Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction.

https://www.ncbi.nlm.nih.gov/pubmed/29712978

Sci Rep. 2018 Apr 30;8(1):6700. doi: 10.1038/s41598-018-25153-w.

Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction.

Xie S1, Zheng X2, Chen Y3,4, Xie L5, Liu J3,4, Zhang Y6, Yan J2, Zhu H2, Hu Y3,4.

Author information

1

Nanjing University of Posts and Telecommunications, College of Telecommunications & Information Engineering, Nanjing, Jiangsu, 210003, China. xie@njupt.edu.cn.

2

Nanjing University of Posts and Telecommunications, College of Telecommunications & Information Engineering, Nanjing, Jiangsu, 210003, China.

3

LIST, Key Laboratory of Computer Network and Information Integration, Ministry of Education, Southeast University, Nanjing, 210096, China.

4

International Joint Research Laboratory of Information Display and Visualization, Southeast University, Ministry of Education, Nanjing, 210096, China.

5

Jiangsu Key Laboratory of Oral Diseases, Nanjing medical university, Nanjing, 210029, China. xielizhe@njmu.edu.cn.

6

Department of Informatics, University of Leicester, Leicester, LE1 7RH, UK.

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.

PMID:

 

29712978

 

PMCID:

 

PMC5928081

 

DOI:

 

10.1038/s41598-018-25153-w

Fig.1

알고리즘  :  FBP algorithm +  deep CNN

201804 Science Report _ CT에서 artifact 줄여주는 GoogLeNet.pdf