Multichannel Electrophysiological Spike Sorting via Joint Dictionary Learning & Mixture Modeling

TL;DR

This paper introduces a novel joint dictionary learning and mixture modeling approach for multichannel electrophysiological spike sorting, enhancing accuracy and robustness in detecting and classifying neural spikes across multiple recording sessions.

Contribution

The work presents a new Bayesian framework that jointly learns features and clusters, incorporates a focused mixture model for multi-day recordings, and handles missing data effectively.

Findings

Achieves state-of-the-art spike sorting performance

Effectively distinguishes spikes from artifacts across channels

Handles neurons appearing and disappearing over time

Abstract

We propose a construction for joint feature learning and clustering of multichannel extracellular electrophysiological data across multiple recording periods for action potential detection and discrimination ("spike sorting"). Our construction improves over the previous state-of-the art principally in four ways. First, via sharing information across channels, we can better distinguish between single-unit spikes and artifacts. Second, our proposed "focused mixture model" (FMM) elegantly deals with units appearing, disappearing, or reappearing over multiple recording days, an important consideration for any chronic experiment. Third, by jointly learning features and clusters, we improve performance over previous attempts that proceeded via a two-stage ("frequentist") learning process. Fourth, by directly modeling spike rate, we improve detection of sparsely spiking neurons. Moreover, our Bayesian construction seamlessly handles missing data. We present state-of-the-art performance without requiring manually tuning of many hyper-parameters on both a public dataset with partial ground truth and a new experimental dataset.