3D Deep Learning Enables Fast Imaging of Spines through Scattering Media by Temporal Focusing Microscopy

TL;DR

This paper introduces a 3D deep learning method that transforms fast but low-resolution temporal focusing microscopy images into high-resolution images comparable to point-scanning two-photon microscopy, enabling rapid, detailed in vivo imaging through scattering tissue.

Contribution

The authors develop a 3D CNN that maps TFM images to PSTPM quality, significantly enhancing resolution and SNR in scattering media, and demonstrate its application in live mouse brain imaging.

Findings

High-resolution images recovered from scattering media

Imaging speed increased by one to two orders of magnitude

Effective in vivo imaging of dendritic spines in mouse cortex

Abstract

Today the gold standard for in vivo imaging through scattering tissue is the point-scanning two-photon microscope (PSTPM). Especially in neuroscience, PSTPM is widely used for deep-tissue imaging in the brain. However, due to sequential scanning, PSTPM is slow. Temporal focusing microscopy (TFM), on the other hand, focuses femtosecond pulsed laser light temporally, while keeping wide-field illumination, and is consequently much faster. However, due to the use of a camera detector, TFM suffers from the scattering of emission photons. As a result, TFM produces images of poor spatial resolution and signal-to-noise ratio (SNR), burying fluorescent signals from small structures such as dendritic spines. In this work, we present a data-driven deep learning approach to improve resolution and SNR of TFM images. Using a 3D convolutional neural network (CNN) we build a map from TFM to PSTPM modalities, to enable fast TFM imaging while maintaining high-resolution through scattering media. We demonstrate this approach for in vivo imaging of dendritic spines on pyramidal neurons in the mouse visual cortex. We show that our trained network rapidly outputs high-resolution images that recover biologically relevant features previously buried in the scattered fluorescence in the TFM images. In vivo imaging that combines TFM and the proposed 3D convolution neural network is one to two orders of magnitude faster than PSTPM but retains the high resolution and SNR necessary to analyze small fluorescent structures. The proposed 3D convolution deep network could also be potentially beneficial for improving the performance of many speed-demanding deep-tissue imaging applications such as in vivo voltage imaging.