English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Today the gold standard for in vivo imaging through scattering tissue is thepoint-scanning two-photon microscope (PSTPM). Especially in neuroscience, PSTPMis widely used for deep-tissue imaging in the brain. However, due to sequentialscanning, PSTPM is slow. Temporal focusing microscopy (TFM), on the other hand,focuses femtosecond pulsed laser light temporally, while keeping wide-fieldillumination, and is consequently much faster. However, due to the use of acamera detector, TFM suffers from the scattering of emission photons. As aresult, TFM produces images of poor spatial resolution and signal-to-noiseratio (SNR), burying fluorescent signals from small structures such asdendritic spines. In this work, we present a data-driven deep learning approachto improve resolution and SNR of TFM images. Using a 3D convolutional neuralnetwork (CNN) we build a map from TFM to PSTPM modalities, to enable fast TFMimaging while maintaining high-resolution through scattering media. Wedemonstrate this approach for in vivo imaging of dendritic spines on pyramidalneurons in the mouse visual cortex. We show that our trained network rapidlyoutputs high-resolution images that recover biologically relevant featurespreviously buried in the scattered fluorescence in the TFM images. In vivoimaging that combines TFM and the proposed 3D convolution neural network is oneto two orders of magnitude faster than PSTPM but retains the high resolutionand SNR necessary to analyze small fluorescent structures. The proposed 3Dconvolution deep network could also be potentially beneficial for improving theperformance of many speed-demanding deep-tissue imaging applications such as invivo voltage imaging.

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