Holo-UNet: hologram-to-hologram neural network restoration for high fidelity low light quantitative phase imaging of live cells

Simple item page
dc.contributor.authorZhang, Z.
dc.contributor.authorZheng, Y.
dc.contributor.authorXu, T.
dc.contributor.authorUpadhya, A.
dc.contributor.authorLim, Y.J.
dc.contributor.authorMathews, A.
dc.contributor.authorXie, L.
dc.contributor.authorLee, W.M.
dc.date.issued2020
dc.description.abstractIntensity shot noise in digital holograms distorts the quality of the phase images after phase retrieval, limiting the usefulness of quantitative phase microscopy (QPM) systems in long term live cell imaging. In this paper, we devise a hologram-to-hologram neural network, Holo-UNet, that restores high quality digital holograms under high shot noise conditions (submW/cm2 intensities) at high acquisition rates (sub-milliseconds). In comparison to current phase recovery methods, Holo-UNet denoises the recorded hologram, and so prevents shot noise from propagating through the phase retrieval step that in turn adversely affects phase and intensity images. Holo-UNet was tested on 2 independent QPM systems without any adjustment to the hardware setting. In both cases, Holo-UNet outperformed existing phase recovery and block-matching techniques by ∼ 1.8 folds in phase fidelity as measured by SSIM. Holo-UNet is immediately applicable to a wide range of other high-speed interferometric phase imaging techniques. The network paves the way towards the expansion of high-speed low light QPM biological imaging with minimal dependence on hardware constraints.
dc.description.statementofresponsibilityZhiduo Zhang, Yujie Zheng, Tienan Xu, Avinash Upadhya, Yean Jin Lim, Alexander Mathews, Lexing Xie, And Woei Ming Lee
dc.identifier.citationBiomedical Optics Express, 2020; 11(10):5478-5487
dc.identifier.doi10.1364/boe.395302
dc.identifier.issn2156-7085
dc.identifier.issn2156-7085
dc.identifier.orcidUpadhya, A. [0000-0003-0841-303X]
dc.identifier.urihttps://hdl.handle.net/2440/138045
dc.language.isoen
dc.publisherOptica Publishing Group
dc.relation.granthttp://purl.org/au-research/grants/arc/DE160100843
dc.relation.granthttp://purl.org/au-research/grants/arc/DP190100039
dc.relation.granthttp://purl.org/au-research/grants/arc/DP200100364
dc.rights© 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement
dc.source.urihttps://doi.org/10.1364/boe.395302
dc.titleHolo-UNet: hologram-to-hologram neural network restoration for high fidelity low light quantitative phase imaging of live cells
dc.typeJournal article
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
hdl_138045.pdf
Size:
4.15 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

Biochemistry publications