No Cover Image

Journal article 388 views 69 downloads

Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction

Davide Micieli, Triestino Minniti, Llion Evans Orcid Logo, Giuseppe Gorini

Scientific Reports, Volume: 9, Issue: 1

Swansea University Author: Llion Evans Orcid Logo

  • miciele2019.pdf

    PDF | Version of Record

    Licensed under a Creative Commons Attribution 4.0 International License (CC-BY).

    Download (2.8MB)

Abstract

Neutron Tomography (NT) is a non-destructive technique to investigate the inner structure of a wide range of objects and, in some cases, provides valuable results in comparison to the more common X-ray imaging techniques. However, NT is time consuming and scanning a set of similar objects during a b...

Full description

Published in: Scientific Reports
ISSN: 2045-2322
Published: Springer Science and Business Media LLC 2019
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa48957
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2019-02-22T20:06:25Z
last_indexed 2020-10-20T02:58:59Z
id cronfa48957
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2020-10-19T16:42:38.1449502</datestamp><bib-version>v2</bib-version><id>48957</id><entry>2019-02-22</entry><title>Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction</title><swanseaauthors><author><sid>74dc5084c47484922a6e0135ebcb9402</sid><ORCID>0000-0002-4964-4187</ORCID><firstname>Llion</firstname><surname>Evans</surname><name>Llion Evans</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2019-02-22</date><deptcode>MECH</deptcode><abstract>Neutron Tomography (NT) is a non-destructive technique to investigate the inner structure of a wide range of objects and, in some cases, provides valuable results in comparison to the more common X-ray imaging techniques. However, NT is time consuming and scanning a set of similar objects during a beamtime leads to data redundancy and long acquisition times. Nowadays NT is unfeasible for quality checking study of large quantities of similar objects. One way to decrease the total scan time is to reduce the number of projections. Analytical reconstruction methods are very fast but under this condition generate streaking artifacts in the reconstructed images. Iterative algorithms generally provide better reconstruction for limited data problems, but at the expense of longer reconstruction time. In this study, we propose the recently introduced Neural Network Filtered Back-Projection (NN-FBP) method to optimize the time usage in NT experiments. Simulated and real neutron data were used to assess the performance of the NN-FBP method as a function of the number of projections. For the first time a machine learning based algorithm is applied and tested for NT image reconstruction problem. We demonstrate that the NN-FBP method can reliably reduce acquisition and reconstruction times and it outperforms conventional reconstruction methods used in NT, providing high image quality for limited datasets.</abstract><type>Journal Article</type><journal>Scientific Reports</journal><volume>9</volume><journalNumber>1</journalNumber><publisher>Springer Science and Business Media LLC</publisher><issnElectronic>2045-2322</issnElectronic><keywords/><publishedDay>1</publishedDay><publishedMonth>12</publishedMonth><publishedYear>2019</publishedYear><publishedDate>2019-12-01</publishedDate><doi>10.1038/s41598-019-38903-1</doi><url/><notes/><college>COLLEGE NANME</college><department>Mechanical Engineering</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MECH</DepartmentCode><institution>Swansea University</institution><apcterm/><lastEdited>2020-10-19T16:42:38.1449502</lastEdited><Created>2019-02-22T13:18:08.7236222</Created><path><level id="1">College of Engineering</level><level id="2">Engineering</level></path><authors><author><firstname>Davide</firstname><surname>Micieli</surname><order>1</order></author><author><firstname>Triestino</firstname><surname>Minniti</surname><order>2</order></author><author><firstname>Llion</firstname><surname>Evans</surname><orcid>0000-0002-4964-4187</orcid><order>3</order></author><author><firstname>Giuseppe</firstname><surname>Gorini</surname><order>4</order></author></authors><documents><document><filename>0048957-22022019132251.pdf</filename><originalFilename>miciele2019.pdf</originalFilename><uploaded>2019-02-22T13:22:51.2870000</uploaded><type>Output</type><contentLength>3106123</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><embargoDate>2019-02-22T00:00:00.0000000</embargoDate><documentNotes>Licensed under a Creative Commons Attribution 4.0 International License (CC-BY).