 |
 |
 |
Journal articles
Deep iterative reconstruction estimation (DIRE): approximate iterative reconstruction estimation for low dose CT imaging
Jin Liu
1, 2
Yi Zhang
3
Qianlong Zhao
1, 2
Tianling Lv
1, 2
Weiwen Wu
4
Ning Cai
1, 2
Guotao Quan
5
Wei Yang
6
Yang Chen
1, 7, 2
Limin Luo
1, 7, 2
Huazhong Shu
2, 7, 1
Jean-Louis Coatrieux
7
Yang Chen 1, 7, 2
Author
Limin Luo 1, 7, 2
Author
Huazhong Shu 2, 7, 1
Author
Jean-Louis Coatrieux 7
Author
1
Nanjing Southeast University (China)
2
LIST - Laboratory of Image Science and Technology [Nanjing] (Si Pai Lou 2, Nanjing, 210096 - China)
- Southeast University [Jiangsu] (Sipailou 2#,Nanjing, Jiangsu Province, 210096 P. R. - China)
- School of Computer Science and Engineering (China)
3
SCU - Sichuan University [Chengdu] (Chengdu , China - China)
4
Chongqing University [Chongqing] (131 Yubei Rd, Shapingba, Chongqing - China)
6
Southern Medical University [Guangzhou] (Guangdong, China - China)
7
CRIBS - Centre de Recherche en Information Biomédicale sino-français (Rennes - France)
- UR1 - Université de Rennes 1 (2 rue du Thabor - CS 46510 - 35065 Rennes cedex - France)
- UNIV-RENNES - Université de Rennes (France)
- Southeast University [Jiangsu] (Sipailou 2#,Nanjing, Jiangsu Province, 210096 P. R. - China)
- INSERM - Institut National de la Santé et de la Recherche Médicale : LABORATOIRE INTERNATIONAL ASSOCIÉ (101, rue de Tolbiac, 75013 Paris - France)
Abstract : The image quality in low dose computed tomography (LDCT) can be severely degraded by amplified mottle noise and streak artifacts. Although the iterative reconstruction (IR) algorithms bring sound improvements, their high computation cost remains a major inconvenient. In this work, a deep iterative reconstruction estimation (DIRE) strategy is developed to estimate IR images from LDCT analytic reconstructions images. Within this DIRE strategy, a 3D residual convolutional network (3D ResNet) architecture is proposed. Experiments on several simulated and real datasets as well as comparisons with state-of-the-art methods demonstrate that the proposed approach is effective in providing improved LDCT images.
Document type :
Journal articles
Domain :
Complete list of metadata
https://hal-univ-rennes1.archives-ouvertes.fr/hal-02378828
Contributor : Laurent Jonchère <>
Submitted on : Monday, November 25, 2019 - 1:43:44 PM
Last modification on : Monday, August 17, 2020 - 2:20:04 PM
Contributor : Laurent Jonchère <>
Submitted on : Monday, November 25, 2019 - 1:43:44 PM
Last modification on : Monday, August 17, 2020 - 2:20:04 PM
Identifiers
- HAL Id : hal-02378828, version 1
- DOI : 10.1088/1361-6560/ab18db
- PUBMED : 30978718
Collections
Citation
Jin Liu, Yi Zhang, Qianlong Zhao, Tianling Lv, Weiwen Wu, et al.. Deep iterative reconstruction estimation (DIRE): approximate iterative reconstruction estimation for low dose CT imaging. Physics in Medicine and Biology, IOP Publishing, 2019, 64 (13), pp.135007. ⟨10.1088/1361-6560/ab18db⟩. ⟨hal-02378828⟩
Metrics
Record views