{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T16:59:46Z","timestamp":1784307586951,"version":"3.55.0"},"reference-count":56,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T00:00:00Z","timestamp":1630022400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T00:00:00Z","timestamp":1630022400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006224","name":"Argonne National Laboratory","doi-asserted-by":"crossref","award":["Contract No. DE-AC02-06CH11357"],"award-info":[{"award-number":["Contract No. DE-AC02-06CH11357"]}],"id":[{"id":"10.13039\/100006224","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Joint ptycho-tomography is a powerful computational imaging framework to recover the refractive properties of a 3D object while relaxing the requirements for probe overlap that is common in conventional phase retrieval. We use an augmented Lagrangian scheme for formulating the constrained optimization problem and employ an alternating direction method of multipliers (ADMM) for the joint solution. ADMM allows the problem to be split into smaller and computationally more efficient subproblems: ptychographic phase retrieval, tomographic reconstruction, and regularization of the solution. We extend our ADMM framework with plug-and-play (PnP) denoisers by replacing the regularization subproblem with a general denoising operator based on machine learning. While the PnP framework enables integrating such learned priors as denoising operators, tuning of the denoiser prior remains challenging. To overcome this challenge, we propose a denoiser parameter to control the effect of the denoiser and to accelerate the solution. In our simulations, we demonstrate that our proposed framework with parameter tuning and learned priors generates high-quality reconstructions under limited and noisy measurement data.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac1d35","type":"journal-article","created":{"date-parts":[[2021,8,12]],"date-time":"2021-08-12T22:41:32Z","timestamp":1628808092000},"page":"045017","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Joint ptycho-tomography with deep generative priors"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1077-948X","authenticated-orcid":false,"given":"Selin","family":"Aslan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengchun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9999-169X","authenticated-orcid":false,"given":"Viktor","family":"Nikitin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tekin","family":"Bicer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1077-948X","authenticated-orcid":false,"given":"Sven","family":"Leyffer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0080-8101","authenticated-orcid":false,"given":"Do\u011fa","family":"G\u00fcrsoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,8,27]]},"reference":[{"key":"mlstac1d35bib1","first-page":"pp 265","article-title":"TensorFlow: a system for large-scale machine learning","author":"Abadi","year":"2016"},{"key":"mlstac1d35bib2","doi-asserted-by":"publisher","first-page":"9128","DOI":"10.1364\/OE.27.009128","article-title":"Joint ptycho-tomography reconstruction through alternating direction method of multipliers","volume":"27","author":"Aslan","year":"2019","journal-title":"Opt. Express"},{"key":"mlstac1d35bib3","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s40679-017-0040-7","article-title":"Trace: a high-throughput tomographic reconstruction engine for large-scale datasets","volume":"3","author":"Bicer","year":"2017","journal-title":"Adv. Struct. Chem. Imaging"},{"key":"mlstac1d35bib4","first-page":"pp 289","author":"Bicer","year":"2015"},{"key":"mlstac1d35bib5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000016","article-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","volume":"3","author":"Boyd","year":"2011","journal-title":"Found. Trends Mach. Learn."},{"key":"mlstac1d35bib6","doi-asserted-by":"publisher","first-page":"2001","DOI":"10.1137\/17M1122451","article-title":"Plug-and-play unplugged: optimization-free reconstruction using consensus equilibrium","volume":"11","author":"Buzzard","year":"2018","journal-title":"SIAM J. Imaging Sci."},{"key":"mlstac1d35bib7","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/TCI.2016.2629286","article-title":"Plug-and-play ADMM for image restoration: fixed-point convergence and applications","volume":"3","author":"Chan","year":"2017","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"mlstac1d35bib8","first-page":"pp 5888","article-title":"One network to solve them all\u2014solving linear inverse problems using deep projection models","author":"Chang","year":"2017"},{"key":"mlstac1d35bib9","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1107\/S1600577517001928","article-title":"XDesign: an open-source software package for designing x-ray imaging phantoms and experiments","volume":"24","author":"Ching","year":"2017","journal-title":"J. Synchrotron Radiat."},{"key":"mlstac1d35bib10","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","article-title":"Image denoising by sparse 3-D transform-domain collaborative filtering","volume":"16","author":"Dabov","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"mlstac1d35bib11","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1137\/S1052623497318992","article-title":"A nonlinear conjugate gradient method with a strong global convergence property","volume":"10","author":"Dai","year":"1999","journal-title":"SIAM J. Optim."