Hybrid-Domain Neural Network Processing for Sparse-View CT Reconstruction

X-ray computed tomography (CT) is one of the most widely used tools in medical imaging, industrial nondestructive testing, lesion detection, and other applications. However, decreasing the projection number to lower the X-ray radiation dose usually leads to severe streak artifacts. To improve the qu...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on radiation and plasma medical sciences 2021-01, Vol.5 (1), p.88-98
Main Authors: Hu, Dianlin, Liu, Jin, Lv, Tianling, Zhao, Qianlong, Zhang, Yikun, Quan, Guotao, Feng, Juan, Chen, Yang, Luo, Limin
Format: Article
Language:English
Subjects:
Algorithms
Bioengineering
Biomedical imaging
Computed tomography
Convolution
Deep learning
Domains
hybrid-domain processing
Image quality
Image reconstruction
Information processing
Interpolation
Life Sciences
Medical imaging
Neural networks
Nondestructive testing
Radiation dosage
residual learning
sparse-view computed tomography (SVCT) reconstruction
X-rays
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:X-ray computed tomography (CT) is one of the most widely used tools in medical imaging, industrial nondestructive testing, lesion detection, and other applications. However, decreasing the projection number to lower the X-ray radiation dose usually leads to severe streak artifacts. To improve the quality of the images reconstructed from sparse-view projection data, we developed a hybrid-domain neural network (HDNet) processing for sparse-view CT (SVCT) reconstruction in this study. The HDNet decomposes the SVCT reconstruction problem into two stages and each stage focuses on one mission, which reduces the learning difficulty of the entire network. Experiments based on the simulated and clinical datasets are performed to demonstrate the performance of the proposed method. Compared with other competitive algorithms, quantitative and qualitative results show that the proposed method makes a great improvement on artifact suppression, tiny structure restoration, and contrast retention.
ISSN:2469-7311
2469-7303
DOI:10.1109/TRPMS.2020.3011413