{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T22:22:48Z","timestamp":1780611768374,"version":"3.54.1"},"reference-count":52,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T00:00:00Z","timestamp":1618358400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,4,14]],"date-time":"2021-04-14T00:00:00Z","timestamp":1618358400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006228","name":"Oak Ridge National Laboratory","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100006228","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":[[2021,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Neutron computed tomography (NCT), a 3D non-destructive characterization technique, is carried out at nuclear reactor or spallation neutron source-based user facilities. Because neutrons are not severely attenuated by heavy elements and are sensitive to light elements like hydrogen, neutron radiography and computed tomography offer a complementary contrast to x-ray CT conducted at a synchrotron user facility. However, compared to synchrotron x-ray CT, the acquisition time for an NCT scan can be orders of magnitude higher due to lower source flux, low detector efficiency and the need to collect a large number of projection images for a high-quality reconstruction when using conventional algorithms. As a result of the long scan times for NCT, the number and type of experiments that can be conducted at a user facility is severely restricted. Recently, several deep convolutional neural network (DCNN) based algorithms have been introduced in the context of accelerating CT scans that can enable high quality reconstructions from sparse-view data. In this paper, we introduce DCNN algorithms to obtain high-quality reconstructions from sparse-view and low signal-to-noise ratio NCT data-sets thereby enabling accelerated scans. Our method is based on the supervised learning strategy of training a DCNN to map a low-quality reconstruction from sparse-view data to a higher quality reconstruction. Specifically, we evaluate the performance of two popular DCNN architectures\u2014one based on using patches for training and the other on using the full images for training. We observe that both the DCNN architectures offer improvements in performance over classical multi-layer perceptron as well as conventional CT reconstruction algorithms. Our results illustrate that the DCNN can be a powerful tool to obtain high-quality NCT reconstructions from sparse-view data thereby enabling accelerated NCT scans for increasing user-facility throughput or enabling high-resolution time-resolved NCT scans.<\/jats:p>","DOI":"10.1088\/2632-2153\/abde8e","type":"journal-article","created":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T18:02:34Z","timestamp":1620756154000},"page":"025031","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Convolutional neural network based non-iterative reconstruction for accelerating neutron tomography\n                  <sup>*<\/sup>"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7637-4987","authenticated-orcid":false,"given":"Singanallur","family":"Venkatakrishnan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4776-457X","authenticated-orcid":false,"given":"Amirkoushyar","family":"Ziabari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7751-1760","authenticated-orcid":false,"given":"Jacob","family":"Hinkle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew W","family":"Needham","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0680-4697","authenticated-orcid":false,"given":"Jeffrey M","family":"Warren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8574-2449","authenticated-orcid":false,"given":"Hassina Z","family":"Bilheux","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,4,14]]},"reference":[{"key":"mlstabde8ebib1","doi-asserted-by":"publisher","author":"Anderson","year":"2009","DOI":"10.1007\/978-0-387-78693-3"},{"key":"mlstabde8ebib2","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1016\/S1369-7021(11)70139-0","volume":"14","author":"Kardjilov","year":"2011","journal-title":"Mater. Today"},{"key":"mlstabde8ebib3","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.jpowsour.2017.11.080","article-title":"Imaging of the Li spatial distribution within V2O5 cathode in a coin cell by neutron computed tomography","volume":"376","author":"Zhang","year":"2018","journal-title":"J. Power Sources"},{"key":"mlstabde8ebib4","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1107\/S0909049512032864","volume":"19","author":"Marone","year":"2012","journal-title":"J. Synchrotron Radiat."