Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction
Abstract Sparse-view Reconstruction can be used to provide accelerated low dose CT imaging with both accelerated scan and reduced projection/back-projection calculation. Despite the rapid developments, image noise and artifacts still remain a major issue in the low dose protocol. In this paper, a de...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2018-04-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-018-25153-w |
id |
doaj-b8cc37968daf44898d6e86aee02c35ce |
---|---|
record_format |
Article |
spelling |
doaj-b8cc37968daf44898d6e86aee02c35ce2020-12-08T05:55:45ZengNature Publishing GroupScientific Reports2045-23222018-04-01811910.1038/s41598-018-25153-wArtifact Removal using Improved GoogLeNet for Sparse-view CT ReconstructionShipeng Xie0Xinyu Zheng1Yang Chen2Lizhe Xie3Jin Liu4Yudong Zhang5Jingjie Yan6Hu Zhu7Yining Hu8Nanjing University of Posts and Telecommunications, College of Telecommunications & Information EngineeringNanjing University of Posts and Telecommunications, College of Telecommunications & Information EngineeringLIST, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast UniversityJiangsu Key Laboratory of Oral Diseases, Nanjing medical universityLIST, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast UniversityDepartment of Informatics, University of LeicesterNanjing University of Posts and Telecommunications, College of Telecommunications & Information EngineeringNanjing University of Posts and Telecommunications, College of Telecommunications & Information EngineeringLIST, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast UniversityAbstract Sparse-view Reconstruction can be used to provide accelerated low dose CT imaging with both accelerated scan and reduced projection/back-projection calculation. Despite the rapid developments, image noise and artifacts still remain a major issue in the low dose protocol. In this paper, a deep learning based method named Improved GoogLeNet is proposed to remove streak artifacts due to projection missing in sparse-view CT reconstruction. Residual learning is used in GoogLeNet to study the artifacts of sparse-view CT reconstruction, and then subtracts the artifacts obtained by learning from the sparse reconstructed images, finally recovers a clear correction image. The intensity of reconstruction using the proposed method is very close to the full-view projective reconstructed image. The results indicate that the proposed method is practical and effective for reducing the artifacts and preserving the quality of the reconstructed image.https://doi.org/10.1038/s41598-018-25153-w |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shipeng Xie Xinyu Zheng Yang Chen Lizhe Xie Jin Liu Yudong Zhang Jingjie Yan Hu Zhu Yining Hu |
spellingShingle |
Shipeng Xie Xinyu Zheng Yang Chen Lizhe Xie Jin Liu Yudong Zhang Jingjie Yan Hu Zhu Yining Hu Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction Scientific Reports |
author_facet |
Shipeng Xie Xinyu Zheng Yang Chen Lizhe Xie Jin Liu Yudong Zhang Jingjie Yan Hu Zhu Yining Hu |
author_sort |
Shipeng Xie |
title |
Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction |
title_short |
Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction |
title_full |
Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction |
title_fullStr |
Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction |
title_full_unstemmed |
Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction |
title_sort |
artifact removal using improved googlenet for sparse-view ct reconstruction |
publisher |
Nature Publishing Group |
series |
Scientific Reports |
issn |
2045-2322 |
publishDate |
2018-04-01 |
description |
Abstract Sparse-view Reconstruction can be used to provide accelerated low dose CT imaging with both accelerated scan and reduced projection/back-projection calculation. Despite the rapid developments, image noise and artifacts still remain a major issue in the low dose protocol. In this paper, a deep learning based method named Improved GoogLeNet is proposed to remove streak artifacts due to projection missing in sparse-view CT reconstruction. Residual learning is used in GoogLeNet to study the artifacts of sparse-view CT reconstruction, and then subtracts the artifacts obtained by learning from the sparse reconstructed images, finally recovers a clear correction image. The intensity of reconstruction using the proposed method is very close to the full-view projective reconstructed image. The results indicate that the proposed method is practical and effective for reducing the artifacts and preserving the quality of the reconstructed image. |
url |
https://doi.org/10.1038/s41598-018-25153-w |
work_keys_str_mv |
AT shipengxie artifactremovalusingimprovedgooglenetforsparseviewctreconstruction AT xinyuzheng artifactremovalusingimprovedgooglenetforsparseviewctreconstruction AT yangchen artifactremovalusingimprovedgooglenetforsparseviewctreconstruction AT lizhexie artifactremovalusingimprovedgooglenetforsparseviewctreconstruction AT jinliu artifactremovalusingimprovedgooglenetforsparseviewctreconstruction AT yudongzhang artifactremovalusingimprovedgooglenetforsparseviewctreconstruction AT jingjieyan artifactremovalusingimprovedgooglenetforsparseviewctreconstruction AT huzhu artifactremovalusingimprovedgooglenetforsparseviewctreconstruction AT yininghu artifactremovalusingimprovedgooglenetforsparseviewctreconstruction |
_version_ |
1724391561881452544 |