Deep Learning-Based Template Matching Spike Classification for Extracellular Recordings

We propose a deep learning-based spike sorting method for extracellular recordings. For analysis of extracellular single unit activity, the process of detecting and classifying action potentials called “spike sorting” has become essential. This is achieved through distinguishing the morphological differences of the spikes from each neuron, which arises from the differences of the surrounding environment and characteristics of the neurons. However, cases of high structural similarity and noise make the task difficult. And for manual spike sorting, it requires professional knowledge along with extensive time cost and suffers from human bias. We propose a deep learning-based spike sorting method on extracellular recordings from a single electrode that is efficient, robust to noise, and accurate. In circumstances where labelled data does not exist, we created pseudo-labels through principal component analysis and K-means clustering to be used for multi-layer perceptron training and built high performing spike classification model. When tested, our model outperformed conventional methods by 2.1% on simulation data of various noise levels, by 6.0% on simulation data of various clusters count, and by 1.7% on in-vivo data. As a result, we showed that the deep learning-based classification can classify spikes from extracellular recordings, even showing high classification accuracy on spikes that are difficult even for manual classification.

[1]  Rodrigo Quian Quiroga,et al.  Past, present and future of spike sorting techniques , 2015, Brain Research Bulletin.

[2]  J. A. Hartigan,et al.  A k-means clustering algorithm , 1979 .

[3]  J. Okada,et al.  Multineuronal spike classification based on multisite electrode recording, whole-waveform analysis, and hierarchical clustering , 1999, IEEE Transactions on Biomedical Engineering.

[4]  Amitava Chatterjee,et al.  Cross-correlation aided support vector machine classifier for classification of EEG signals , 2009, Expert Syst. Appl..

[5]  Yeowool Huh,et al.  Differential Responses of Thalamic Reticular Neurons to Nociception in Freely Behaving Mice , 2016, Front. Behav. Neurosci..

[6]  Yi Zhou,et al.  Spike sorting based on automatic template reconstruction with a partial solution to the overlapping problem , 2004, Journal of Neuroscience Methods.

[7]  Taeseong Kim,et al.  KIKI‐net: cross‐domain convolutional neural networks for reconstructing undersampled magnetic resonance images , 2018, Magnetic resonance in medicine.

[8]  Sayanti Chaudhuri,et al.  Obstructive sleep apnoea detection using convolutional neural network based deep learning framework , 2017, Biomedical Engineering Letters.

[9]  Ioannis Iossifidis,et al.  SpikeDeeptector: a deep-learning based method for detection of neural spiking activity , 2019, Journal of neural engineering.

[10]  Xinyu Liu,et al.  Quality Metrics of Spike Sorting Using Neighborhood Components Analysis , 2014, The open biomedical engineering journal.

[11]  Richard A. Andersen,et al.  Latent variable models for neural data analysis , 1999 .

[12]  István Ulbert,et al.  Spike detection and sorting with deep learning , 2020, Journal of neural engineering.

[13]  Rene F. Jansen,et al.  Automatic wave form classification of extracellular multineuron recordings , 1992, Journal of Neuroscience Methods.

[14]  P. Prabhu Improving the Performance of K-Means Clustering for High Dimensional Dataset , 2011 .

[15]  Shubha Singh,et al.  A Survey of Clustering Techniques , 2010 .

[16]  J.P. Miller,et al.  Optimal discrimination and classification of neuronal action potential waveforms from multiunit, multichannel recordings using software-based linear filters , 1994, IEEE Transactions on Biomedical Engineering.

[17]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Sewon Kim,et al.  Neural spike classification via deep neural network , 2019 .

[19]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[20]  Kenneth D Harris,et al.  Improving data quality in neuronal population recordings , 2016, Nature Neuroscience.

[21]  Adriano B L Tort,et al.  Spike sorting with Gaussian mixture models , 2018, Scientific Reports.

[22]  Rodrigo Quian Quiroga,et al.  How many neurons can we see with current spike sorting algorithms? , 2012, Journal of Neuroscience Methods.

[23]  Alexis Boukouvalas,et al.  What to Do When K-Means Clustering Fails: A Simple yet Principled Alternative Algorithm , 2016, PloS one.

[24]  Pierre Yger,et al.  A spike sorting toolbox for up to thousands of electrodes validated with ground truth recordings in vitro and in vivo , 2018, eLife.

[25]  Zhi Yang,et al.  Noise-robust unsupervised spike sorting based on discriminative subspace learning with outlier handling , 2017, Journal of neural engineering.

[26]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[27]  Jadin C. Jackson,et al.  Quantitative measures of cluster quality for use in extracellular recordings , 2005, Neuroscience.

[28]  Stephen L. Chiu,et al.  Fuzzy Model Identification Based on Cluster Estimation , 1994, J. Intell. Fuzzy Syst..

[29]  R. Quian Quiroga,et al.  Unsupervised Spike Detection and Sorting with Wavelets and Superparamagnetic Clustering , 2004, Neural Computation.

[30]  Cenk Sahin,et al.  Neural Network-Based Computer-Aided Diagnosis in Classification of Primary Generalized Epilepsy by EEG Signals , 2009, Journal of Medical Systems.

[31]  Kemal Polat,et al.  Efficient sleep stage recognition system based on EEG signal using k-means clustering based feature weighting , 2010, Expert Syst. Appl..

[32]  Partha P. Mitra,et al.  Automatic sorting of multiple unit neuronal signals in the presence of anisotropic and non-Gaussian variability , 1996, Journal of Neuroscience Methods.

[33]  Yeowool Huh,et al.  Discrete Pattern of Burst Stimulation in the Ventrobasal Thalamus for Anti-Nociception , 2013, PloS one.

[34]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[35]  C. Koch,et al.  On the origin of the extracellular action potential waveform: A modeling study. , 2006, Journal of neurophysiology.

[36]  Shy Shoham,et al.  Robust, automatic spike sorting using mixtures of multivariate t-distributions , 2003, Journal of Neuroscience Methods.

[37]  Luis A. Camuñas-Mesa,et al.  A Detailed and Fast Model of Extracellular Recordings , 2013, Neural Computation.

[38]  J. T. Taylor,et al.  First demonstration of velocity selective recording from the pig vagus using a nerve cuff shows respiration afferents , 2018, Biomedical engineering letters.

[39]  Rushi Bhatt,et al.  Interactive Responses of a Thalamic Neuron to Formalin Induced Lasting Pain in Behaving Mice , 2012, PloS one.

[40]  I. Bankman,et al.  Optimal detection, classification, and superposition resolution in neural waveform recordings , 1993, IEEE Transactions on Biomedical Engineering.

[41]  Kenneth Revett,et al.  EEG Signal Classification Using Wavelet Feature Extraction and Neural Networks , 2006, IEEE John Vincent Atanasoff 2006 International Symposium on Modern Computing (JVA'06).

[42]  T. Suzuki,et al.  Fast Automatic Template Matching for Spike Sorting Based on Davies-Bouldin Validation Indices , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.