Share Email Print

Proceedings Paper

Towards scalable and reliable deep learning based phase microscopy using intensity-only measurements (Conference Presentation)
Author(s): Lei Tian

Paper Abstract

I will discuss our recent efforts in building deep learning based phase imaging techniques that provide improved scalability and reliability. I will demonstrate a physics guided deep learning imaging approach that enables designing highly efficient multiplexed data acquisition schemes and fully leverages the powerful deep learning-based inverse problem framework. We apply this approach to large space-bandwidth product phase microscopy and intensity diffraction tomography, all implemented on a simple LED-array based computational microscopy platform. I will discuss an uncertainty quantification framework to assess the reliability of the deep learning predictions. Quantifying the uncertainty provides per-pixel evaluation of the prediction’s confidence level as well as the quality of the model and dataset.

Paper Details

Date Published: 11 March 2020
Proc. SPIE 11249, Quantitative Phase Imaging VI, 1124912 (11 March 2020); doi: 10.1117/12.2548615
Show Author Affiliations
Lei Tian, Boston Univ. (United States)

Published in SPIE Proceedings Vol. 11249:
Quantitative Phase Imaging VI
Yang Liu; Gabriel Popescu; YongKeun Park, 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?