Compensating Sparse-view Inline Computed Tomography Artifacts with Neural Representation and Incremental Forward-Backward Network Architecture
Sparse-view computed tomography (CT) is appealing for inline industrial quality control because it can significantly reduce scan acquisition times compared to full-view CT of 1-2 hours to a few minutes. This allows sparse view CT to be used in inline process manufacturing for 100% inspection of eve...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | deu |
| Published: |
NDT.net
2025-02-01
|
| Series: | e-Journal of Nondestructive Testing |
| Online Access: | https://www.ndt.net/search/docs.php3?id=30720 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832086568299397120 |
|---|---|
| author | Manuel Buchfink Faizan Ahmad Guangpu Yang Ammar Alsaffar Charles Clark Ahmed Baraka Xingyu Liu Sven Simon |
| author_facet | Manuel Buchfink Faizan Ahmad Guangpu Yang Ammar Alsaffar Charles Clark Ahmed Baraka Xingyu Liu Sven Simon |
| author_sort | Manuel Buchfink |
| collection | DOAJ |
| description |
Sparse-view computed tomography (CT) is appealing for inline industrial quality control because it can significantly reduce scan acquisition times compared to full-view CT of 1-2 hours to a few minutes. This allows sparse view CT to be used in inline process manufacturing for 100% inspection of every component. However, the smaller number of projections in sparse-view CT scans leads to streak artifacts, which generally cause measurement deviations during the metrological inspection of components. Therefore, this paper discusses two deep-learning-based approaches for removing such artifacts. The two methods utilize a neural representation architecture to reproduce an estimate of the scanned object and then simulate a sparse-view forward projection to generate an artifact image. This approach was initially proposed for application in medical CT imaging, but it is modified for applications in inline industrial CT concerning speed. The two methods differ in how the neural representation is optimized during training. The first method is optimized based on an image-to-image basis, and the second method is on a projection basis. Our results show that both explored methods produce good correction results that lead to a promising minimization of surface deviation on the tested objects while meeting time constraints. This makes their application in industrial inline CT feasible.
|
| format | Article |
| id | doaj-art-46add9a788bb42969ca174b6d15a5359 |
| institution | Kabale University |
| issn | 1435-4934 |
| language | deu |
| publishDate | 2025-02-01 |
| publisher | NDT.net |
| record_format | Article |
| series | e-Journal of Nondestructive Testing |
| spelling | doaj-art-46add9a788bb42969ca174b6d15a53592025-02-06T10:48:18ZdeuNDT.nete-Journal of Nondestructive Testing1435-49342025-02-0130210.58286/30720Compensating Sparse-view Inline Computed Tomography Artifacts with Neural Representation and Incremental Forward-Backward Network ArchitectureManuel BuchfinkFaizan AhmadGuangpu YangAmmar AlsaffarCharles Clarkhttps://orcid.org/0000-0001-6642-8489Ahmed Barakahttps://orcid.org/0009-0007-5272-187XXingyu Liuhttps://orcid.org/0009-0008-8093-1767Sven Simon Sparse-view computed tomography (CT) is appealing for inline industrial quality control because it can significantly reduce scan acquisition times compared to full-view CT of 1-2 hours to a few minutes. This allows sparse view CT to be used in inline process manufacturing for 100% inspection of every component. However, the smaller number of projections in sparse-view CT scans leads to streak artifacts, which generally cause measurement deviations during the metrological inspection of components. Therefore, this paper discusses two deep-learning-based approaches for removing such artifacts. The two methods utilize a neural representation architecture to reproduce an estimate of the scanned object and then simulate a sparse-view forward projection to generate an artifact image. This approach was initially proposed for application in medical CT imaging, but it is modified for applications in inline industrial CT concerning speed. The two methods differ in how the neural representation is optimized during training. The first method is optimized based on an image-to-image basis, and the second method is on a projection basis. Our results show that both explored methods produce good correction results that lead to a promising minimization of surface deviation on the tested objects while meeting time constraints. This makes their application in industrial inline CT feasible. https://www.ndt.net/search/docs.php3?id=30720 |
| spellingShingle | Manuel Buchfink Faizan Ahmad Guangpu Yang Ammar Alsaffar Charles Clark Ahmed Baraka Xingyu Liu Sven Simon Compensating Sparse-view Inline Computed Tomography Artifacts with Neural Representation and Incremental Forward-Backward Network Architecture e-Journal of Nondestructive Testing |
| title | Compensating Sparse-view Inline Computed Tomography Artifacts with Neural Representation and Incremental Forward-Backward Network Architecture |
| title_full | Compensating Sparse-view Inline Computed Tomography Artifacts with Neural Representation and Incremental Forward-Backward Network Architecture |
| title_fullStr | Compensating Sparse-view Inline Computed Tomography Artifacts with Neural Representation and Incremental Forward-Backward Network Architecture |
| title_full_unstemmed | Compensating Sparse-view Inline Computed Tomography Artifacts with Neural Representation and Incremental Forward-Backward Network Architecture |
| title_short | Compensating Sparse-view Inline Computed Tomography Artifacts with Neural Representation and Incremental Forward-Backward Network Architecture |
| title_sort | compensating sparse view inline computed tomography artifacts with neural representation and incremental forward backward network architecture |
| url | https://www.ndt.net/search/docs.php3?id=30720 |
| work_keys_str_mv | AT manuelbuchfink compensatingsparseviewinlinecomputedtomographyartifactswithneuralrepresentationandincrementalforwardbackwardnetworkarchitecture AT faizanahmad compensatingsparseviewinlinecomputedtomographyartifactswithneuralrepresentationandincrementalforwardbackwardnetworkarchitecture AT guangpuyang compensatingsparseviewinlinecomputedtomographyartifactswithneuralrepresentationandincrementalforwardbackwardnetworkarchitecture AT ammaralsaffar compensatingsparseviewinlinecomputedtomographyartifactswithneuralrepresentationandincrementalforwardbackwardnetworkarchitecture AT charlesclark compensatingsparseviewinlinecomputedtomographyartifactswithneuralrepresentationandincrementalforwardbackwardnetworkarchitecture AT ahmedbaraka compensatingsparseviewinlinecomputedtomographyartifactswithneuralrepresentationandincrementalforwardbackwardnetworkarchitecture AT xingyuliu compensatingsparseviewinlinecomputedtomographyartifactswithneuralrepresentationandincrementalforwardbackwardnetworkarchitecture AT svensimon compensatingsparseviewinlinecomputedtomographyartifactswithneuralrepresentationandincrementalforwardbackwardnetworkarchitecture |