1
|
Wu Y, Li BZ, Wang L, Fan S, Chen C, Li A, Lin Q, Wang P. An unsupervised real-time spike sorting system based on optimized OSort. J Neural Eng 2023; 20:066015. [PMID: 37972395 DOI: 10.1088/1741-2552/ad0d15] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2023] [Accepted: 11/15/2023] [Indexed: 11/19/2023]
Abstract
Objective. The OSort algorithm, a pivotal unsupervised spike sorting method, has been implemented in dedicated hardware devices for real-time spike sorting. However, due to the inherent complexity of neural recording environments, OSort still grapples with numerous transient cluster occurrences during the practical sorting process. This leads to substantial memory usage, heavy computational load, and complex hardware architectures, especially in noisy recordings and multi-channel systems.Approach. This study introduces an optimized OSort algorithm (opt-OSort) which utilizes correlation coefficient (CC), instead of Euclidean distance as classification criterion. TheCCmethod not only bolsters the robustness of spike classification amidst the diverse and ever-changing conditions of physiological and recording noise environments, but also can finish the entire sorting procedure within a fixed number of cluster slots, thus preventing a large number of transient clusters. Moreover, the opt-OSort incorporates two configurable validation loops to efficiently reject cluster outliers and track recording variations caused by electrode drifting in real-time.Main results. The opt-OSort significantly reduces transient cluster occurrences by two orders of magnitude and decreases memory usage by 2.5-80 times in the number of pre-allocated transient clusters compared with other hardware implementations of OSort. The opt-OSort maintains an accuracy comparable to offline OSort and other commonly-used algorithms, with a sorting time of 0.68µs as measured by the hardware-implemented system in both simulated datasets and experimental data. The opt-OSort's ability to handle variations in neural activity caused by electrode drifting is also demonstrated.Significance. These results present a rapid, precise, and robust spike sorting solution suitable for integration into low-power, portable, closed-loop neural control systems and brain-computer interfaces.
Collapse
Affiliation(s)
- Yingjiang Wu
- School of Biomedical Engineering, Guangdong Medical University, Dongguan, People's Republic of China
- Songshan Lake Innovation Center of Medicine and Engineering, Guangdong Medical University, Dongguan, People's Republic of China
- Dongguan Key Laboratory of Medical Electronics and Medical Imaging Equipment, Dongguan, People's Republic of China
| | - Ben-Zheng Li
- Department of Physiology and Biophysics, University of Colorado Anschutz Medical Campus, Aurora, CO, United States of America
- Department of Electrical Engineering, University of Colorado Denver, Denver, CO, United States of America
| | - Liyang Wang
- State Key Laboratory of Analog and Mixed Signal VLSI, University of Macau, Macau, People's Republic of China
- Department of Electrical and Computer Engineering, University of Macau, Macau, People's Republic of China
| | - Shaocan Fan
- School of Electronics and Communication Engineering, Sun Yat-sen University-Shenzhen Campus, Shenzhen, People's Republic of China
| | - Changhao Chen
- Zhuhai Hokai Medical Instruments Co., Ltd, Zhuhai, People's Republic of China
| | - Anan Li
- Jiangsu Key Laboratory of Brain Disease and Bioinformation, Research Center for Biochemistry and Molecular Biology, Xuzhou Medical University, Xuzhou, People's Republic of China
| | - Qin Lin
- School of Biomedical Engineering, Guangdong Medical University, Dongguan, People's Republic of China
- Songshan Lake Innovation Center of Medicine and Engineering, Guangdong Medical University, Dongguan, People's Republic of China
- Dongguan Key Laboratory of Medical Electronics and Medical Imaging Equipment, Dongguan, People's Republic of China
| | - Panke Wang
- School of Biomedical Engineering, Guangdong Medical University, Dongguan, People's Republic of China
- Songshan Lake Innovation Center of Medicine and Engineering, Guangdong Medical University, Dongguan, People's Republic of China
- Dongguan Key Laboratory of Medical Electronics and Medical Imaging Equipment, Dongguan, People's Republic of China
| |
Collapse
|
2
|
Rokai J, Rácz M, Fiáth R, Ulbert I, Márton G. ELVISort: encoding latent variables for instant sorting, an artificial intelligence-based end-to-end solution. J Neural Eng 2021; 18. [PMID: 33823497 DOI: 10.1088/1741-2552/abf521] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2020] [Accepted: 04/06/2021] [Indexed: 11/12/2022]
Abstract
