Automatic spike sorting for extracellular electrophysiological recording using unsupervised single linkage clustering based on grey relational analysis

Hsin Yi Lai, You Yin Chen, Sheng Huang Lin, Yu Chun Lo, Siny Tsang, Shin Yuan Chen, Wan Ting Zhao, Wen Hung Chao, Yao Chuan Chang, Robby Wu, Yen Yu I Shih, Sheng Tsung Tsai, Fu Shan Jaw

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Automatic spike sorting is a prerequisite for neuroscience research on multichannel extracellular recordings of neuronal activity. A novel spike sorting framework, combining efficient feature extraction and an unsupervised clustering method, is described here. Wavelet transform (WT) is adopted to extract features from each detected spike, and the Kolmogorov-Smirnov test (KS test) is utilized to select discriminative wavelet coefficients from the extracted features. Next, an unsupervised single linkage clustering method based on grey relational analysis (GSLC) is applied for spike clustering. The GSLC uses the grey relational grade as the similarity measure, instead of the Euclidean distance for distance calculation; the number of clusters is automatically determined by the elbow criterion in the threshold-cumulative distribution. Four simulated data sets with four noise levels and electrophysiological data recorded from the subthalamic nucleus of eight patients with Parkinson's disease during deep brain stimulation surgery are used to evaluate the performance of GSLC. Feature extraction results from the use of WT with the KS test indicate a reduced number of feature coefficients, as well as good noise rejection, despite similar spike waveforms. Accordingly, the use of GSLC for spike sorting achieves high classification accuracy in all simulated data sets. Moreover, J-measure results in the electrophysiological data indicating that the quality of spike sorting is adequate with the use of GSLC.

Original languageEnglish
Article number036003
JournalJournal of Neural Engineering
Volume8
Issue number3
DOIs
Publication statusPublished - Jun 2011
Externally publishedYes

Fingerprint

Sorting
Cluster Analysis
Wavelet Analysis
Nonparametric Statistics
Noise
Wavelet transforms
Feature extraction
Subthalamic Nucleus
Deep Brain Stimulation
Neurosciences
Elbow
Parkinson Disease
Surgery
Brain
Research
Datasets

ASJC Scopus subject areas

  • Biomedical Engineering
  • Cellular and Molecular Neuroscience

Cite this

Automatic spike sorting for extracellular electrophysiological recording using unsupervised single linkage clustering based on grey relational analysis. / Lai, Hsin Yi; Chen, You Yin; Lin, Sheng Huang; Lo, Yu Chun; Tsang, Siny; Chen, Shin Yuan; Zhao, Wan Ting; Chao, Wen Hung; Chang, Yao Chuan; Wu, Robby; Shih, Yen Yu I; Tsai, Sheng Tsung; Jaw, Fu Shan.

In: Journal of Neural Engineering, Vol. 8, No. 3, 036003, 06.2011.

Research output: Contribution to journalArticle

Lai, Hsin Yi ; Chen, You Yin ; Lin, Sheng Huang ; Lo, Yu Chun ; Tsang, Siny ; Chen, Shin Yuan ; Zhao, Wan Ting ; Chao, Wen Hung ; Chang, Yao Chuan ; Wu, Robby ; Shih, Yen Yu I ; Tsai, Sheng Tsung ; Jaw, Fu Shan. / Automatic spike sorting for extracellular electrophysiological recording using unsupervised single linkage clustering based on grey relational analysis. In: Journal of Neural Engineering. 2011 ; Vol. 8, No. 3.
@article{21e99963e1ee4e02896295609ef2a083,
title = "Automatic spike sorting for extracellular electrophysiological recording using unsupervised single linkage clustering based on grey relational analysis",
abstract = "Automatic spike sorting is a prerequisite for neuroscience research on multichannel extracellular recordings of neuronal activity. A novel spike sorting framework, combining efficient feature extraction and an unsupervised clustering method, is described here. Wavelet transform (WT) is adopted to extract features from each detected spike, and the Kolmogorov-Smirnov test (KS test) is utilized to select discriminative wavelet coefficients from the extracted features. Next, an unsupervised single linkage clustering method based on grey relational analysis (GSLC) is applied for spike clustering. The GSLC uses the grey relational grade as the similarity measure, instead of the Euclidean distance for distance calculation; the number of clusters is automatically determined by the elbow criterion in the threshold-cumulative distribution. Four simulated data sets with four noise levels and electrophysiological data recorded from the subthalamic nucleus of eight patients with Parkinson's disease during deep brain stimulation surgery are used to evaluate the performance of GSLC. Feature extraction results from the use of WT with the KS test indicate a reduced number of feature coefficients, as well as good noise rejection, despite similar spike waveforms. Accordingly, the use of GSLC for spike sorting achieves high classification accuracy in all simulated data sets. Moreover, J-measure results in the electrophysiological data indicating that the quality of spike sorting is adequate with the use of GSLC.",
author = "Lai, {Hsin Yi} and Chen, {You Yin} and Lin, {Sheng Huang} and Lo, {Yu Chun} and Siny Tsang and Chen, {Shin Yuan} and Zhao, {Wan Ting} and Chao, {Wen Hung} and Chang, {Yao Chuan} and Robby Wu and Shih, {Yen Yu I} and Tsai, {Sheng Tsung} and Jaw, {Fu Shan}",
year = "2011",
month = "6",
doi = "10.1088/1741-2560/8/3/036003",
language = "English",
volume = "8",
journal = "Journal of Neural Engineering",
issn = "1741-2560",
publisher = "IOP Publishing Ltd.",
number = "3",