},{"key":"mlstac1d35bib12","first-page":"pp 248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"mlstac1d35bib13","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature09419","article-title":"Ptychographic x-ray computed tomography at the nanoscale","volume":"467","author":"Dierolf","year":"2010","journal-title":"Nature"},{"key":"mlstac1d35bib14","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1126\/sciadv.aay3700","article-title":"Three dimensions, two microscopes, one code: automatic differentiation for x-ray nanotomography beyond the depth of focus limit","volume":"6","author":"Du","year":"2020","journal-title":"Sci. Adv."},{"key":"mlstac1d35bib15","doi-asserted-by":"publisher","first-page":"3736","DOI":"10.1109\/TIP.2006.881969","article-title":"Image denoising via sparse and redundant representations over learned dictionaries","volume":"15","author":"Elad","year":"2006","journal-title":"IEEE Trans. Image Process."},{"key":"mlstac1d35bib16","first-page":"pp 2672","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014"},{"key":"mlstac1d35bib17","first-page":"pp 2862","article-title":"Weighted nuclear norm minimization with application to image denoising","author":"Gu","year":"2014"},{"key":"mlstac1d35bib18","doi-asserted-by":"publisher","first-page":"3169","DOI":"10.1364\/OL.42.003169","article-title":"Direct coupling of tomography and ptychography","volume":"42","author":"G\u00fcrsoy","year":"2017","journal-title":"Opt. Lett."},{"key":"mlstac1d35bib19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-12141-9","article-title":"Rapid alignment of nanotomography data using joint iterative reconstruction and reprojection","volume":"7","author":"Gursoy","year":"2017","journal-title":"Sci. Rep."},{"key":"mlstac1d35bib20","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1109\/TMI.2018.2865202","article-title":"Optimizing a parameterized plug-and-play ADMM for iterative low-dose CT reconstruction","volume":"38","author":"He","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstac1d35bib21","volume":"vol 2","author":"Helgason","year":"1999"},{"key":"mlstac1d35bib22","first-page":"pp 1","article-title":"Memxct: memory-centric x-ray CT reconstruction with massive parallelization","author":"Hidayeto\u011flu","year":"2019"},{"key":"mlstac1d35bib23","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1107\/S0567739469001045","article-title":"Beugung im inhomogenen Prim\u00e4rstrahlwellenfeld, I: Prinzip einer Phasenmessung","volume":"25","author":"Hoppe","year":"1969","journal-title":"Acta Crystallogr. A"},{"key":"mlstac1d35bib24","article-title":"An introduction to complex differentials and complex differentiability","author":"Hunger","year":"2007"},{"key":"mlstac1d35bib25","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","article-title":"Deep convolutional neural network for inverse problems in imaging","volume":"26","author":"Jin","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"mlstac1d35bib26","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1364\/OPTICA.6.001282","article-title":"Coupled ptychography and tomography algorithm improves reconstruction of experimental data","volume":"6","author":"Kahnt","year":"2019","journal-title":"Optica"},{"key":"mlstac1d35bib27","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1109\/LSP.2017.2763583","article-title":"A plug-and-play priors approach for solving nonlinear imaging inverse problems","volume":"24","author":"Kamilov","year":"2017","journal-title":"IEEE Signal Process. Lett."},{"key":"mlstac1d35bib28","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstac1d35bib29","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1155\/2015\/104531","article-title":"Alternating direction method of multipliers for separable convex optimization of real functions in complex variables","volume":"104531","author":"Li","year":"2015","journal-title":"Math. Problems Eng."},{"key":"mlstac1d35bib30","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1364\/JOSAA.375595","article-title":"Tomogan: low-dose synchrotron x-ray tomography with generative adversarial networks","volume":"37","author":"Liu","year":"2020","journal-title":"J. Opt. Soc. Am. A"},{"key":"mlstac1d35bib31","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.ultramic.2012.06.001","article-title":"An annealing algorithm to correct positioning errors in ptychography","volume":"120","author":"Maiden","year":"2012","journal-title":"Ultramicroscopy"},{"key":"mlstac1d35bib32","article-title":"Deepred: deep image prior powered by red","author":"Mataev","year":"2019"},{"key":"mlstac1d35bib33","first-page":"pp 1781","article-title":"Learning proximal operators: using denoising networks for regularizing inverse imaging problems","author":"Meinhardt","year":"2017"},{"key":"mlstac1d35bib34","article-title":"prDeep: robust phase retrieval with a flexible deep network","author":"Metzler","year":"2018"},{"key":"mlstac1d35bib35","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/TCI.2021.3060915","article-title":"Distributed optimization for nonrigid nano-tomography","volume":"7","author":"Nikitin","year":"2021","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"mlstac1d35bib36","doi-asserted-by":"publisher","first-page":"2948","DOI":"10.1364\/OSAC.2.002948","article-title":"Photon-limited ptychography of 3D objects via Bayesian reconstruction","volume":"2","author":"Nikitin","year":"2019","journal-title":"OSA Continuum"},{"key":"mlstac1d35bib37","author":"Nocedal","year":"2006","edition":"2nd edn"},{"key":"mlstac1d35bib38","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.99.023801","article-title":"Direct three-dimensional tomographic reconstruction and phase retrieval of far-field coherent diffraction patterns","volume":"99","author":"Ramos","year":"2019","journal-title":"Phys. Rev. A"},{"key":"mlstac1d35bib39","doi-asserted-by":"publisher","first-page":"1804","DOI":"10.1137\/16M1102884","article-title":"The little engine that could: regularization by denoising (RED)","volume":"10","author":"Romano","year":"2017","journal-title":"SIAM J. Imaging Sci."