Single-shot quantitative phase contrast imaging based on deep learning

Yu-Chun Lin; Yuan Luo; Ying-Ju Chen; Huei-Wen Chen; Tai-Horng Young; Hsuan-Ming Huang

doi:10.1364/BOE.493828

Single-shot quantitative phase contrast imaging based on deep learning

Biomed Opt Express. 2023 Jun 20;14(7):3458-3468. doi: 10.1364/BOE.493828. eCollection 2023 Jul 1.

Authors

Yu-Chun Lin¹, Yuan Luo¹, Ying-Ju Chen¹, Huei-Wen Chen², Tai-Horng Young³, Hsuan-Ming Huang¹

Affiliations

¹ Institute of Medical Device and Imaging, College of Medicine, National Taiwan University, No. 1, Sec. 1, Jen Ai Rd., Zhongzheng Dist., Taipei City 100, Taiwan.
² Graduate Institute of Toxicology, College of Medicine, National Taiwan University, No. 1, Sec. 1, Jen Ai Rd., Zhongzheng Dist., Taipei City 100, Taiwan.
³ Department of Biomedical Engineering, National Taiwan University, No. 1, Sec. 1, Jen Ai Rd., Zhongzheng Dist., Taipei City 100, Taiwan.

Abstract

Quantitative differential phase-contrast (DPC) imaging is one of the commonly used methods for phase retrieval. However, quantitative DPC imaging requires several pairwise intensity measurements, which makes it difficult to monitor living cells in real-time. In this study, we present a single-shot quantitative DPC imaging method based on the combination of deep learning (DL) and color-encoded illumination. Our goal is to train a model that can generate an isotropic quantitative phase image (i.e., target) directly from a single-shot intensity measurement (i.e., input). The target phase image was reconstructed using a linear-gradient pupil with two-axis measurements, and the model input was the measured color intensities obtained from a radially asymmetric color-encoded illumination pattern. The DL-based model was trained, validated, and tested using thirteen different cell lines. The total number of training, validation, and testing images was 264 (10 cells), 10 (1 cell), and 40 (2 cells), respectively. Our results show that the DL-based phase images are visually similar to the ground-truth phase images and have a high structural similarity index (>0.98). Moreover, the phase difference between the ground-truth and DL-based phase images was smaller than 13%. Our study shows the feasibility of using DL to generate quantitative phase imaging from a single-shot intensity measurement.