}

TY - JOUR

T1 - Automatic spike sorting for extracellular electrophysiological recording using unsupervised single linkage clustering based on grey relational analysis

AU - Lai, Hsin Yi

AU - Chen, You Yin

AU - Lin, Sheng Huang

AU - Lo, Yu Chun

AU - Tsang, Siny

AU - Chen, Shin Yuan

AU - Zhao, Wan Ting

AU - Chao, Wen Hung

AU - Chang, Yao Chuan

AU - Wu, Robby

AU - Shih, Yen Yu I

AU - Tsai, Sheng Tsung

AU - Jaw, Fu Shan

PY - 2011/6

Y1 - 2011/6

N2 - Automatic spike sorting is a prerequisite for neuroscience research on multichannel extracellular recordings of neuronal activity. A novel spike sorting framework, combining efficient feature extraction and an unsupervised clustering method, is described here. Wavelet transform (WT) is adopted to extract features from each detected spike, and the Kolmogorov-Smirnov test (KS test) is utilized to select discriminative wavelet coefficients from the extracted features. Next, an unsupervised single linkage clustering method based on grey relational analysis (GSLC) is applied for spike clustering. The GSLC uses the grey relational grade as the similarity measure, instead of the Euclidean distance for distance calculation; the number of clusters is automatically determined by the elbow criterion in the threshold-cumulative distribution. Four simulated data sets with four noise levels and electrophysiological data recorded from the subthalamic nucleus of eight patients with Parkinson's disease during deep brain stimulation surgery are used to evaluate the performance of GSLC. Feature extraction results from the use of WT with the KS test indicate a reduced number of feature coefficients, as well as good noise rejection, despite similar spike waveforms. Accordingly, the use of GSLC for spike sorting achieves high classification accuracy in all simulated data sets. Moreover, J-measure results in the electrophysiological data indicating that the quality of spike sorting is adequate with the use of GSLC.

AB - Automatic spike sorting is a prerequisite for neuroscience research on multichannel extracellular recordings of neuronal activity. A novel spike sorting framework, combining efficient feature extraction and an unsupervised clustering method, is described here. Wavelet transform (WT) is adopted to extract features from each detected spike, and the Kolmogorov-Smirnov test (KS test) is utilized to select discriminative wavelet coefficients from the extracted features. Next, an unsupervised single linkage clustering method based on grey relational analysis (GSLC) is applied for spike clustering. The GSLC uses the grey relational grade as the similarity measure, instead of the Euclidean distance for distance calculation; the number of clusters is automatically determined by the elbow criterion in the threshold-cumulative distribution. Four simulated data sets with four noise levels and electrophysiological data recorded from the subthalamic nucleus of eight patients with Parkinson's disease during deep brain stimulation surgery are used to evaluate the performance of GSLC. Feature extraction results from the use of WT with the KS test indicate a reduced number of feature coefficients, as well as good noise rejection, despite similar spike waveforms. Accordingly, the use of GSLC for spike sorting achieves high classification accuracy in all simulated data sets. Moreover, J-measure results in the electrophysiological data indicating that the quality of spike sorting is adequate with the use of GSLC.

UR - http://www.scopus.com/inward/record.url?scp=79957961575&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957961575&partnerID=8YFLogxK

U2 - 10.1088/1741-2560/8/3/036003

DO - 10.1088/1741-2560/8/3/036003

M3 - Article

C2 - 21464520

AN - SCOPUS:79957961575

VL - 8

JO - Journal of Neural Engineering

JF - Journal of Neural Engineering

SN - 1741-2560

IS - 3

M1 - 036003

ER -