دورية أكاديمية
أعرض في EDS

Artefact removal in ground truth deficient fluctuations-based nanoscopy images using deep learning.

التفاصيل البيبلوغرافية
العنوان: Artefact removal in ground truth deficient fluctuations-based nanoscopy images using deep learning.
المؤلفون: Jadhav S; Indian Institute of Technology (Indian School of Mines), Dhanbad 826004, India., Acuña S; Department of Physics and Technology, UiT The Arctic University of Norway, Tromsø, Norway., Opstad IS; Department of Physics and Technology, UiT The Arctic University of Norway, Tromsø, Norway., Singh Ahluwalia B; Department of Physics and Technology, UiT The Arctic University of Norway, Tromsø, Norway., Agarwal K; Department of Physics and Technology, UiT The Arctic University of Norway, Tromsø, Norway., Prasad DK; Department of Computer Science, UiT The Arctic University of Norway, Tromsø, Norway.
المصدر: Biomedical optics express [Biomed Opt Express] 2020 Dec 08; Vol. 12 (1), pp. 191-210. Date of Electronic Publication: 2020 Dec 08 (Print Publication: 2021).
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Optica Publishing Group Country of Publication: United States NLM ID: 101540630 Publication Model: eCollection Cited Medium: Print ISSN: 2156-7085 (Print) Linking ISSN: 21567085 NLM ISO Abbreviation: Biomed Opt Express Subsets: PubMed not MEDLINE
أسماء مطبوعة: Publication: Washington, DC : Optica Publishing Group
Original Publication: Washington, DC : Optical Society of America
مستخلص: Image denoising or artefact removal using deep learning is possible in the availability of supervised training dataset acquired in real experiments or synthesized using known noise models. Neither of the conditions can be fulfilled for nanoscopy (super-resolution optical microscopy) images that are generated from microscopy videos through statistical analysis techniques. Due to several physical constraints, a supervised dataset cannot be measured. Further, the non-linear spatio-temporal mixing of data and valuable statistics of fluctuations from fluorescent molecules that compete with noise statistics. Therefore, noise or artefact models in nanoscopy images cannot be explicitly learned. Here, we propose a robust and versatile simulation-supervised training approach of deep learning auto-encoder architectures for the highly challenging nanoscopy images of sub-cellular structures inside biological samples. We show the proof of concept for one nanoscopy method and investigate the scope of generalizability across structures, and nanoscopy algorithms not included during simulation-supervised training. We also investigate a variety of loss functions and learning models and discuss the limitation of existing performance metrics for nanoscopy images. We generate valuable insights for this highly challenging and unsolved problem in nanoscopy, and set the foundation for the application of deep learning problems in nanoscopy for life sciences.
Competing Interests: Authors declare no conflicts of interest.
(© 2020 Optical Society of America under the terms of the OSA Open Access Publishing Agreement.)
References: Nat Methods. 2013 Feb;10(2):96-7. (PMID: 23361087)
Opt Express. 2020 Nov 9;28(23):34434-34449. (PMID: 33182913)
Annu Rev Phys Chem. 2012;63:595-617. (PMID: 22404588)
Nat Struct Mol Biol. 2010 Nov;17(11):1318-23. (PMID: 20935633)
Nat Protoc. 2017 Jun;12(6):1198-1228. (PMID: 28518172)
PLoS One. 2016 Sep 01;11(9):e0161602. (PMID: 27583365)
BMC Biol. 2013 Jun 24;11:71. (PMID: 23800141)
EMBO J. 2011 Aug 31;30(17):3481-500. (PMID: 21878991)
IEEE Trans Image Process. 2004 Apr;13(4):600-12. (PMID: 15376593)
Science. 2006 Sep 15;313(5793):1642-5. (PMID: 16902090)
Sci Rep. 2018 Mar 21;8(1):4988. (PMID: 29563529)
PLoS One. 2014 Apr 30;9(4):e94807. (PMID: 24788039)
J Microsc. 2000 May;198(Pt 2):82-7. (PMID: 10810003)
Sci Rep. 2019 May 22;9(1):7725. (PMID: 31118450)
Opt Lett. 1994 Jun 1;19(11):780-2. (PMID: 19844443)
Nature. 1997 Jul 24;388(6640):355-8. (PMID: 9237752)
G3 (Bethesda). 2017 May 5;7(5):1385-1392. (PMID: 28391243)
Sci Rep. 2019 Aug 27;9(1):12419. (PMID: 31455826)
Traffic. 2020 Jan;21(1):60-75. (PMID: 31808235)
IEEE Trans Pattern Anal Mach Intell. 1986 Jun;8(6):679-98. (PMID: 21869365)
Proc Natl Acad Sci U S A. 2020 Jan 7;117(1):60-67. (PMID: 31871202)
Biomed Opt Express. 2019 Jul 10;10(8):3860-3874. (PMID: 31452980)
Opt Express. 2018 Jul 9;26(14):18238-18269. (PMID: 30114104)
Proc Natl Acad Sci U S A. 2009 Dec 29;106(52):22287-92. (PMID: 20018714)
PLoS Comput Biol. 2018 Dec 3;14(12):e1006628. (PMID: 30507940)
J Opt Soc Am A Opt Image Sci Vis. 2017 Jun 1;34(6):1029-1034. (PMID: 29036087)
Nat Commun. 2016 Dec 09;7:13752. (PMID: 27934858)
Nat Biotechnol. 2018 Jun;36(5):460-468. (PMID: 29658943)
Opt Express. 2020 Sep 14;28(19):27736-27763. (PMID: 32988061)
J Opt Soc Am A. 1992 Jan;9(1):154-66. (PMID: 1738047)
Sci Rep. 2016 Feb 17;6:20640. (PMID: 26884148)
Proc Natl Acad Sci U S A. 2017 Mar 14;114(11):2910-2915. (PMID: 28265065)
Nat Methods. 2019 Jan;16(1):103-110. (PMID: 30559434)
Nat Methods. 2006 Oct;3(10):793-5. (PMID: 16896339)
Nature. 1982 Jul 8;298(5870):131-5. (PMID: 7201078)
ACS Cent Sci. 2020 Aug 26;6(8):1421-1430. (PMID: 32875083)
Sci Rep. 2017 Jun 30;7(1):4445. (PMID: 28667336)
Trends Cell Biol. 1999 Apr;9(4):154-9. (PMID: 10203794)
Biophys J. 2011 Dec 21;101(12):2855-70. (PMID: 22208184)
Nat Methods. 2011 Dec 04;9(2):195-200. (PMID: 22138825)
Nat Commun. 2016 Aug 12;7:12471. (PMID: 27514992)
تواريخ الأحداث: Date Created: 20210304 Latest Revision: 20210305
رمز التحديث: 20231215
مُعرف محوري في PubMed: PMC7899514
DOI: 10.1364/BOE.410617
PMID: 33659075
قاعدة البيانات: MEDLINE
الوصف
تدمد:2156-7085
DOI:10.1364/BOE.410617