomial is proposed and modelled employing its cascaded derivatives to non-uniformly capture the essential samples in each spike for reliable feature extraction and sorting. Inclusion of the approximation unit can provide 3X compression (i.e. from 66 to 22 samples) to the spike waveforms while preserving their shapes. Detailed spike waveform sequences based on in-vivo measurements have been generated using a customized neural simulator for performance assessment of the approximation unit tested on six published feature extractors. For noise levels {\sigma}_N between 0.05 and 0.3 and groups of 3 spikes in each channel, all the feature extractors provide almost same sorting performance before and after approximation. The overall implementation cost when including the approximation unit and feature extraction shows a large reduction (i.e. up to 8.7X) in the hardware costly and more accurate feature extractors, offering a substantial improvement in feature extraction design.
Extracellular recordings are severely contaminated by a considerable amount of noise sources, rendering the denoising process an extremely challenging task that should be tackled for efficient spike sorting. To this end, we propose an end-to-end deep learning approach to the problem, utilizing a Fully Convolutional Denoising Autoencoder, which learns to produce a clean neuronal activity signal from a noisy multichannel input. The experimental results on simulated data show that our proposed method can improve significantly the quality of noise-corrupted neural signals, outperforming widely-used wavelet denoising techniques.
An important prerequisite for the analysis of spike synchrony in extracellular recordings is the extraction of single unit activity from the recorded multi unit signal. To identify single units (SUs), potential spikes are detected and separated with respect to their potential neuronal origins ('spike sorting'). However, different sorting algorithms yield inconsistent unit assignments which seriously influences the subsequent analyses of the spiking activity. To evaluate the quality of spike sortings performed with different prevalent algorithms offered by the 'Plexon Offline Sorter' we first apply these algorithms to experimental data (ED), namely recordings in the Subthalamic Nucleus of patients with Parkinson's disease, obtained during Deep Brain Stimulation surgery. Since this procedure leaves us unsure about the best sorting result we then apply all methods again to artificial data (AD) with known ground truth (GT). AD consists of pairs of SUs with different shape similarity embedded in the background noise of the ED. The sorting evaluation is based on the influence of the respective methods on the SU assignments and its effect on the resulting firing characteristics. We find a high variability in the sorting results obtained by different algorithms that increases with SU shape similarity. We also find significant differences in the resulting firing characteristics of the ED. We conclude that Valley-Seeking produces the most accurate results if the exclusion of artifacts as unsorted events is important. If the latter is less important ('clean' data) K-Means is a better option. Our results strongly argue for the need of standardized validation procedures for spike sorting based on GT data. The recipe suggested here is simple enough to become a standard procedure.