Volumetric imaging of cellular dynamics with deep learning enhanced bioluminescence microscopy
Year: 2022
Type: dataset
Abstract: The low photon emission of known luciferases, currently limit their widespread use as contrast agents in live cell microscopy because they demand long exposure times that are prohibitive for imaging fast biological dynamics. To increase the versatility of bioluminescence microscopy as an alternative for fluorescence microscopy, we present an improved low-light microscope in combination with deep learning methods to image extremely photon-starved samples enabling subsecond exposures for timelapse and volumetric imaging. Here, we leverage a versatile training data set for deep learning based bioluminescence microscopy including paired images of noisy and ground thruth fluorescence data of body wall muscle labeled Caenorhabditis elegans animals. These data include light-field images and their ground truth reconstructions for training a CNN for fast light fiel deconvolution.
Institution: Institute of Photonic Sciences
Language: English
Subfield: Biophysics
Domain: Life Sciences
Open Access status: green
Funder: Horizon 2020 Framework Programme
Award: G3989185837
OpenAlex ID: W4393786430