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

Limits of classification capability for the simulated and real datasets.A - ROC graph showing the performance of the FCM-classifier during balanced (dotted line) and unbalanced modification (solid lines) of classes in the simulated dataset; B – the same for the real dataset A; C - the same for the real dataset B.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 14: Limits of classification capability for the simulated and real datasets.A - ROC graph showing the performance of the FCM-classifier during balanced (dotted line) and unbalanced modification (solid lines) of classes in the simulated dataset; B – the same for the real dataset A; C - the same for the real dataset B.

Mentions: To investigate this issue, in this section we evaluated the robustness of datasets classification to disparity in cluster size, by progressively eliminating spikes in a cluster and computing the performance of the clustering algorithm as function of the class saturation, i.e. of the fraction of spikes left in the cluster. Results are shown in Figure 14, showing the simulated data and the real datasets A and B. Color lines show the true positive rate (i.e. the percentage of spikes retaining true cluster membership) when reducing the size of a particular cluster while the size of other clusters remains unchanged. The accuracy of classification of the simulated Example 2 with noise level 0.15 is shown in Figure 14A. Unbalanced decrease of clusters up to 40% of their original size shows still high classification accuracy (right-hand side of the graph). Further cluster decrease shows minor deterioration of classification accuracy due to drifting of smaller clusters toward lager adjacent ones. An abrupt and pronounced deterioration in the partitioning of the data was found only when clusters 1, 2 or 3 remain less than 34,7%, 18,5% or 14,1%, of their original size, respectively.


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

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

Limits of classification capability for the simulated and real datasets.A - ROC graph showing the performance of the FCM-classifier during balanced (dotted line) and unbalanced modification (solid lines) of classes in the simulated dataset; B – the same for the real dataset A; C - the same for the real dataset B.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 14: Limits of classification capability for the simulated and real datasets.A - ROC graph showing the performance of the FCM-classifier during balanced (dotted line) and unbalanced modification (solid lines) of classes in the simulated dataset; B – the same for the real dataset A; C - the same for the real dataset B.
Mentions: To investigate this issue, in this section we evaluated the robustness of datasets classification to disparity in cluster size, by progressively eliminating spikes in a cluster and computing the performance of the clustering algorithm as function of the class saturation, i.e. of the fraction of spikes left in the cluster. Results are shown in Figure 14, showing the simulated data and the real datasets A and B. Color lines show the true positive rate (i.e. the percentage of spikes retaining true cluster membership) when reducing the size of a particular cluster while the size of other clusters remains unchanged. The accuracy of classification of the simulated Example 2 with noise level 0.15 is shown in Figure 14A. Unbalanced decrease of clusters up to 40% of their original size shows still high classification accuracy (right-hand side of the graph). Further cluster decrease shows minor deterioration of classification accuracy due to drifting of smaller clusters toward lager adjacent ones. An abrupt and pronounced deterioration in the partitioning of the data was found only when clusters 1, 2 or 3 remain less than 34,7%, 18,5% or 14,1%, of their original size, respectively.

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