},{"key":"mlstabde8ebib5","author":"Bouman","year":"2013"},{"key":"mlstabde8ebib6","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1109\/TIP.2010.2058811","volume":"20","author":"Yu","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabde8ebib7","doi-asserted-by":"publisher","first-page":"1660","DOI":"10.1109\/TBME.2015.2422135","volume":"62","author":"van Sloun","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"mlstabde8ebib8","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1002\/mrm.21391","volume":"58","author":"Lustig","year":"2007","journal-title":"Magn. Reson. Med."},{"key":"mlstabde8ebib9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854939","article-title":"Model-based iterative reconstruction for synchrotron x-ray tomography","author":"Mohan","year":"2014"},{"key":"mlstabde8ebib10","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TCI.2015.2431913","volume":"1","author":"Mohan","year":"2015","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"mlstabde8ebib11","doi-asserted-by":"publisher","first-page":"4532","DOI":"10.1109\/TIP.2013.2277784","volume":"22","author":"Venkatakrishnan","year":"2013","journal-title":"IEEE Trans. on Computational Imaging"},{"key":"mlstabde8ebib12","doi-asserted-by":"publisher","first-page":"1864","DOI":"10.1109\/ACSSC.2017.8335686","article-title":"Model-based iterative reconstruction for neutron laminography","author":"Venkatakrishnan","year":"2017"},{"key":"mlstabde8ebib13","doi-asserted-by":"publisher","DOI":"10.1063\/1.5037341","volume":"89","author":"Barnard","year":"2018","journal-title":"Rev. Sci. Instrum."},{"key":"mlstabde8ebib14","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/13\/06\/C06006","volume":"13","author":"Micieli","year":"2018","journal-title":"J. Instrum."},{"key":"mlstabde8ebib15","first-page":"8","volume":"66","author":"Forman","year":"2016","journal-title":"MAGNETOM Flash"},{"key":"mlstabde8ebib16","doi-asserted-by":"publisher","first-page":"9014","DOI":"10.1364\/OE.23.009014","volume":"23","author":"G\u00fcrsoy","year":"2015","journal-title":"Opt. Express"},{"key":"mlstabde8ebib17","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/MSP.2017.2739299","volume":"34","author":"McCann","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"mlstabde8ebib18","doi-asserted-by":"publisher","DOI":"10.14760\/SNAP-2019-015-EN","article-title":"Deep learning and inverse problems","author":"Arridge","year":"2019"},{"key":"mlstabde8ebib19","doi-asserted-by":"publisher","first-page":"5238","DOI":"10.1109\/TIP.2013.2283142","volume":"22","author":"Pelt","year":"2013","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabde8ebib20","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"mlstabde8ebib21","author":"Han","year":"2016"},{"key":"mlstabde8ebib22","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","volume":"26","author":"Jin","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabde8ebib23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-017-17765-5","volume":"8","author":"Yang","year":"2018","journal-title":"Sci. Rep."},{"key":"mlstabde8ebib24","doi-asserted-by":"publisher","first-page":"2044","DOI":"10.1109\/ACSSC.2018.8645364","article-title":"2.5D deep learning for CT image reconstruction using a multi-GPU implementation","author":"Ziabari","year":"2018"},{"key":"mlstabde8ebib25","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1017\/S1431927619002617","volume":"25","author":"Ziabari","year":"2019","journal-title":"Microsc. Microanal."},{"key":"mlstabde8ebib26","first-page":"V02BT02A043","article-title":"Beam hardening artifact reduction in x-ray CT reconstruction of 3D printed metal parts leveraging deep learning and CAD models","volume":"84492","author":"Ziabari","year":"2020"},{"key":"mlstabde8ebib27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPHOT.2019.8747328","article-title":"4D x-ray CT reconstruction using multi-slice fusion","author":"Majee","year":"2019"},{"key":"mlstabde8ebib28","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1364\/JOSAA.375595","volume":"37","author":"Liu","year":"2020","journal-title":"J. Opt. Soc. Am. A"},{"key":"mlstabde8ebib29","doi-asserted-by":"publisher","first-page":"128","DOI":"10.3390\/jimaging4110128","volume":"4","author":"Pelt","year":"2018","journal-title":"J. Imaging"},{"key":"mlstabde8ebib30","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1073\/pnas.1715832114","volume":"115","author":"Pelt","year":"2018","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstabde8ebib31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-38903-1","volume":"9","author":"Micieli","year":"2019","journal-title":"Sci. Rep."