Experimentally unsupervised deconvolution for light-sheet microscopy with propagation-invariant beams

Wijesinghe, Philip and Corsetti, Stella and Chow, Darren J. X. and Sakata, Shuzo and Dunning, Kylie R. and Dholakia, Kishan (2022) Experimentally unsupervised deconvolution for light-sheet microscopy with propagation-invariant beams. Light: Science & Applications, 11 (1). 319. ISSN 2047-7538 (https://doi.org/10.1038/s41377-022-00975-6)

[thumbnail of Wijesinghe-etal-LSA-2022-Experimentally-unsupervised-deconvolution-for-light-sheet-microscopy]
Preview
 Text. Filename: Wijesinghe_etal_LSA_2022_Experimentally_unsupervised_deconvolution_for_light_sheet_microscopy.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (4MB)| Preview

Abstract

Deconvolution is a challenging inverse problem, particularly in techniques that employ complex engineered point-spread functions, such as microscopy with propagation-invariant beams. Here, we present a deep-learning method for deconvolution that, in lieu of end-to-end training with ground truths, is trained using known physics of the imaging system. Specifically, we train a generative adversarial network with images generated with the known point-spread function of the system, and combine this with unpaired experimental data that preserve perceptual content. Our method rapidly and robustly deconvolves and super-resolves microscopy images, demonstrating a two-fold improvement in image contrast to conventional deconvolution methods. In contrast to common end-to-end networks that often require 1000–10,000s paired images, our method is experimentally unsupervised and can be trained solely on a few hundred regions of interest. We demonstrate its performance on light-sheet microscopy with propagation-invariant Airy beams in oocytes, preimplantation embryos and excised brain tissue, as well as illustrate its utility for Bessel-beam LSM. This method aims to democratise learned methods for deconvolution, as it does not require data acquisition outwith the conventional imaging protocol.

CORE (COnnecting REpositories)