Using deep neural networks to detect complex spikes of cerebellar Purkinje cells

Abstract

Purkinje cell “complex spikes,” fired at perplexingly low rates, play a crucial role in cerebellum-based motor learning. Careful interpretations of these spikes require manually detecting them, since conventional online or offline spike sorting algorithms are optimized for classifying much simpler waveform morphologies. We present a novel deep learning approach for identifying complex spikes, which also measures additional relevant neurophysiological features, with an accuracy level matching that of human experts yet with very little time expenditure.

P-sort: an open-source software for cerebellar neurophysiology

“…UMAP is a nonlinear technique that, in our experience, is particularly powerful for clustering waveforms and identifying complex spikes, as also shown by the work of Markanday et al (2020). Indeed, in the case of the data in Fig.…”

“…Identification of complex spikes suffers from additional problems. There are variable number of spikelets in the complex spike waveform (Burroughs et al, 2017;Davie et al, 2008;Ito & Simpson, 1971;Monsivais et al, 2005;Najafi & Medina, 2013;Yang & Lisberger, 2014), and thus template matching may have difficulty labeling all complex spikes (Markanday et al, 2020). Examples of the variable spikelets are shown in Fig.…”

“…Finally, the complex spike waveform can be distorted because of the proximity of a simple spike, as shown in Fig. 2B (Markanday et al, 2020;Servais et al, 2004). This is because simple and complex spikes are driven by different inputs to the P-cell, one is from a climbing fiber that generates a dendritic complex spike, while the other is from granule cells that generate somatic simple spikes.…”

“…Because the main difference between P-sort and the automated algorithms was regarding identification of complex spikes, we thought to further verify P-sort's performance specifically on complex spikes. We did this by comparing P-sort with a recently developed neural network (Markanday et al, 2020) that was specifically trained on complex spike waveforms. Here we found near unanimous agreement between the two approaches ( Supplementary Fig.…”

“…As a result, a typical complex spike can produce a "broad spike" in the lowpass filtered representation of the data (local field potential, LFP). Indeed, two recent developments in complex spike detection are novel algorithms that depend partly on the LFP waveform (Markanday et al, 2020;Zur & Joshua, 2019). Once the simple and complex spikes are labeled, the final step is to determine whether the simple spikes have been suppressed after a complex spike.…”