High-resolution limited-angle phase tomography of dense layered objects using deep neural networks.
deep learning
imaging through scattering media
tomography
Journal
Proceedings of the National Academy of Sciences of the United States of America
ISSN: 1091-6490
Titre abrégé: Proc Natl Acad Sci U S A
Pays: United States
ID NLM: 7505876
Informations de publication
Date de publication:
01 10 2019
01 10 2019
Historique:
pubmed:
19
9
2019
medline:
19
9
2019
entrez:
19
9
2019
Statut:
ppublish
Résumé
We present a machine learning-based method for tomographic reconstruction of dense layered objects, with range of projection angles limited to [Formula: see text] Whereas previous approaches to phase tomography generally require 2 steps, first to retrieve phase projections from intensity projections and then to perform tomographic reconstruction on the retrieved phase projections, in our work a physics-informed preprocessor followed by a deep neural network (DNN) conduct the 3-dimensional reconstruction directly from the intensity projections. We demonstrate this single-step method experimentally in the visible optical domain on a scaled-up integrated circuit phantom. We show that even under conditions of highly attenuated photon fluxes a DNN trained only on synthetic data can be used to successfully reconstruct physical samples disjoint from the synthetic training set. Thus, the need for producing a large number of physical examples for training is ameliorated. The method is generally applicable to tomography with electromagnetic or other types of radiation at all bands.
Identifiants
pubmed: 31527279
pii: 1821378116
doi: 10.1073/pnas.1821378116
pmc: PMC6778227
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
19848-19856Informations de copyright
Copyright © 2019 the Author(s). Published by PNAS.
Déclaration de conflit d'intérêts
The authors declare no conflict of interest.
Références
IEEE Trans Image Process. 2009 Nov;18(11):2419-34
pubmed: 19635705
Br J Radiol. 1973 Dec;46(552):1023-47
pubmed: 4757353
Phys Med Biol. 2003 Oct 7;48(19):R65-106
pubmed: 14579853
IEEE Trans Med Imaging. 2018 Jun;37(6):1440-1453
pubmed: 29870372
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
Appl Opt. 1972 Jan 1;11(1):205-7
pubmed: 20111484
Opt Express. 2018 May 28;26(11):14678-14688
pubmed: 29877404
Nature. 1968 Jan 13;217(5124):130-4
pubmed: 23610788
Opt Express. 2018 Oct 29;26(22):29340-29352
pubmed: 30470099
Opt Express. 2013 Jun 17;21(12):14430-41
pubmed: 23787630
Sci Rep. 2017 Dec 19;7(1):17865
pubmed: 29259269
IEEE Trans Pattern Anal Mach Intell. 2016 Feb;38(2):295-307
pubmed: 26761735
IEEE Trans Image Process. 2017 Sep;26(9):4509-4522
pubmed: 28641250
IEEE Trans Med Imaging. 2018 Feb;37(2):491-503
pubmed: 29035212
Phys Rev Lett. 2018 Dec 14;121(24):243902
pubmed: 30608745
Light Sci Appl. 2018 Feb 23;7:17141
pubmed: 30839514
Nat Methods. 2007 Sep;4(9):717-9
pubmed: 17694065
Nature. 1970 May 2;226(5244):421-5
pubmed: 4314822
Br J Radiol. 1973 Dec;46(552):1016-22
pubmed: 4757352