},{"key":"mlstabde8ebib32","doi-asserted-by":"publisher","author":"Kak","year":"2001","DOI":"10.1137\/1.9780898719277"},{"key":"mlstabde8ebib33","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"mlstabde8ebib34","doi-asserted-by":"publisher","first-page":"6668","DOI":"10.1109\/ICASSP.2018.8461408","article-title":"Deep residual learning for model-based iterative CT reconstruction using plug-and-play framework","author":"Ye","year":"2018"},{"key":"mlstabde8ebib35","first-page":"448","volume":"37","author":"Ioffe","year":"2015","journal-title":"Proc. Machine Learning Research"},{"key":"mlstabde8ebib36","doi-asserted-by":"publisher","first-page":"4700","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"mlstabde8ebib37","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/0167-2789(92)90242-F","volume":"60","author":"Rudin","year":"1992","journal-title":"Phys. D: Nonlinear Phenom."},{"key":"mlstabde8ebib38","first-page":"313","article-title":"Fast newton-type methods for total variation regularization","author":"Barbero","year":"2011"},{"key":"mlstabde8ebib39","first-page":"1","volume":"19","author":"Barbero","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"mlstabde8ebib40","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1107\/S1600577514013939","volume":"21","author":"G\u00fcrsoy","year":"2014","journal-title":"J. Synchrotron Radiat."},{"key":"mlstabde8ebib41","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.ultramic.2015.05.002","article-title":"The ASTRA Toolbox: a platform for advanced algorithm development in electron tomography","volume":"157","author":"van Aarle","year":"2015","journal-title":"Ultramicroscopy"},{"key":"mlstabde8ebib42","doi-asserted-by":"publisher","first-page":"25129","DOI":"10.1364\/OE.24.025129","volume":"24","author":"van Aarle","year":"2016","journal-title":"Opt. Express"},{"key":"mlstabde8ebib43","author":"Venkatakrishnan","year":"2019"},{"key":"mlstabde8ebib44","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstabde8ebib45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3126908.3126911","article-title":"Massively parallel 3D image reconstruction","author":"Wang","year":"2017"},{"key":"mlstabde8ebib46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50371-0_18","article-title":"Sparse matrix-based HPC tomography","author":"Marchesini","year":"2020"},{"key":"mlstabde8ebib47","first-page":"1","article-title":"Petascale XCT: 3D image reconstruction with hierarchical communications on multi-GPU nodes","author":"Hidayetoglu","year":"2020"},{"key":"mlstabde8ebib48","doi-asserted-by":"publisher","first-page":"28640","DOI":"10.1364\/OE.27.028640","volume":"27","author":"T\u00f6tzke","year":"2019","journal-title":"Opt. Express"},{"key":"mlstabde8ebib49","doi-asserted-by":"publisher","first-page":"3557","DOI":"10.1029\/2018JB016522","volume":"124","author":"Tudisco","year":"2019","journal-title":"J. Geophys. Res. Solid Earth"},{"key":"mlstabde8ebib50","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1007\/s11104-012-1579-7","volume":"366","author":"Warren","year":"2013","journal-title":"Plant Soil"},{"key":"mlstabde8ebib51","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/s11104-017-3408-5","volume":"424","author":"Dhiman","year":"2018","journal-title":"Plant Soil"},{"key":"mlstabde8ebib52","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1073\/pnas.1907377117","volume":"117","author":"Antun","year":"2020","journal-title":"Proc. Natl Acad. Sci."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abde8e","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abde8e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abde8e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abde8e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,21]],"date-time":"2021-12-21T20:00:37Z","timestamp":1640116837000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abde8e"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,14]]},"references-count":52,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,4,14]]},"published-print":{"date-parts":[[2021,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abde8e","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,14]]},"assertion":[{"value":"Convolutional neural network based non-iterative reconstruction for accelerating neutron tomography\n                  *","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":"\u00a9 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-07-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-01-21","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-04-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}