Share Email Print

Proceedings Paper

Quantitative phase microscopy using deep neural networks
Author(s): Shuai Li; Ayan Sinha; Justin Lee; George Barbastathis
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Deep learning has been proven to achieve ground-breaking accuracy in various tasks. In this paper, we implemented a deep neural network (DNN) to achieve phase retrieval in a wide-field microscope. Our DNN utilized the residual neural network (ResNet) architecture and was trained using the data generated by a phase SLM. The results showed that our DNN was able to reconstruct the profile of the phase target qualitatively. In the meantime, large error still existed, which indicated that our approach still need to be improved.

Paper Details

Date Published: 23 February 2018
PDF: 9 pages
Proc. SPIE 10503, Quantitative Phase Imaging IV, 105032D (23 February 2018); doi: 10.1117/12.2289056
Show Author Affiliations
Shuai Li, Massachusetts Institute of Technology (United States)
Ayan Sinha, Massachusetts Institute of Technology (United States)
Justin Lee, Massachusetts Institute of Technology (United States)
George Barbastathis, Massachusetts Institute of Technology (United States)
Singapore-MIT Alliance for Research and Technology (SMART) Ctr. (Singapore)

Published in SPIE Proceedings Vol. 10503:
Quantitative Phase Imaging IV
Gabriel Popescu; YongKeun Park, Editor(s)

© SPIE. Terms of Use
Back to Top