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.
Bibliographical noteFunding Information:
We would like to acknowledge Federico Gasparoli for early support in constructing the imaging system and providing multiphoton data, and Mirna Merkler for preparing the excised mouse brain section. We acknowledge Erik Linder-Norén’s implementations of GANs in PyTorch ( https://github.com/eriklindernoren/PyTorch-GAN ) that instantiated the code developed in this project. This project was funded by the UK Engineering and Physical Sciences Research Council (grants EP/P030017/1 and EP/R004854/1), and has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement (EC-GA 871212) and H2020 FETOPEN project "Dynamic” (EC-GA 863203). P.W. was supported by the 1851 Research Fellowship from the Royal Commission. KRD was supported by a Mid-Career Fellowship from the Hospital Research Foundation (C-MCF-58-2019). K.D. acknowledges support from the Australian Research Council through a Laureate Fellowship. S.S. was funded by BBSRC (BB/M00905X/1).
© 2022, The Author(s).
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Atomic and Molecular Physics, and Optics