Sparse-sampling CT Sinogram Completion using Generative Adversarial Networks

• Published in: 2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI) pp. 640 - 644
• Main Authors: Liu, Jiancong, Li, Jiangwei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 17.10.2020
• Subjects: Computed tomography; computer memory; computerised tomography; Deep learning; deep learning method; FBP algorithms; GAN; generative adversarial networks; Generators; image reconstruction; interpolation; interpolation methods; iterative methods; low-dose Computed tomography; medical image processing; Phantoms; Pix2Pix; radiation dose; radiation therapy; severe streak artifacts; sinogram domain; sparse-sampled data; sparse-sampled sinogram; sparse-sampling CT sinogram completion; sparse-sampling image; synthesized sinograms; Training
• DOI: 10.1109/CISP-BMEI51763.2020.9263571

Sparse-sampling for low-dose Computed tomography (CT) is currently a subject of extensive investigations due to its potential to reduce the radiation dose. However, severe streak artifacts can be observed when reconstructing the sparse-sampled data with conventional FBP algorithms. Solutions to this problem fall into two categories - interpolation methods in the sinogram domain and iterative methods for reconstruction. The former often yield results with residual streak artifacts, and the latter require ample time and computer memory. In this work, we propose to use a deep learning method to complete the sparse-sampled sinogram. The network is named Pix2Pix, which is a conditional GAN structure. Results show our approach can accurately complete sinograms with excellent generalization ability. The synthesized sinograms can thus be reconstructed by FBP without streak artifacts.