9 March 2018 Low-dose CT reconstruction with MRF prior predicted from patch samples of normal-dose CT database
Author Affiliations +
Abstract
Markov random field (MRF) model-based penalty is widely used in statistical iterative reconstruction (SIR) of low dose CT (LDCT) reconstruction for noise suppression and edge-preserving. In this strategy, normal dose CT scans are usually used as a priori information to further improve the LDCT quality. However, repeated CT scans are needed and registration or segmentation is usually applied first when misalignment between the low-dose and normal-dose scans exists. The study aims to propose a new MRF prior model of SIR based on the NDCT database without registration. In the proposed model, MRF weights are predicted using optimal similar patch samples from the NDCT database. The patch samples are determined by evaluating the similarity with Euclidean distance between patches from NDCT and the target patch of LDCT. The proposed prior term is incorporated into the SIR cost function, which is to be minimized for LDCT reconstruction. The proposed method is tested on an artificial LDCT data based on a high-dose patient data. Preliminary result has proved its potential performance in edge and structure detail preservation.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Junyan Rong, Yuanke Zhang, Yuxiang Xing, Peng Gao, Tianshuai Liu, Zhengrong Liang, Hongbing Lu, "Low-dose CT reconstruction with MRF prior predicted from patch samples of normal-dose CT database", Proc. SPIE 10573, Medical Imaging 2018: Physics of Medical Imaging, 1057334 (9 March 2018); doi: 10.1117/12.2293446; https://doi.org/10.1117/12.2293446
PROCEEDINGS
5 PAGES


SHARE
Back to Top