Abstract
Multispectral quantitative phase imaging (MS-QPI) is a high-contrast label-free technique for morphological imaging of the specimens. The aim of the present study is to extract spectral dependent quantitative information in single-shot using a highly spatially sensitive digital holographic microscope assisted by a deep neural network. There are three different wavelengths used in our method: $\lambda = {532}$, 633, and 808 nm. The first step is to get the interferometric data for each wavelength. The acquired datasets are used to train a generative adversarial network to generate multispectral (MS) quantitative phase maps from a single input interferogram. The network was trained and validated on two different samples: the optical waveguide and MG63 osteosarcoma cells. Validation of the present approach is performed by comparing the predicted MS phase maps with numerically reconstructed (${\rm FT} + {\rm TIE}$) phase maps and quantifying with different image quality assessment metrices.
© 2023 Optica Publishing Group
Full Article | PDF ArticleMore Like This
Yu-Chun Lin, Yuan Luo, Ying-Ju Chen, Huei-Wen Chen, Tai-Horng Young, and Hsuan-Ming Huang
Biomed. Opt. Express 14(7) 3458-3468 (2023)
Naru Yoneda, Shunsuke Kakei, Koshi Komuro, Aoi Onishi, Yusuke Saita, and Takanori Nomura
Appl. Opt. 60(28) 8802-8808 (2021)
Eunjung Min, Nurbolat Aimakov, Sangjin Lee, Sungbea Ban, Hyunmo Yang, Yujin Ahn, Joon S. You, and Woonggyu Jung
Biomed. Opt. Express 14(5) 2068-2079 (2023)