Medical low-dose CT image denoising based on variable order variational model
WANG Na1,2, ZHANG Quan1,2, LIU Yi1,2, JIA Lina1,2, GUI Zhiguo1,2
1. Shanxi Provincial Key Laboratory for Biomedical Imaging and Big Data, North University of China, Taiyuan 030051, China;
2. School of Information and Communication Engineering, North University of China, Taiyuan 030051, China
Abstract：Low-dose CT (LDCT) is widely used for clinical diagnosis to reduce radiation risk to patients. However, the radiation dose reduction introduces mottle noise and streak artifacts into the reconstructed LDCT images. In this paper, a post-processing technique is proposed based on variable order variational model to improve the LDCT image quality. The proposed variational model employs the edge indicator to control the order of variation, which can alternate between the first order total variation (TV) regularizer and second order bounded Hessian(BH) regularizer based on the image feature. Moreover, the proposed model is solved by split Bregman algorithm based on fast Fourier transform (FFT). The proposed model effectively suppresses mottle noise and streak artifacts, meanwhile preserving structure in reference to high-dose CT (HDCT) images. The reconstructed images and experimental data indicate that the proposed model has better quality than some existing state-of-the-art models.
王娜, 张权, 刘祎, 贾丽娜, 桂志国. 基于可变阶变分模型的医用低剂量CT图像去噪[J]. 北京航空航天大学学报, 2019, 45(9): 1757-1764.
WANG Na, ZHANG Quan, LIU Yi, JIA Lina, GUI Zhiguo. Medical low-dose CT image denoising based on variable order variational model. JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2019, 45(9): 1757-1764.
[1] ZHU Y,ZHAO M,ZHAO Y,et al.Noise reduction with low dose CT data based on a modified ROF model[J].Optics Express,2012,20(16):17987-18004.
[2] CHEN Y,YIN X,SHI L,et al.Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing[J].Physics in Medicine and Biology,2013,58(16):5803-5820.
[3] ZHANG C,ZHANG T,LI M,et al.Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares[J].BioMedical Engineering OnLine,2016,15(1):66.
[4] LEE D,LEE J,KIM H,et al.A feasibility study of low-dose single-scan dual-energy cone-beam CT in many-view under-sampling framework[J].IEEE Transactions on Medical Imaging,2017,36(12):2578-2587.
[5] CHEN Y,LIU J,HU Y,et al.Discriminative feature representation:An effective postprocessing solution to low dose CT imaging[J].Physics in Medicine and Biology,2017,62(6):2103-2131.
[6] CHEN Y,LIU J,XIE L,et al.Discriminative prior-prior image constrained compressed sensing reconstruction for low-dose CT imaging[J].Scientific Reports,2017,7(1):13868.
[7] FRUSH D P,DONNELLY L F,ROSEN N S.Computed tomography and radiation risks:What pediatric health care providers should know[J].Pediatrics,2003,112(4):951-957.
[8] BRENNER D J,HALL E J.Computed tomography-An increasing source of radiation exposure[J].New England Journal of Medicine,2007,357(22):2277-2284.
[9] CHEN Y,SHI L,YANG J,et al.Radiation dose reduction with dictionary learning based processing for head CT[J].Australasian Physical and Engineering Sciences in Medicine,2014,37(3):483-493.
[10] YANG Q,YAN P,ZHANG Y,et al.Low dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss[J].IEEE Transactions on Medical Imaging,2018,37(6):1348-1357.
[11] LIU J,MA J,ZHANG Y,et al.Discriminative feature representation to improve projection data inconsistency for low dose CT imaging[J].IEEE Transactions on Medical Imaging,2017,36(12):2499-2509.
[12] HASAN A M,MELLI A,WAHID K A,et al.Denoising low-dose CT images using multi-frame blind source separation and block matching filter[J].IEEE Transactions on Radiation and Plasma Medical Sciences,2018,2(4):279-287.
[13] DIWAKAR M,KUMAR M.CT image denoising using NLM and correlation-based wavelet packet thresholding[J].IET Image Processing,2018,12(5):708-715.
[14] YOU C,YANG Q,SHAN H,et al.Structure-sensitive multi-scale deep neural network for low-dose CT denoising[J].IEEE Access,2018,6:41839-41855.
[15] LIU Y,ZHANG Y.Low-dose CT restoration via stacked sparse denoising autoencoders[J].Neurocomputing,2018,284:80-89.
[16] 罗立民,胡轶宁,陈阳.低剂量CT成像的研究现状与展望[J].数据采集与处理,2015,30(1):24-34.LUO L M,HU Y N,CHEN Y.Research status and prospect for low-dose CT imaging[J].Data Acquisition and Processing,2015,30(1):24-34(in Chinese).
[17] LU W,DUAN J,QIU Z,et al.Implementation of high-order variational models made easy for image processing[J].Mathematical Methods in the Applied Sciences,2016,39(14):4208-4233.
[18] DUAN J,QIU Z,LU W,et al.An edge-weighted second order variational model for image decomposition[J].Digital Signal Processing,2016,49:162-181.
[19] DUAN J,WARD W O C,SIBBETT L,et al.Introducing anisotropic tensor to high order variational model for image restoration[J].Digital Signal Processing,2017,69:323-336.
[20] CHEN Y,YANG Z,HU Y,et al.Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means[J].Physics in Medicine and Biology,2012,57(9):2667-2688.
[21] BUADES A,COLL B,MOREL J M.A non-local algorithm for image denoising[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2005,2:60-65.
[22] WANG J,LU H,WEN J,et al.Multiscale penalized weighted least-squares sinogram restoration for low-dose X-ray computed tomography[J].IEEE Transactions on Biomedical Engineering,2008,55(3):1022-1031.
2019, Vol. 45 