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2020-10-19T16:42:38.1449502 v2 48957 2019-02-22 Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction 74dc5084c47484922a6e0135ebcb9402 0000-0002-4964-4187 Llion Evans Llion Evans true false 2019-02-22 MECH Neutron Tomography (NT) is a non-destructive technique to investigate the inner structure of a wide range of objects and, in some cases, provides valuable results in comparison to the more common X-ray imaging techniques. However, NT is time consuming and scanning a set of similar objects during a beamtime leads to data redundancy and long acquisition times. Nowadays NT is unfeasible for quality checking study of large quantities of similar objects. One way to decrease the total scan time is to reduce the number of projections. Analytical reconstruction methods are very fast but under this condition generate streaking artifacts in the reconstructed images. Iterative algorithms generally provide better reconstruction for limited data problems, but at the expense of longer reconstruction time. In this study, we propose the recently introduced Neural Network Filtered Back-Projection (NN-FBP) method to optimize the time usage in NT experiments. Simulated and real neutron data were used to assess the performance of the NN-FBP method as a function of the number of projections. For the first time a machine learning based algorithm is applied and tested for NT image reconstruction problem. We demonstrate that the NN-FBP method can reliably reduce acquisition and reconstruction times and it outperforms conventional reconstruction methods used in NT, providing high image quality for limited datasets. Journal Article Scientific Reports 9 1 Springer Science and Business Media LLC 2045-2322 1 12 2019 2019-12-01 10.1038/s41598-019-38903-1 COLLEGE NANME Mechanical Engineering COLLEGE CODE MECH Swansea University 2020-10-19T16:42:38.1449502 2019-02-22T13:18:08.7236222 College of Engineering Engineering Davide Micieli 1 Triestino Minniti 2 Llion Evans 0000-0002-4964-4187 3 Giuseppe Gorini 4 0048957-22022019132251.pdf miciele2019.pdf 2019-02-22T13:22:51.2870000 Output 3106123 application/pdf Version of Record true 2019-02-22T00:00:00.0000000 Licensed under a Creative Commons Attribution 4.0 International License (CC-BY). true eng http://creativecommons.org/licenses/by/4.0/
title Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction
spellingShingle Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction
Llion Evans
title_short Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction
title_full Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction
title_fullStr Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction
title_full_unstemmed Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction
title_sort Accelerating Neutron Tomography experiments through Artificial Neural Network based reconstruction
author_id_str_mv 74dc5084c47484922a6e0135ebcb9402
author_id_fullname_str_mv 74dc5084c47484922a6e0135ebcb9402_***_Llion Evans
author Llion Evans
author2 Davide Micieli
Triestino Minniti
Llion Evans
Giuseppe Gorini
format Journal article
container_title Scientific Reports
container_volume 9
container_issue 1
publishDate 2019
institution Swansea University
issn 2045-2322
doi_str_mv 10.1038/s41598-019-38903-1
publisher Springer Science and Business Media LLC
college_str College of Engineering
hierarchytype
hierarchy_top_id collegeofengineering
hierarchy_top_title College of Engineering
hierarchy_parent_id collegeofengineering
hierarchy_parent_title College of Engineering
department_str Engineering{{{_:::_}}}College of Engineering{{{_:::_}}}Engineering
document_store_str 1
active_str 0
description Neutron Tomography (NT) is a non-destructive technique to investigate the inner structure of a wide range of objects and, in some cases, provides valuable results in comparison to the more common X-ray imaging techniques. However, NT is time consuming and scanning a set of similar objects during a beamtime leads to data redundancy and long acquisition times. Nowadays NT is unfeasible for quality checking study of large quantities of similar objects. One way to decrease the total scan time is to reduce the number of projections. Analytical reconstruction methods are very fast but under this condition generate streaking artifacts in the reconstructed images. Iterative algorithms generally provide better reconstruction for limited data problems, but at the expense of longer reconstruction time. In this study, we propose the recently introduced Neural Network Filtered Back-Projection (NN-FBP) method to optimize the time usage in NT experiments. Simulated and real neutron data were used to assess the performance of the NN-FBP method as a function of the number of projections. For the first time a machine learning based algorithm is applied and tested for NT image reconstruction problem. We demonstrate that the NN-FBP method can reliably reduce acquisition and reconstruction times and it outperforms conventional reconstruction methods used in NT, providing high image quality for limited datasets.
published_date 2019-12-01T04:01:53Z
_version_ 1737027080064860160
score 10.898073