Limits...
Automatic online spike sorting with singular value decomposition and fuzzy C-mean clustering.

Oliynyk A, Bonifazzi C, Montani F, Fadiga L - BMC Neurosci (2012)

Bottom Line: The results of these tests showed an excellent accuracy in discriminating low-amplitude and overlapping spikes under strong background noise.This new software provides neuroscience laboratories with a new tool for fast and robust online classification of single neuron activity.This feature could become crucial in situations when online spike detection from multiple electrodes is paramount, such as in human clinical recordings or in brain-computer interfaces.

View Article: PubMed Central - HTML - PubMed

Affiliation: Section of Human Physiology, Department of Biomedical Sciences and Advanced Therapies, Faculty of Medicine, University of Ferrara, Via Fossato di Mortara 17/19, 44121, Ferrara, Italy. lynnry@unife.it

ABSTRACT

Background: Understanding how neurons contribute to perception, motor functions and cognition requires the reliable detection of spiking activity of individual neurons during a number of different experimental conditions. An important problem in computational neuroscience is thus to develop algorithms to automatically detect and sort the spiking activity of individual neurons from extracellular recordings. While many algorithms for spike sorting exist, the problem of accurate and fast online sorting still remains a challenging issue.

Results: Here we present a novel software tool, called FSPS (Fuzzy SPike Sorting), which is designed to optimize: (i) fast and accurate detection, (ii) offline sorting and (iii) online classification of neuronal spikes with very limited or human intervention. The method is based on a combination of Singular Value Decomposition for fast and highly accurate pre-processing of spike shapes, unsupervised Fuzzy C-mean, high-resolution alignment of extracted spike waveforms, optimal selection of the number of features to retain, automatic identification the number of clusters, and quantitative quality assessment of resulting clusters independent on their size. After being trained on a short testing data stream, the method can reliably perform supervised online classification and monitoring of single neuron activity. The generalized procedure has been implemented in our FSPS spike sorting software (available free for non-commercial academic applications at the address: http://www.spikesorting.com) using LabVIEW (National Instruments, USA). We evaluated the performance of our algorithm both on benchmark simulated datasets with different levels of background noise and on real extracellular recordings from premotor cortex of Macaque monkeys. The results of these tests showed an excellent accuracy in discriminating low-amplitude and overlapping spikes under strong background noise. The performance of our method is competitive with respect to other robust spike sorting algorithms.

Conclusions: This new software provides neuroscience laboratories with a new tool for fast and robust online classification of single neuron activity. This feature could become crucial in situations when online spike detection from multiple electrodes is paramount, such as in human clinical recordings or in brain-computer interfaces.

Show MeSH

Related in: MedlinePlus

Distribution of-norm values of input singular vectors.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3473300&req=5

Figure 7: Distribution of-norm values of input singular vectors.

Mentions: Though SVD is a powerful tool for characterizing spike waveforms, it does not help to identify the neurons. It is merely a clustering technique wherein the dataset is divided into distinct clusters, which are ultimately interpreted as different single units. We have used the FCM approach based on the classical ISODATA method, using the selected above features/PCs as input variables for clustering. FCM is one of the best known and the most widely used fuzzy clustering algorithms[33]. However, due to the unsupervised nature it requires that the desired number of clusters is specified in advance. If this choice does not correspond to the actual number of clusters, the results of FCM deteriorate. In FSPS software we implemented an algorithm determining the number of clusters automatically and without supervision. To do so, we used histogram-based methods of dataset segmentation which are widely used in real-time pattern recognition systems[34]. The basic idea of algorithm we implemented in our FSPS software rests on the assumption that local densities and the number of peaks on histogram showing the distribution of-norm values for every left singular vector in the corresponds to particular clusters (Figure‚ÄČ7).-norm is considered to be generalized length (or magnitude) of the vector and calculated using the following equation:


Automatic online spike sorting with singular value decomposition and fuzzy C-mean clustering.

Oliynyk A, Bonifazzi C, Montani F, Fadiga L - BMC Neurosci (2012)

Distribution of-norm values of input singular vectors.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3473300&req=5

Figure 7: Distribution of-norm values of input singular vectors.
Mentions: Though SVD is a powerful tool for characterizing spike waveforms, it does not help to identify the neurons. It is merely a clustering technique wherein the dataset is divided into distinct clusters, which are ultimately interpreted as different single units. We have used the FCM approach based on the classical ISODATA method, using the selected above features/PCs as input variables for clustering. FCM is one of the best known and the most widely used fuzzy clustering algorithms[33]. However, due to the unsupervised nature it requires that the desired number of clusters is specified in advance. If this choice does not correspond to the actual number of clusters, the results of FCM deteriorate. In FSPS software we implemented an algorithm determining the number of clusters automatically and without supervision. To do so, we used histogram-based methods of dataset segmentation which are widely used in real-time pattern recognition systems[34]. The basic idea of algorithm we implemented in our FSPS software rests on the assumption that local densities and the number of peaks on histogram showing the distribution of-norm values for every left singular vector in the corresponds to particular clusters (Figure‚ÄČ7).-norm is considered to be generalized length (or magnitude) of the vector and calculated using the following equation:

Bottom Line: The results of these tests showed an excellent accuracy in discriminating low-amplitude and overlapping spikes under strong background noise.This new software provides neuroscience laboratories with a new tool for fast and robust online classification of single neuron activity.This feature could become crucial in situations when online spike detection from multiple electrodes is paramount, such as in human clinical recordings or in brain-computer interfaces.

View Article: PubMed Central - HTML - PubMed

Affiliation: Section of Human Physiology, Department of Biomedical Sciences and Advanced Therapies, Faculty of Medicine, University of Ferrara, Via Fossato di Mortara 17/19, 44121, Ferrara, Italy. lynnry@unife.it

ABSTRACT

Background: Understanding how neurons contribute to perception, motor functions and cognition requires the reliable detection of spiking activity of individual neurons during a number of different experimental conditions. An important problem in computational neuroscience is thus to develop algorithms to automatically detect and sort the spiking activity of individual neurons from extracellular recordings. While many algorithms for spike sorting exist, the problem of accurate and fast online sorting still remains a challenging issue.

Results: Here we present a novel software tool, called FSPS (Fuzzy SPike Sorting), which is designed to optimize: (i) fast and accurate detection, (ii) offline sorting and (iii) online classification of neuronal spikes with very limited or human intervention. The method is based on a combination of Singular Value Decomposition for fast and highly accurate pre-processing of spike shapes, unsupervised Fuzzy C-mean, high-resolution alignment of extracted spike waveforms, optimal selection of the number of features to retain, automatic identification the number of clusters, and quantitative quality assessment of resulting clusters independent on their size. After being trained on a short testing data stream, the method can reliably perform supervised online classification and monitoring of single neuron activity. The generalized procedure has been implemented in our FSPS spike sorting software (available free for non-commercial academic applications at the address: http://www.spikesorting.com) using LabVIEW (National Instruments, USA). We evaluated the performance of our algorithm both on benchmark simulated datasets with different levels of background noise and on real extracellular recordings from premotor cortex of Macaque monkeys. The results of these tests showed an excellent accuracy in discriminating low-amplitude and overlapping spikes under strong background noise. The performance of our method is competitive with respect to other robust spike sorting algorithms.

Conclusions: This new software provides neuroscience laboratories with a new tool for fast and robust online classification of single neuron activity. This feature could become crucial in situations when online spike detection from multiple electrodes is paramount, such as in human clinical recordings or in brain-computer interfaces.

Show MeSH
Related in: MedlinePlus