Joint sparsity and fidelity regularization for segmentation-driven CT image preprocessing  

作　　者：Feng LIU Huibin LI 

机构地区：[1]School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an 710049, China [2]Beijing Center for Mathematics and Information Interdisciplinary Sciences, Beijing 100037, China

出　　处：《Science China(Information Sciences)》2016年第3期142-148,共7页中国科学（信息科学）（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant No.11401464);the China Postdoctoral Science Foundation(Grant No.2014M560785)

摘　　要：In this paper, we propose a novel segmentation-driven computed tomography （CT） image prepro- cessing approach. The proposed approach, namely, joint sparsity and fidelity regularization （JSFR） model can be regarded as a generalized total variation （TV） denoising model or a generalized sparse representation de- noising model by adding an additional gradient fidelity regularizer and a stronger gradient sparsity regularizer. Thus, JSFR model consists of three terms： intensity fidelity term, gradient fidelity term, and gradient sparsity term. The interactions and counterbalance of these terms make JSFR model has the ability to reduce intensity inhomogeneities and improve edge ambiguities of a given image. Experimental results carried out on the real dental cone-beam CT data demonstrate the effectiveness and usefulness of JSFR model for CT image intensity homogenization, edge enhancement, as well as tissue segmentation.In this paper, we propose a novel segmentation-driven computed tomography （CT） image prepro- cessing approach. The proposed approach, namely, joint sparsity and fidelity regularization （JSFR） model can be regarded as a generalized total variation （TV） denoising model or a generalized sparse representation de- noising model by adding an additional gradient fidelity regularizer and a stronger gradient sparsity regularizer. Thus, JSFR model consists of three terms： intensity fidelity term, gradient fidelity term, and gradient sparsity term. The interactions and counterbalance of these terms make JSFR model has the ability to reduce intensity inhomogeneities and improve edge ambiguities of a given image. Experimental results carried out on the real dental cone-beam CT data demonstrate the effectiveness and usefulness of JSFR model for CT image intensity homogenization, edge enhancement, as well as tissue segmentation.

关 键 词：CT image HOMOGENIZATION enhancement tissue segmentation gradient fidelity gradient sparsity 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TM383.6[自动化与计算机技术—计算机科学与技术]