Share Email Print

Proceedings Paper

Semi-supervised learned sinogram restoration network for low-dose CT image reconstruction
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

With the development of deep learning (DL), many deep learning (DL) based algorithms have been widely used in the low-dose CT imaging and achieved promising reconstruction performance. However, most DL-based algorithms need to pre-collect a large set of image pairs (low-dose/high-dose image pairs) and trains networks in a supervised end-to-end manner. Actually, it is not feasible in clinical to obtain such a large amount of paired training data, especially for high-dose ones. Therefore, in this work, we present a semi-supervised learned sinogram restoration network (SLSR-Net) for low-dose CT image reconstruction. The presented SLSR-Net consists of supervised sub-network and unsupervised sub-network. Specifically, different from the traditional supervised DL networks which only use low-dose/high-dose sinogram pairs, the presented SLSR-Net method is capable of feeding only a few supervised sinogram pairs and massive unsupervised low-dose sinograms into the network training procedure. The supervised pairs are used to capture critical features (i.e., noise distribution, and tissue characteristics) latent in a supervised way and the unsupervised sub-network efficiently learns these features using a conventional weighted least-squares model with a regularization term. Moreover, another contribution of the presented SLSR-Net method is to adaptively transfer learned feature distribution from supervised subnetwork with the paired sinograms to unsupervised sub-network with unlabeled low-dose sinograms to obtain high-fidelity sinogram with a Kullback-Leibler divergence. Finally, the filtered backprojection algorithm is used to reconstruct CT images from the obtained sinograms. Real patient datasets are used to evaluate the performance of the presented SLSR-Net method and the corresponding experimental results show that compared with the traditional supervised learning method, the presented SLSR-Net method achieves competitive performance in terms of noise reduction and structure preservation in low-dose CT imaging.

Paper Details

Date Published: 16 March 2020
PDF: 7 pages
Proc. SPIE 11312, Medical Imaging 2020: Physics of Medical Imaging, 113120B (16 March 2020); doi: 10.1117/12.2548985
Show Author Affiliations
Mingqiang Meng, Southern Medical Univ. (China)
Sui Li, Southern Medical Univ. (China)
Lisha Yao, Southern Medical Univ. (China)
Danyang Li, Southern Medical Univ. (China)
Manman Zhu, Southern Medical Univ. (China)
Qi Gao, Southern Medical Univ. (China)
Qi Xie, Xi'an Jiaotong Univ. (China)
Qian Zhao, Xi'an Jiaotong Univ. (China)
Zhaoying Bian, Southern Medical Univ. (China)
Jing Huang, Southern Medical Univ. (China)
Deyu Meng, Xi'an Jiaotong Univ. (China)
Dong Zeng, South China Univ. of Technology (China)
Jianhua Ma Sr., Southern Medical Univ. (China)

Published in SPIE Proceedings Vol. 11312:
Medical Imaging 2020: Physics of Medical Imaging
Guang-Hong Chen; Hilde Bosmans, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?