Quantitative phase microscopy using deep neural networks
Author(s)Li, Shuai; Sinha, Ayan T; Lee, Justin; Barbastathis, George
MetadataShow full item record
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.
DepartmentInstitute for Medical Engineering and Science; Massachusetts Institute of Technology. Department of Mechanical Engineering
Quantitative Phase Imaging IV
Li, Shuai, et al. “Quantitative Phase Microscopy Using Deep Neural Networks.” Quantitative Phase Imaging IV, 27 January, - February 1, 2018, San Francisco, California, edited by Gabriel Popescu and YongKeun Park, SPIE, 2018, p. 84. © SPIE.
Final published version