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.
© 2023 The Author(s)
PDF Article | Presentation VideoMore Like This
Dongli Xu, Jun B. Ding, and Leilei Peng
BW4B.3 Optics and the Brain (BRAIN) 2023
Tom Vettenburg
NM3C.2 Novel Techniques in Microscopy (NTM) 2023
Kevin T. Takasaki, Olga Gliko, Russel Torres, Pooja Balaram, Ayana Hellevik, Emily Turschak, Bryan MacLennan, Sam Kinn, Eric Perlman, and R. Clay Reid
BW1B.2 Optics and the Brain (BRAIN) 2023