دورية أكاديمية
أعرض في EDS

Patching-based deep-learning model for the inpainting of Bragg coherent diffraction patterns affected by detector gaps.

التفاصيل البيبلوغرافية
العنوان: Patching-based deep-learning model for the inpainting of Bragg coherent diffraction patterns affected by detector gaps.
المؤلفون: Masto M; ESRF, The European Synchrotron, 71 Avenue des Martyrs, Grenoble, France.; Univ. Grenoble Alpes, Grenoble, France., Favre-Nicolin V; ESRF, The European Synchrotron, 71 Avenue des Martyrs, Grenoble, France.; Univ. Grenoble Alpes, Grenoble, France., Leake S; ESRF, The European Synchrotron, 71 Avenue des Martyrs, Grenoble, France., Schülli T; ESRF, The European Synchrotron, 71 Avenue des Martyrs, Grenoble, France., Richard MI; Univ. Grenoble Alpes, CEA Grenoble, IRIG, MEM, NRS, 17 Avenue des Martyrs, Grenoble, France., Bellec E; Univ. Grenoble Alpes, CEA Grenoble, IRIG, MEM, NRS, 17 Avenue des Martyrs, Grenoble, France.
المصدر: Journal of applied crystallography [J Appl Crystallogr] 2024 Jun 18; Vol. 57 (Pt 4), pp. 966-974. Date of Electronic Publication: 2024 Jun 18 (Print Publication: 2024).
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: Wiley Online Library Country of Publication: United States NLM ID: 9876190 Publication Model: eCollection Cited Medium: Print ISSN: 0021-8898 (Print) Linking ISSN: 00218898 NLM ISO Abbreviation: J Appl Crystallogr Subsets: PubMed not MEDLINE
أسماء مطبوعة: Publication: [Malden, MA] : Wiley Online Library
Original Publication: Copenhagen, Munksgaard International Booksellers and Publishers.
مستخلص: A deep-learning algorithm is proposed for the inpainting of Bragg coherent diffraction imaging (BCDI) patterns affected by detector gaps. These regions of missing intensity can compromise the accuracy of reconstruction algorithms, inducing artefacts in the final result. It is thus desirable to restore the intensity in these regions in order to ensure more reliable reconstructions. The key aspect of the method lies in the choice of training the neural network with cropped sections of diffraction data and subsequently patching the predictions generated by the model along the gap, thus completing the full diffraction peak. This approach enables access to a greater amount of experimental data for training and offers the ability to average overlapping sections during patching. As a result, it produces robust and dependable predictions for experimental data arrays of any size. It is shown that the method is able to remove gap-induced artefacts on the reconstructed objects for both simulated and experimental data, which becomes essential in the case of high-resolution BCDI experiments.
(© Matteo Masto et al. 2024.)
References: Nature. 2006 Jul 6;442(7098):63-6. (PMID: 16823449)
Nat Commun. 2018 Aug 24;9(1):3422. (PMID: 30143615)
Nat Commun. 2021 Sep 10;12(1):5385. (PMID: 34508094)
Nat Mater. 2011 Sep 25;10(11):862-6. (PMID: 21946612)
Nat Mater. 2009 Apr;8(4):291-8. (PMID: 19308088)
Nat Commun. 2019 Nov 26;10(1):5365. (PMID: 31772159)
Nano Lett. 2014 Sep 10;14(9):5123-7. (PMID: 25141157)
Opt Lett. 1978 Jul 1;3(1):27-9. (PMID: 19684685)
Opt Express. 2010 Aug 30;18(18):18598-614. (PMID: 20940752)
Acta Crystallogr D Biol Crystallogr. 2000 Oct;56(Pt 10):1312-5. (PMID: 10998627)
J Appl Crystallogr. 2022 May 16;55(Pt 3):621-625. (PMID: 35719306)
J Synchrotron Radiat. 2019 Mar 1;26(Pt 2):571-584. (PMID: 30855270)
Proc Natl Acad Sci U S A. 2001 Jun 5;98(12):6641-5. (PMID: 11390993)
ACS Nano. 2024 May 28;18(21):13517-13527. (PMID: 38753950)
IUCrJ. 2017 May 24;4(Pt 4):455-465. (PMID: 28875032)
Opt Express. 2022 Feb 28;30(5):6886-6906. (PMID: 35299464)
Sci Rep. 2018 Nov 8;8(1):16520. (PMID: 30410034)
Rev Sci Instrum. 2007 Jan;78(1):011301. (PMID: 17503899)
J Appl Crystallogr. 2022 Feb 01;55(Pt 1):122-132. (PMID: 35145358)
Phys Rev Lett. 2019 Dec 13;123(24):246001. (PMID: 31922849)
J Appl Crystallogr. 2022 Sep 28;55(Pt 5):1277-1288. (PMID: 36249508)
Sci Rep. 2019 Nov 22;9(1):17357. (PMID: 31758040)
Nat Mater. 2023 Jun;22(6):754-761. (PMID: 37095227)
Sci Rep. 2017 Apr 06;7:45993. (PMID: 28383028)
IUCrJ. 2021 Jan 01;8(Pt 1):12-21. (PMID: 33520239)
IEEE Trans Image Process. 2004 Apr;13(4):600-12. (PMID: 15376593)
J Phys Chem Lett. 2016 Aug 4;7(15):3008-13. (PMID: 27429219)
Nat Commun. 2022 May 30;13(1):3003. (PMID: 35637233)
فهرسة مساهمة: Keywords: Bragg coherent diffraction imaging; deep learning; image inpainting
تواريخ الأحداث: Date Created: 20240807 Latest Revision: 20240808
رمز التحديث: 20240808
مُعرف محوري في PubMed: PMC11299604
DOI: 10.1107/S1600576724004163
PMID: 39108812
قاعدة البيانات: MEDLINE
الوصف
تدمد:0021-8898
DOI:10.1107/S1600576724004163