Fast amortized inference of neural activity from calcium imaging data with variational autoencoders

TL;DR

This paper introduces a variational autoencoder-based framework for fast, accurate inference of neural spike trains from calcium imaging data, significantly reducing computation time while maintaining competitive accuracy.

Contribution

It presents a novel amortized inference method using deep neural networks for efficient spike train extraction from calcium imaging, applicable to various nonlinear generative models.

Findings

Significantly faster inference compared to traditional Bayesian methods.

Achieves competitive accuracy in spike train reconstruction.

First probabilistic approach to separate backpropagating action potentials from synaptic inputs.

Abstract

Calcium imaging permits optical measurement of neural activity. Since intracellular calcium concentration is an indirect measurement of neural activity, computational tools are necessary to infer the true underlying spiking activity from fluorescence measurements. Bayesian model inversion can be used to solve this problem, but typically requires either computationally expensive MCMC sampling, or faster but approximate maximum-a-posteriori optimization. Here, we introduce a flexible algorithmic framework for fast, efficient and accurate extraction of neural spikes from imaging data. Using the framework of variational autoencoders, we propose to amortize inference by training a deep neural network to perform model inversion efficiently. The recognition network is trained to produce samples from the posterior distribution over spike trains. Once trained, performing inference amounts to a fast single forward pass through the network, without the need for iterative optimization or sampling. We show that amortization can be applied flexibly to a wide range of nonlinear generative models and significantly improves upon the state of the art in computation time, while achieving competitive accuracy. Our framework is also able to represent posterior distributions over spike-trains. We demonstrate the generality of our method by proposing the first probabilistic approach for separating backpropagating action potentials from putative synaptic inputs in calcium imaging of dendritic spines.