Share Email Print

Proceedings Paper

Deep learning based computational microscopy in scattering media (Conference Presentation)
Author(s): Lei Tian

Paper Abstract

I will discuss our efforts in developing computational microscopy techniques that can provide improved robustness and scalability to multiple scattering problems. First, I will discuss a new model for quantifying the effects of anisotropic scattering on image quality degradation. In particular, I will illustrate how to quantitatively relate the macroscopic scattering properties to the microscopic parameters used in the model. Next, I will discuss a deep learning approach to invert the effect of scattering. Particular emphasis will be placed on the scalability of this approach and how the model can be generalizable to different objects/media by extracting statistically invariant information.

Paper Details

Date Published: 11 March 2020
Proc. SPIE 11248, Adaptive Optics and Wavefront Control for Biological Systems VI, 112480A (11 March 2020); doi: 10.1117/12.2550412
Show Author Affiliations
Lei Tian, Boston Univ. (United States)

Published in SPIE Proceedings Vol. 11248:
Adaptive Optics and Wavefront Control for Biological Systems VI
Thomas G. Bifano; Sylvain Gigan; Na Ji, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?