文献类型：期刊文献

英文题名：LEARN: Learned Experts' Assessment-Based Reconstruction Network for Sparse-Data CT

作者：Chen, Hu[1];Zhang, Yi[1];Chen, Yunjin[2];Zhang, Junfeng[3];Zhang, Weihua[1];Sun, Huaiqiang[4];Lv, Yang[5];Liao, Peixi[6];Zhou, Jiliu[1];Wang, Ge[7]

第一作者：Chen, Hu

通讯作者：Zhang, Y[1]

机构：[1]Sichuan Univ, Coll Comp Sci, Chengdu 610065, Sichuan, Peoples R China;[2]ULSee Inc, Hangzhou 310020, Zhejiang, Peoples R China;[3]Henan Univ Econ & Law, Sch Comp & Informat Engn, Zhengzhou 450046, Henan, Peoples R China;[4]Sichuan Univ, West China Hosp, Dept Radiol, Chengdu 610041, Sichuan, Peoples R China;[5]Shanghai United Imaging Healthcare Co Ltd, Shanghai, Peoples R China;[6]Sixth Peoples Hosp Chengdu, Dept Sci Res & Educ, Chengdu 610065, Sichuan, Peoples R China;[7]Rensselaer Polytech Inst, Dept Biomed Engn, Troy, NY 12180 USA

第一机构：Sichuan Univ, Coll Comp Sci, Chengdu 610065, Sichuan, Peoples R China

通讯机构：[1]corresponding author), Sichuan Univ, Coll Comp Sci, Chengdu 610065, Sichuan, Peoples R China.

年份：2018

卷号：37

期号：6

起止页码：1333-1347

外文期刊名：IEEE TRANSACTIONS ON MEDICAL IMAGING

收录：;EI(收录号：20180804814547);Scopus(收录号：2-s2.0-85042088719);WOS:【SCI-EXPANDED(收录号:WOS:000434302700005)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61671312, Grant 31700858, and Grant 61302028, and in part by the National Institute of Biomedical Imaging and Bioengineering/National Institutes of Health under Grant R01 EB016977 and Grant U01 EB017140.

语种：英文

外文关键词：Computed tomography (CT); sparse-data CT; iterative reconstruction; compressive sensing; fields of experts; machine learning; deep learning

摘要：Compressive sensing (CS) has proved effective for tomographic reconstruction from sparsely collected data or under-sampled measurements, which are practically important for few-view computed tomography (CT), tomosynthesis, interior tomography, and so on. To perform sparse-data CT, the iterative reconstruction commonly uses regularizers in the CS framework. Currently, how to choose the parameters adaptively for regularization is a major open problem. In this paper, inspired by the idea of machine learning especially deep learning, we unfold the state-of-the- art "fields of experts"-based iterative reconstruction scheme up to a number of iterations for data-driven training, construct a learned experts' assessment-based reconstruction network (LEARN) for sparse-data CT, and demonstrate the feasibility and merits of our LEARN network. The experimental results with our proposed LEARN network produces a superior performance with the well-known Mayo Clinic low-dose challenge data set relative to the several state-of- the-art methods, in terms of artifact reduction, feature preservation, and computational speed. This is consistent to our insight that because all the regularization terms and parameters used in the iterative reconstruction are now learned from the training data, our LEARN network utilizes application-oriented knowledge more effectively and recovers underlying images more favorably than competing algorithms. Also, the number of layers in the LEARN network is only 50, reducing the computational complexity of typical iterative algorithms by orders of magnitude.