Objective.The growing number of recording sites of silicon-based probes means that an increasing amount of neural cell activities can be recorded simultaneously, facilitating the investigation of underlying complex neural dynamics. In order to overcome the challenges generated by the increasing number of channels, highly automated signal processing tools are needed. Our goal was to build a spike sorting model that can perform as well as offline solutions while maintaining high efficiency, enabling high-performance online sorting.Approach.In this paper we present ELVISort, a deep learning method that combines the detection and clustering of different action potentials in an end-to-end fashion.Main results.The performance of ELVISort is comparable with other spike sorting methods that use manual or semi-manual techniques, while exceeding the methods which use an automatic approach: ELVISort has been tested on three independent datasets and yielded average F1scores of 0.96, 0.82 and 0.81, which comparable with the results of state-of-the-art algorithms on the same data. We show that despite the good performance, ELVISort is capable to process data in real-time: the time it needs to execute the necessary computations for a sample of given length is only 1/15.71 of its actual duration (i.e. the sampling time multiplied by the number of the sampling points).Significance.ELVISort, because of its end-to-end nature, can exploit the massively parallel processing capabilities of GPUs via deep learning frameworks by processing multiple batches in parallel, with the potential to be used on other cutting-edge AI-specific hardware such as TPUs, enabling the development of integrated, portable and real-time spike sorting systems with similar performance to offline sorters.
Collapse
Affiliation(s)
- János Rokai
- Institute of Cognitive Neuroscience and Psychology, Research Centre for Natural Sciences, Magyar tudósok körútja 2, Budapest H-1117, Hungary.,School of PhD Studies, Semmelweis University, Üllői út 26, H-1085 Budapest, Hungary
| | - Melinda Rácz
- Institute of Cognitive Neuroscience and Psychology, Research Centre for Natural Sciences, Magyar tudósok körútja 2, Budapest H-1117, Hungary.,School of PhD Studies, Semmelweis University, Üllői út 26, H-1085 Budapest, Hungary
| | - Richárd Fiáth
- Institute of Cognitive Neuroscience and Psychology, Research Centre for Natural Sciences, Magyar tudósok körútja 2, Budapest H-1117, Hungary.,Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 50/a, H-1083 Budapest, Hungary
| | - István Ulbert
- Institute of Cognitive Neuroscience and Psychology, Research Centre for Natural Sciences, Magyar tudósok körútja 2, Budapest H-1117, Hungary.,Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 50/a, H-1083 Budapest, Hungary
| | - Gergely Márton
- Institute of Cognitive Neuroscience and Psychology, Research Centre for Natural Sciences, Magyar tudósok körútja 2, Budapest H-1117, Hungary.,Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 50/a, H-1083 Budapest, Hungary
| |
Collapse
|
3
|
Baldazzi G, Solinas G, Del Valle J, Barbaro M, Micera S, Raffo L, Pani D. Systematic analysis of wavelet denoising methods for neural signal processing. J Neural Eng 2020; 17. [PMID: 33142283 DOI: 10.1088/1741-2552/abc741] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2020] [Accepted: 11/03/2020] [Indexed: 12/13/2022]
Abstract
Objective.Among the different approaches for denoising neural signals, wavelet-based methods are widely used due to their ability to reduce in-band noise. All wavelet denoising algorithms have a common structure, but their effectiveness strongly depends on several implementation choices, including the mother wavelet, the decomposition level, the threshold definition, and the way it is applied (i.e. the thresholding). In this work, we investigated these factors to quantitatively assess their effects on neural signals in terms of noise reduction and morphology preservation, which are important when spike sorting is required downstream.Approach.Based on the spectral characteristics of the neural signal, according to the sampling rate of the signals, we considered two possible decomposition levels and identified the best-performing mother wavelet. Then, we compared different threshold estimation and thresholding methods and, for the best ones, we also evaluated their effect on clearing the approximation coefficients. The assessments were performed on synthetic signals that had been corrupted by different types of noise and on a murine peripheral nervous system dataset, both of which were sampled at about 16 kHz. The results were statistically analysed in terms of their Pearson's correlation coefficients, root-mean-square errors, and signal-to-noise ratios.Main results.As expected, the wavelet implementation choices greatly influenced the processing performance. Overall, the Haar wavelet with a five-level decomposition, hard thresholding method, and the threshold proposed by Hanet al(2007) achieved the best outcomes. Based on the adopted performance metrics, wavelet denoising with these parametrizations outperformed conventional 300-3000 Hz linear bandpass filtering.Significance.These results can be used to guide the reasoned and accurate selection of wavelet denoising implementation choices in the context of neural signal processing, particularly when spike-morphology preservation is required.
