Identifying Functional Brain Networks of Spatiotemporal Wide-Field Calcium Imaging Data via a Long Short-Term Memory Autoencoder

TL;DR

This paper introduces a novel LSTM autoencoder method for identifying functional brain networks from wide-field calcium imaging data, outperforming traditional methods in accounting for variability and flexibility.

Contribution

The study presents a new unsupervised deep learning approach using LSTM autoencoders to identify FBNs, improving upon seed-based and ICA methods.

Findings

LSTM-AER produces FBN maps similar to traditional methods.

LSTM-AER better accounts for intra-subject variation.

LSTM-AER handles shorter data epochs and variable latent components.

Abstract

Wide-field calcium imaging (WFCI) that records neural calcium dynamics allows for identification of functional brain networks (FBNs) in mice that express genetically encoded calcium indicators. Estimating FBNs from WFCI data is commonly achieved by use of seed-based correlation (SBC) analysis and independent component analysis (ICA). These two methods are conceptually distinct and each possesses limitations. Recent success of unsupervised representation learning in neuroimage analysis motivates the investigation of such methods to identify FBNs. In this work, a novel approach referred as LSTM-AER, is proposed in which a long short-term memory (LSTM) autoencoder (AE) is employed to learn spatial-temporal latent embeddings from WFCI data, followed by an ordinary least square regression (R) to estimate FBNs. The goal of this study is to elucidate and illustrate, qualitatively and quantitatively, the FBNs identified by use of the LSTM-AER method and compare them to those from traditional SBC and ICA. It was observed that spatial FBN maps produced from LSTM-AER resembled those derived by SBC and ICA while better accounting for intra-subject variation, data from a single hemisphere, shorter epoch lengths and tunable number of latent components. The results demonstrate the potential of unsupervised deep learning-based approaches to identifying and mapping FBNs.