},{"key":"mlstac1d35bib40","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.jvcir.2016.09.009","article-title":"Poisson inverse problems by the plug-and-play scheme","volume":"41","author":"Rond","year":"2016","journal-title":"J. Vis. Commun. Image Represent."},{"key":"mlstac1d35bib41","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/0167-2789(92)90242-F","article-title":"Nonlinear total variation based noise removal algorithms","volume":"60","author":"Rudin","year":"1992","journal-title":"Physica D"},{"key":"mlstac1d35bib42","first-page":"pp 5546","article-title":"Plug-and-play methods provably converge with properly trained denoisers","author":"Ryu","year":"2019"},{"key":"mlstac1d35bib43","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.1109\/TMI.2018.2832217","article-title":"3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-D trained network","volume":"37","author":"Shan","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstac1d35bib44","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"mlstac1d35bib45","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1109\/TCI.2016.2599778","article-title":"Plug-and-play priors for bright field electron tomography and sparse interpolation","volume":"2","author":"Sreehari","year":"2016","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"mlstac1d35bib46","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1109\/TCI.2019.2893568","article-title":"An online plug- and-play algorithm for regularized image reconstruction","volume":"5","author":"Sun","year":"2019","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"mlstac1d35bib47","first-page":"pp 7665","article-title":"Regularized fourier ptychography using an online plug-and-play algorithm","author":"Sun","year":"2019"},{"key":"mlstac1d35bib48","author":"Tikhonov","year":"1977"},{"key":"mlstac1d35bib49","doi-asserted-by":"publisher","first-page":"948","DOI":"10.1109\/JPROC.2010.2044010","article-title":"Computational methods for sparse solution of linear inverse problems","volume":"98","author":"Tropp","year":"2010","journal-title":"Proc. IEEE"},{"key":"mlstac1d35bib50","first-page":"pp 945","article-title":"Plug-and-play priors for model based reconstruction","author":"Venkatakrishnan","year":"2013"},{"key":"mlstac1d35bib51","article-title":"Tuning-free plug-and-play proximal algorithm for inverse imaging problems","author":"Wei","year":"2020"},{"key":"mlstac1d35bib52","doi-asserted-by":"crossref","DOI":"10.1109\/IEEECONF51394.2020.9443410","article-title":"Boosting the performance of plug-and-play priors via denoiser scaling","author":"Xu","year":"2020"},{"key":"mlstac1d35bib53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-19426-7","article-title":"Low-dose x-ray tomography through a deep convolutional neural network","volume":"8","author":"Yang","year":"2018","journal-title":"Sci. Rep."},{"key":"mlstac1d35bib54","first-page":"6668","article-title":"Deep residual learning for model-based iterative CT reconstruction using plug-and-play framework","author":"Ye","year":"2018"},{"key":"mlstac1d35bib55","article-title":"Scalable and accurate multi-gpu based image reconstruction of large-scale ptychography data","author":"Yu","year":"2021"},{"key":"mlstac1d35bib56","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","article-title":"Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1d35","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1d35\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1d35","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1d35\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1d35\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1d35\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1d35\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1d35\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T16:58:57Z","timestamp":1639414737000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac1d35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,27]]},"references-count":56,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,8,27]]},"published-print":{"date-parts":[[2021,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac1d35","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,27]]},"assertion":[{"value":"Joint ptycho-tomography with deep generative priors","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"Not subject to copyright in the USA. Contribution of U.S. Department of Energy.","name":"copyright_information","label":"Copyright Information"},{"value":"2021-03-05","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-08-12","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-08-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}