DLIMD: Dictionary Learning based Image-domain Material Decomposition for spectral CT
Authors:
- Weiwen WuWWWeiwen Wu
- Haijun YuHYHaijun Yu
- Peijun ChenPCPeijun Chen
- Fulin LuoFLFulin Luo
- Fenglin LiuFLFenglin Liu
- Qian WangQWQian Wang
- Yining ZhuYZYining Zhu
- Yanbo ZhangYZYanbo Zhang
- Jian FengJFJian Feng
- Hengyong YuHYHengyong Yu
Preprint
Abstract
The potential huge advantage of spectral computed tomography (CT) is its capability to provide accuracy material identification and quantitative tissue information. This can benefit clinical applications, such as brain angiography, early tumor recognition, etc. To achieve more accurate material components with higher material image quality, we develop a dictionary learning based image-domain material decomposition (DLIMD) for spectral CT in this paper. First, we reconstruct spectral CT image from projections and calculate material coefficients matrix by selecting uniform regions of basis materials from image reconstruction results. Second, we employ the direct inversion (DI) method to obtain initial material decomposition results, and a set of image patches are extracted from the mode-1 unfolding of normalized material image tensor to train a united dictionary by the K-SVD technique. Third, the trained dictionary is employed to explore the similarities from decomposed material images by constructing the DLIMD model. Fourth, more constraints (i.e., volume conservation and the bounds of each pixel within material maps) are further integrated into the model to improve the accuracy of material decomposition. Finally, both physical phantom and preclinical experiments are employed to evaluate the performance of the proposed DLIMD in material decomposition accuracy, material image edge preservation and feature recovery.Keywords
All Related Versions
This publication has 41 references indexed in Scilit:
- Material Decomposition in X-ray Spectral CT Using Multiple Constraints in Image DomainJournal of Nondestructive Evaluation, 2019
- Low-dose spectral CT reconstruction using image gradient ℓ0–norm and tensor dictionaryApplied Mathematical Modelling, 2018
- Reduced iodinated contrast media for abdominal imaging by dual-layer spectral detector computed tomography for patients with kidney diseaseRadiology Case Reports, 2018
- Statistical image‐domain multimaterial decomposition for dual‐energy CTMedical Physics, 2017
- An algorithm for constrained one-step inversion of spectral CT dataPhysics in Medicine & Biology, 2016
- Dictionary learning based sinogram inpainting for CT sparse reconstructionOptik, 2014
- Dual energy spectral CT imaging of insulinoma—Value in preoperative diagnosis compared with conventional multi-detector CTEuropean Journal of Radiology, 2012
- Photon counting spectral CT versus conventional CT: comparative evaluation for breast imaging applicationPhysics in Medicine & Biology, 2011
- Material differentiation by dual energy CT: initial experienceEuropean Radiology, 2006
- Orthogonal least squares methods and their application to non-linear system identificationInternational Journal of Control, 1989