Biological system

Iterative reconstruction

Biology

Computer science

Gene

Optics

Cell biology

Computer vision

Biochemistry

Microscopy

Artifact (error)

Temporal resolution

Video microscopy

Artificial intelligence

Light sheet fluorescence microscopy

Scanning confocal electron microscopy

Physics

Image resolution

Zebrafish

Light field

Nature Methods

Light-field microscopy has emerged as a technique of choice for high-speed volumetric imaging of fast biological processes. However, artifacts, nonuniform resolution and a slow reconstruction speed have limited its full capabilities for in toto extraction of dynamic spatiotemporal patterns in samples. Here, we combined a view-channel-depth (VCD) neural network with light-field microscopy to mitigate these limitations, yielding artifact-free three-dimensional image sequences with uniform spatial resolution and high-video-rate reconstruction throughput. We imaged neuronal activities across moving Caenorhabditis elegans and blood flow in a beating zebrafish heart at single-cell resolution with volumetric imaging rates up to 200 Hz. Reconstruction of light-field microscopy data with a deep-learning network achieves high reconstruction speed and reduces artifacts, as illustrated for moving C. elegans and beating zebrafish hearts.

Real-time volumetric reconstruction of biological dynamics with light-field microscopy and deep learning