Semi-supervised spike sorting using pattern matching and a scaled Mahalanobis distance metric

Sorting action potentials (spikes) from tetrode recordings can be time consuming, labor intensive, and inconsistent, depending on the methods used and the experience of the operator. The techniques presented here were designed to address these issues. A feature related to the slope of the spike during repolarization is computed. A small subsample of the features obtained from the tetrode (ca. 10,000–20,000 events) is clustered using a modified version of k-means that uses Mahalanobis distance and a scaling factor related to the cluster size. The cluster-size-based scaling improves the clustering by increasing the separability of close clusters, especially when they are of disparate size. The full data set is then classified from the statistics of the clusters. The technique yields consistent results for a chosen number of clusters. A MATLAB implementation is able to classify more than 5000 spikes per second on a modern workstation.

► Algorithms have been developed for use in spike sorting.
► Slope of action potentials in repolarization region is useful as a feature.
► Repolarization region slope does not require dimensionality reduction such as PCA.
► Clustering algorithm based on k-means with Mahalanobis distance metric and cluster size scaling performs well and is fast.