Share Email Print
cover

Proceedings Paper

High-speed optical diffraction tomography (ODT) with deep-learning approach (Conference Presentation)

Paper Abstract

Optical diffraction tomography (ODT) is a powerful label-free three-dimensional (3D) quantitative imaging technique. However, current ODT modalities require around 50 different illumination angles to reconstruct the 3D refraction index (RI) map, which limits its imaging speed and prohibit it from further applications. Here we propose a deep-learning approach to reduce the number of illumination angles and improve the imaging speed of ODT. With 3D Unet architecture and large training data of different species of cells, we can decrease the number of illumination angles from 49 to 5 with similar reconstruction performance, which empowers ODT the capability to reveal high-speed biological dynamics.

Paper Details

Date Published: 11 March 2020
PDF
Proc. SPIE 11249, Quantitative Phase Imaging VI, 1124906 (11 March 2020); doi: 10.1117/12.2546172
Show Author Affiliations
Baoliang Ge, Massachusetts Institute of Technology (United States)
Mo Deng, Massachusetts Institute of Technology (United States)
George Barbastathis, Massachusetts Institute of Technology (United States)
Peter T. C. So, Massachusetts Institute of Technology (United States)
Renjie Zhou, The Chinese Univ. of Hong Kong (China)
Zahid Yaqoob, Massachusetts Institute of Technology (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
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray