Open AccessAutomated phase unwrapping in digital holography with deep learning
Author(s) -
Seonghwan Park,
You-Hyun Kim,
Inkyu Moon
Publication year - 2021
Publication title -
biomedical optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.362
H-Index - 86
ISSN - 2156-7085
DOI - 10.1364/boe.440338
Subject(s) - digital holography , computer science , holography , image translation , artificial intelligence , phase (matter) , deep learning , computer vision , image (mathematics) , discontinuity (linguistics) , digital imaging , generative grammar , phase unwrapping , image processing , digital holographic microscopy , digital image , optics , mathematics , interferometry , physics , mathematical analysis , quantum mechanics
Digital holography can provide quantitative phase images related to the morphology and content of biological samples. After the numerical image reconstruction, the phase values are limited between -π and π; thus, discontinuity may occur due to the modulo 2π operation. We propose a new deep learning model that can automatically reconstruct unwrapped focused-phase images by combining digital holography and a Pix2Pix generative adversarial network (GAN) for image-to-image translation. Compared with numerical phase unwrapping methods, the proposed GAN model overcomes the difficulty of accurate phase unwrapping due to abrupt phase changes and can perform phase unwrapping at a twice faster rate. We show that the proposed model can generalize well to different types of cell images and has high performance compared to recent U-net models. The proposed method can be useful in observing the morphology and movement of biological cells in real-time applications.