基于剪切波变换的医学图像融合算法

doi:10.3969/j.issn.0258-8021. 2013. 03.05

摘要
图/表
参考文献
相关文章 (8)

全文: PDF (788 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要剪切波变换是一种新颖的多尺度几何分析工具，具有多分辨率、多方向性、效率较高等优点，比小波变换、曲波变换、轮廓波变换等图像表示方法有独特有的优势。基于剪切波变换提出一种医学图像融合算法，先将原始图像通过剪切波变换分解为低频子带图像和高频方向子带图像，然后采用非负矩阵分解方法融合低频子带系数，再通过深入研究人类视觉系统的特性提出最大视觉能量对比度方法，利用局部对比度和局部区域的能量和进行高频方向子带系数的融合，最后通过剪切波逆变换得到融合图像。两组实验均显示所提出的融合方法在与其余3种融合方法的比较中，采用的5项客观评价指标均有4项指标达到最优值，证明所提出的方法获取的融合图像效果最好。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	阿都建华^* 王邦平王珂王艳

关键词 ：医学图像, 图像融合, 剪切波, 非负矩阵分解（NMF）, 人类视觉系统

Abstract：Shearlet transform is a novel multiscale geometric analysis tool that has many virtue such as multiresolution, multidirectional, high efficiency and has unique advantages compared with the wavelet transform, curvelet transform and contourlet transform. This paper proposed a novel fusion method for medical image based on shearlet transform. First, two original images were decomposed into different frequency sub-band coefficients by using shearlet. Next, the selection of the lowfrequency sub-band coefficient and the high-frequency directional sub-band coefficient were discussed. The method based on non-negative matrix factorization（NMF）was used to fuse the low-frequency sub-band coefficient, and for the high-frequency directional sub-band coefficient, this paper proposed a maximum visual energy contrast method that chose coefficient based on the local contrast and the sum of local regional energy after studying the human visual characteristics closely. At last, the fused image was obtained by performing the inverse shearlet on the combined coefficients. The proposed fusion method was compared with the other three fusion methods in two sets of experiments, and four of the five objective evaluation indicators also have reached the optimal value. In conclusion, the proposed fusion method has a considerable improvement in subjective fusion quality and objective evaluation

Key words： medical image ;image fusion shearlet non-negative matrix factorization human visual system

基金资助:国家自然科学基金（61071162）；四川省教育厅一般项目（13ZB0085）

引用本文:

阿都建华^* 王邦平王珂王艳. 基于剪切波变换的医学图像融合算法[J]. 中国生物医学工程学报, 2013, 32(3): 284-291.
ADU Jian Hua^*WANG Bang Ping WANG Ke WANG Yan. An Algorithm of Medical Image Fusion Based on Shearlet Transformation. journal1, 2013, 32(3): 284-291.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021. 2013. 03.05 或 http://cjbme.csbme.org/CN/Y2013/V32/I3/284

［1］陈晓艳, 李健楠, 王化祥. 一种电阻抗图像与CT 图像融合方法研究［J］.中国生物医学工程学报,2012,30(6): 892-896.
［2］Constantinos S, Pattichis MS, MicheliTzanakou E. Medical imaging fusion applications: An overview［C］ //Conference Record of the ThirtyFifth Asilomar Conference on Signals, Systems and Computers. Pacific Grove: IEEE,2001:1263-1267.
［3］Das S, Kundu MK. NSCTbased multimodal medical image fusion using pulsecoupled neural network and modified spatial frequency ［J］. Medical and Biological Engineering and Computing, 2012, 50(10): 1105-1114.
［4］Li Shutao, Yin Haitao, Fang Leyuan. Groupsparse representation with dictionary learning for medical image denoising and fusion［J］. IEEE Transactions on Biomedical Engineering, 2012,59(12): 3450 - 3459.
［5］Singh R, Srivastava R, Prakash O, et al. Multimodal medical image fusion in dual tree complex wavelet transform domain using maximum and average fusion rules［J］. Journal of Medical Imaging and Health Informatics, 2012,2(2): 168-173.
［6］Townsend DW, Beyer T. A combined PET/CT scanner: the path to true image fusion［J］. British journal of Radiology, 2002, 75(9): S24-S30.
［7］Yang Liu, Guo Baolong, Ni Wei. Multimodality medical image fusion based on multiscale geometric analysis of contourlet transform［J］.Neurocomputing, 2008, 72(1): 203-211.
［8］杨立才, 刘延梅, 刘欣, 等. 基于小波包变换的医学图像融合方法［J］. 中国生物医学工程学报, 2009, 28(1): 12-16.
［9］Guo Kanghui, Labate D. Optimally sparse multidimensional representation using shearlets［J］. SIAM journal on mathematical analysis, 2008, 39(1): 298-318.
［10］Kutyniok G, Labate D. Resolution of the wavefront set using continuous shearlets［J］. Trans Amer Math Soc, 2009, 361(5): 2719-2754.
［11］Easley G, Labate D, Lim WQ. Sparse directional image representations using the discrete shearlet transform［J］. Applied and Computational Harmonic Analysis, 2008, 25(1): 25-46.
［12］Candes EJ, Donoho DL. Curvelets: A surprisingly effective nonadaptive representation for objects with edges［C］//in Curve and Surface Fitting: SaintMalo, Nashville,USA: Vanderbilt University Press,2000:105-120.
［13］Do MN, Vetterli M. The contourlet transform: an efficient directional multiresolution image representation［J］. IEEE Transactions on Image Processing, 2005 , 14(12): 2091-2106.
［14］Cunha AL, Zhou J, Do MN. The nonsubsampled contourlet transform: theory, design, and applications［J］. IEEE Transactions on Image Processing, 2006 , 15(10): 3089-3101.［15］Miao Qiguang, Shi Cheng, Xua Pengfei, et al. A novel algorithm of imagefusion using shearlets［J］. Optics Communications,2011,284(6): 1540-1547.
［16］郑红,郑晨,闫秀生,陈海霞. 基于剪切波变换的可见光与红外图像融合算法［J］. 仪器仪表学报,2012,33(7):1613-1619.
［17］Lee DD, Seung HS. Learning the parts of objects by nonnegative matrix factorization［J］. Nature, 1999, 401(6755): 788-791.
［18］Lim WQ. The discrete shearlet transform: A new directional transform and compactly supported shearlet frames［J］. IEEE Transactions on Image Processing, 2010 , 19(5): 1166-1180.
［19］Seung D, Lee L. Algorithms for nonnegative matrix factorization［J］. Advances in Neural Information Processing Systems, 2001, 13(2): 556-562.
［20］苗启广,王宝树. 基于非负矩阵分解的多聚焦图像融合研究［J］. 光学学报, 2005, 25(6): 755-759.
［21］苗启广, 王宝树. 图像融合的非负矩阵分解算法［J］. 计算机辅助设计与图形学学报, 2005,17(7): 2029-2032.
［22］Legge GE, Foley JM. Contrast masking in human vision［J］. JOSA, 1980,70(12): 1458-1471.
［23］Watson AB. DCT quantization matrices visually optimized for individual images［C］// Human Vision, Visual Processing and Digital Display IV. San Jose: SPIE, 1993: 202-216.［24］Watson AB. Efficiency of a model human image code［J］. JOSA A, 1987,4(12): 2401-2417.
［25］Legge GE. A power law for contrast discrimination［J］. Vision Research, 1981, 21(4): 457-467.
［26］http://www.bic.mni.mcgill.ca/brainweb/.