Optimizing Imaging Throughput and Resolution in Light Sheet Microscopy Using Deep-learning-based Beam Shape Translation
- 1 January 2023
- conference paper
- Published by Optica Publishing Group
- p. NTu1C.3
Abstract
A conditional generative adversarial network (cGAN) approach to optimize resolution or contrast and field-of-view (FOV) in beam-scanned light sheet microscopy by beam shape translation is demonstrated. Large FOV images acquired with collimated (pencil) beam (weakly-focused) illumination are used to predict large FOV, but higher contrast, images mimicking Gaussian-beam (highly focused) illumination. In this way, imaging throughput and resolution is improved.Keywords
This publication has 3 references indexed in Scilit:
- Rapid three-dimensional isotropic imaging of living cells using Bessel beam plane illuminationNature Methods, 2011
- Comparison of Bessel and Gaussian beamsOptics Letters, 1988
- Diffraction-free beamsPhysical Review Letters, 1987