Discriminative feature representation: an effective postprocessing solution to low dose CT imaging

被引:36
作者
Chen, Yang [1 ,2 ,3 ]
Liu, Jin [1 ,2 ,3 ]
Hu, Yining [1 ,2 ,3 ]
Yang, Jian [5 ]
Shi, Luyao [1 ,2 ,3 ]
Shu, Huazhong [1 ,2 ,3 ]
Gui, Zhiguo [4 ]
Coatrieux, Gouenou [6 ]
Luo, Limin [1 ,2 ,3 ]
机构
[1] Southeast Univ, Lab Image Sci & Technol, Nanjing 210096, Jiangsu, Peoples R China
[2] Ctr Rech Informat Biomed Sinofrancais LIA CRIBs, Rennes, France
[3] Southeast Univ, Key Lab Comp Network & Informat Integrat, Minist Educ, Nanjing, Jiangsu, Peoples R China
[4] North Univ China, Natl Key Lab Elect Measurement Technol, Beijing, Peoples R China
[5] Beijing Inst Technol, Sch Opt & Elect, Beijing Engn Res Ctr Mixed Real & Adv Display, Beijing 100081, Peoples R China
[6] Inst Mines Telecom, Telecom Bretagne, Unite Inserm LaTIM U1101, Technopole Brest Iroise,CS 83818, F-29238 Brest, France
关键词
discriminative feature representation (DFR); low dose CT (LDCT); high dose CT (HDCT); HDCT features; noise-artifact features; X-RAY CT; ORTHOGONAL MATCHING PURSUIT; COMPUTED-TOMOGRAPHY; ITERATIVE RECONSTRUCTION; SPARSE REPRESENTATION; QUALITY ASSESSMENT; MULTIDETECTOR CT; NOISE-REDUCTION; ABDOMINAL CT; HELICAL CT;
D O I
10.1088/1361-6560/aa5c24
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
This paper proposes a concise and effective approach termed discriminative feature representation (DFR) for low dose computerized tomography (LDCT) image processing, which is currently a challenging problem in medical imaging field. This DFR method assumes LDCT images as the superposition of desirable high dose CT (HDCT) 3D features and undesirable noise- artifact 3D features (the combined term of noise and artifact features induced by low dose scan protocols), and the decomposed HDCT features are used to provide the processed LDCT images with higher quality. The target HDCT features are solved via the DFR algorithm using a featured dictionary composed by atoms representing HDCT features and noise-artifact features. In this study, the featured dictionary is efficiently built using physical phantom images collected from the same CT scanner as the target clinical LDCT images to process. The proposed DFR method also has good robustness in parameter setting for different CT scanner types. This DFR method can be directly applied to process DICOM formatted LDCT images, and has good applicability to current CT systems. Comparative experiments with abdomen LDCT data validate the good performance of the proposed approach.
引用
收藏
页码:2103 / 2131
页数:29
相关论文
共 66 条
[11]   Bayesian statistical reconstruction for low-dose X-ray computed tomography using an adaptive-weighting nonlocal prior [J].
Chen, Yang ;
Gao, Dazhi ;
Nie, Cong ;
Luo, Limin ;
Chen, Wufan ;
Yin, Xindao ;
Lin, Yazhong .
COMPUTERIZED MEDICAL IMAGING AND GRAPHICS, 2009, 33 (07) :495-500
[12]   Analysis of Orthogonal Matching Pursuit Using the Restricted Isometry Property [J].
Davenport, Mark A. ;
Wakin, Michael B. .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2010, 56 (09) :4395-4401
[13]   Projected Cancer Risks From Computed Tomographic Scans Performed in the United States in 2007 [J].
de Gonzalez, Amy Berrington ;
Mahesh, Mahadevappa ;
Kim, Kwang-Pyo ;
Bhargavan, Mythreyi ;
Lewis, Rebecca ;
Mettler, Fred ;
Land, Charles .
ARCHIVES OF INTERNAL MEDICINE, 2009, 169 (22) :2071-2077
[14]   Noise Reduction to Decrease Radiation Dose and Improve Conspicuity of Hepatic Lesions at Contrast-Enhanced 80-kV Hepatic CT Using Projection Space Denoising [J].
Ehman, Eric C. ;
Guimaraes, Luis S. ;
Fidler, Jeff L. ;
Takahashi, Naoki ;
Ramirez-Giraldo, Juan Carlos ;
Yu, Lifeng ;
Manduca, Armando ;
Huprich, James E. ;
McCollough, Cynthia H. ;
Holmes, David, III ;
Harmsen, W. Scott ;
Fletcher, Joel G. .
AMERICAN JOURNAL OF ROENTGENOLOGY, 2012, 198 (02) :405-411
[15]   Image denoising via sparse and redundant representations over learned dictionaries [J].
Elad, Michael ;
Aharon, Michal .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2006, 15 (12) :3736-3745
[16]   A Decomposition Framework for Image Denoising Algorithms [J].
Ghimpeteanu, Gabriela ;
Batard, Thomas ;
Bertalmio, Marcelo ;
Levine, Stacey .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 25 (01) :388-399
[17]  
Hakansson M, 2009, SPIE MED IMAGING
[18]   Algorithm-Enabled Low-Dose Micro-CT Imaging [J].
Han, Xiao ;
Bian, Junguo ;
Eaker, Diane R. ;
Kline, Timothy L. ;
Sidky, Emil Y. ;
Ritman, Erik L. ;
Pan, Xiaochuan .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2011, 30 (03) :606-620
[19]   Adaptive streak artifact reduction in computed tomography resulting from excessive x-ray photon noise [J].
Hsieh, J .
MEDICAL PHYSICS, 1998, 25 (11) :2139-2147
[20]  
Hsieh J, 2011, INVERSE PROBL, V27