Collapse
Affiliation(s)
- Giulia Baldazzi
- Department of Informatics, Bioengineering, Robotics and Systems Engineering (DIBRIS), University of Genoa, Genoa, Italy.,Department of Electrical and Electronic Engineering (DIEE), University of Cagliari, Cagliari, Italy
| | - Giuliana Solinas
- Department of Biomedical Sciences, University of Sassari, Sassari, Italy
| | - Jaume Del Valle
- Institute of Neurosciences, Department of Cell Biology, Physiology and Immunology, Universitat Autònoma de Barcelona and CIBERNED, Bellaterra, Spain
| | - Massimo Barbaro
- Department of Electrical and Electronic Engineering (DIEE), University of Cagliari, Cagliari, Italy
| | - Silvestro Micera
- The BioRobotics Institute and Department of Excellence in Robotics and Artificial Intelligence, Scuola Superiore Sant'Anna, Pisa, Italy.,Bertarelli Foundation Chair, Center for Neuroprosthetics and Institute of Bioengineering, School of Engineering, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
| | - Luigi Raffo
- Department of Electrical and Electronic Engineering (DIEE), University of Cagliari, Cagliari, Italy
| | - Danilo Pani
- Department of Electrical and Electronic Engineering (DIEE), University of Cagliari, Cagliari, Italy
| |
Collapse
|
4
|
Wang PK, Pun SH, Chen CH, McCullagh EA, Klug A, Li A, Vai MI, Mak PU, Lei TC. Low-latency single channel real-time neural spike sorting system based on template matching. PLoS One 2019; 14:e0225138. [PMID: 31756211 PMCID: PMC6874356 DOI: 10.1371/journal.pone.0225138] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2019] [Accepted: 10/29/2019] [Indexed: 11/26/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Pan Ke Wang
- State Key Laboratory of Analog and Mixed-Signal VLSI, Institute of Microelectronics, University of Macau, Macau, China
- Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Macau, China
| | - Sio Hang Pun
- State Key Laboratory of Analog and Mixed-Signal VLSI, Institute of Microelectronics, University of Macau, Macau, China
- * E-mail:
| | - Chang Hao Chen
- State Key Laboratory of Analog and Mixed-Signal VLSI, Institute of Microelectronics, University of Macau, Macau, China
| | - Elizabeth A. McCullagh
- Department of Physiology and Biophysics, University of Colorado Anschutz Medical Campus, Aurora, CO, United States of America
| | - Achim Klug
- Department of Physiology and Biophysics, University of Colorado Anschutz Medical Campus, Aurora, CO, United States of America
| | - Anan Li
- Jiangsu Key Laboratory of Brain Disease and Bioinformation, Research Center for Biochemistry and Molecular Biology, Xuzhou Medical University, Xuzhou, China
| | - Mang I. Vai
- State Key Laboratory of Analog and Mixed-Signal VLSI, Institute of Microelectronics, University of Macau, Macau, China
- Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Macau, China
| | - Peng Un Mak
- Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Macau, China
| | - Tim C. Lei
- State Key Laboratory of Analog and Mixed-Signal VLSI, Institute of Microelectronics, University of Macau, Macau, China
- Department of Electrical Engineering, University of Colorado, Denver, CO, United States of America
| |
Collapse
|