Cargando…

Computed Tomography slice interpolation in the longitudinal direction based on deep learning techniques: To reduce slice thickness or slice increment without dose increase

Large slice thickness or slice increment causes information insufficiency of Computed Tomography (CT) data in the longitudinal direction, which degrades the quality of CT-based diagnosis. Traditional approaches such as high-resolution computed tomography (HRCT) and linear interpolation can solve thi...

Descripción completa

Detalles Bibliográficos
Autores principales: Wu, Shuqiong, Nakao, Megumi, Imanishi, Keiho, Nakamura, Mitsuhiro, Mizowaki, Takashi, Matsuda, Tetsuya
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9754169/
https://www.ncbi.nlm.nih.gov/pubmed/36520814
http://dx.doi.org/10.1371/journal.pone.0279005
_version_ 1784851123966836736
author Wu, Shuqiong
Nakao, Megumi
Imanishi, Keiho
Nakamura, Mitsuhiro
Mizowaki, Takashi
Matsuda, Tetsuya
author_facet Wu, Shuqiong
Nakao, Megumi
Imanishi, Keiho
Nakamura, Mitsuhiro
Mizowaki, Takashi
Matsuda, Tetsuya
author_sort Wu, Shuqiong
collection PubMed
description Large slice thickness or slice increment causes information insufficiency of Computed Tomography (CT) data in the longitudinal direction, which degrades the quality of CT-based diagnosis. Traditional approaches such as high-resolution computed tomography (HRCT) and linear interpolation can solve this problem. However, HRCT suffers from dose increase, and linear interpolation causes artifacts. In this study, we propose a deep-learning-based approach to reconstruct densely sliced CT from sparsely sliced CT data without any dose increase. The proposed method reconstructs CT images from neighboring slices using a U-net architecture. To prevent multiple reconstructed slices from influencing one another, we propose a parallel architecture in which multiple U-net architectures work independently. Moreover, for a specific organ (i.e., the liver), we propose a range-clip technique to improve reconstruction quality, which enhances the learning of CT values within this organ by enlarging the range of the training data. CT data from 130 patients were collected, with 80% used for training and the remaining 20% used for testing. Experiments showed that our parallel U-net architecture reduced the mean absolute error of CT values in the reconstructed slices by 22.05%, and also reduced the incidence of artifacts around the boundaries of target organs, compared with linear interpolation. Further improvements of 15.12%, 11.04%, 10.94%, and 10.63% were achieved for the liver, left kidney, right kidney, and stomach, respectively, using the proposed range-clip algorithm. Also, we compared the proposed architecture with original U-net method, and the experimental results demonstrated the superiority of our approach.
format Online
Article
Text
id pubmed-9754169
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-97541692022-12-16 Computed Tomography slice interpolation in the longitudinal direction based on deep learning techniques: To reduce slice thickness or slice increment without dose increase Wu, Shuqiong Nakao, Megumi Imanishi, Keiho Nakamura, Mitsuhiro Mizowaki, Takashi Matsuda, Tetsuya PLoS One Research Article Large slice thickness or slice increment causes information insufficiency of Computed Tomography (CT) data in the longitudinal direction, which degrades the quality of CT-based diagnosis. Traditional approaches such as high-resolution computed tomography (HRCT) and linear interpolation can solve this problem. However, HRCT suffers from dose increase, and linear interpolation causes artifacts. In this study, we propose a deep-learning-based approach to reconstruct densely sliced CT from sparsely sliced CT data without any dose increase. The proposed method reconstructs CT images from neighboring slices using a U-net architecture. To prevent multiple reconstructed slices from influencing one another, we propose a parallel architecture in which multiple U-net architectures work independently. Moreover, for a specific organ (i.e., the liver), we propose a range-clip technique to improve reconstruction quality, which enhances the learning of CT values within this organ by enlarging the range of the training data. CT data from 130 patients were collected, with 80% used for training and the remaining 20% used for testing. Experiments showed that our parallel U-net architecture reduced the mean absolute error of CT values in the reconstructed slices by 22.05%, and also reduced the incidence of artifacts around the boundaries of target organs, compared with linear interpolation. Further improvements of 15.12%, 11.04%, 10.94%, and 10.63% were achieved for the liver, left kidney, right kidney, and stomach, respectively, using the proposed range-clip algorithm. Also, we compared the proposed architecture with original U-net method, and the experimental results demonstrated the superiority of our approach. Public Library of Science 2022-12-15 /pmc/articles/PMC9754169/ /pubmed/36520814 http://dx.doi.org/10.1371/journal.pone.0279005 Text en © 2022 Wu et al https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Wu, Shuqiong
Nakao, Megumi
Imanishi, Keiho
Nakamura, Mitsuhiro
Mizowaki, Takashi
Matsuda, Tetsuya
Computed Tomography slice interpolation in the longitudinal direction based on deep learning techniques: To reduce slice thickness or slice increment without dose increase
title Computed Tomography slice interpolation in the longitudinal direction based on deep learning techniques: To reduce slice thickness or slice increment without dose increase
title_full Computed Tomography slice interpolation in the longitudinal direction based on deep learning techniques: To reduce slice thickness or slice increment without dose increase
title_fullStr Computed Tomography slice interpolation in the longitudinal direction based on deep learning techniques: To reduce slice thickness or slice increment without dose increase
title_full_unstemmed Computed Tomography slice interpolation in the longitudinal direction based on deep learning techniques: To reduce slice thickness or slice increment without dose increase
title_short Computed Tomography slice interpolation in the longitudinal direction based on deep learning techniques: To reduce slice thickness or slice increment without dose increase
title_sort computed tomography slice interpolation in the longitudinal direction based on deep learning techniques: to reduce slice thickness or slice increment without dose increase
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9754169/
https://www.ncbi.nlm.nih.gov/pubmed/36520814
http://dx.doi.org/10.1371/journal.pone.0279005
work_keys_str_mv AT wushuqiong computedtomographysliceinterpolationinthelongitudinaldirectionbasedondeeplearningtechniquestoreduceslicethicknessorsliceincrementwithoutdoseincrease
AT nakaomegumi computedtomographysliceinterpolationinthelongitudinaldirectionbasedondeeplearningtechniquestoreduceslicethicknessorsliceincrementwithoutdoseincrease
AT imanishikeiho computedtomographysliceinterpolationinthelongitudinaldirectionbasedondeeplearningtechniquestoreduceslicethicknessorsliceincrementwithoutdoseincrease
AT nakamuramitsuhiro computedtomographysliceinterpolationinthelongitudinaldirectionbasedondeeplearningtechniquestoreduceslicethicknessorsliceincrementwithoutdoseincrease
AT mizowakitakashi computedtomographysliceinterpolationinthelongitudinaldirectionbasedondeeplearningtechniquestoreduceslicethicknessorsliceincrementwithoutdoseincrease
AT matsudatetsuya computedtomographysliceinterpolationinthelongitudinaldirectionbasedondeeplearningtechniquestoreduceslicethicknessorsliceincrementwithoutdoseincrease