基于在线字典学习的医学图像特征提取与融合

doi:10.3969/j.issn.0258-8021.2014. 03.04

摘要
图/表
参考文献
相关文章 (4)

全文: PDF (1407 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要提出一种基于在线字典学习(ODL)的医学图像特征提取与融合的新算法。首先，采用大小为8像素×8像素的滑动窗处理源图像，得到联合矩阵；通过ODL算法得到该联合矩阵的冗余字典，并利用最小角回归算法(LARS)计算该联合矩阵的稀疏编码；将稀疏编码列向量的1范数作为稀疏编码的活动级测量准则，然后根据活动级最大准则融合稀疏编码；最后根据融合后的稀疏编码和冗余字典重构融合图像。实验图像为20位患者的已配准脑部CT和MR图像，采用5种性能指标评价融合图像的质量，同两种流行的融合算法比较。结果显示，所提出算法的各项客观指标均值最优，Piella指数、QAB/F指数、MIAB/F指数、BSSIM指数和空间频率的均值分别为0.800 4、0.552 4、3.630 2、0.726 9和31.941 3，融合图像对比度、清晰度高，病灶的边缘清晰，运行速度较快，可以辅助医生诊断和临床治疗。

	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
	吴双邱天爽^#*高珊

关键词 ：图像融合, 在线字典学习算法(ODL), 最小角回归算法(LARS)

Abstract：An image features extraction and fusion algorithm based on online dictionary learning (ODL) is presented in this paper. Firstly, source images were combined into a joint matrix by the sliding window technique, the size of the sliding window was 8×8, the overcomplete dictionary was trained by ODL algorithm and the sparse codes were acquired by LARS algorithm; the activity level measurement of sparse codes was the L1 norm of its vector, then, the sparse codes were fused by activity level maximum rule; finally, the fused image was reconstructed by overcomplete dictionary and fused sparse codes. Coaligned medical images of twenty patients were tested by experiments and the quality of the fused image was evaluated by five kinds of commonly used objective criterions. Compared with the other two popular medical image fusion algorithms, objective criterions of the fusion result show the advantage of the proposed algorithm, the mean of Piella, QAB/F，MIAB/F， BSSIM and space frequency index is 0.800 4, 0.552 4,
3.630 2, 0.726 9 and 31.941 3, the fusion images of the proposed algorithm have high definition and contrast, clear texture and edge and fast speed, showing its application potentials of aiding clinical diagnoses and treatment.

Key words： image fusion online dictionary learning (ODL) least angle regression (LARS) algorithm

基金资助:国家自然科学基金（81241059，61172108）；国家科技支撑计划项目（2012BAJ18B06）

引用本文:

吴双邱天爽^#*高珊. 基于在线字典学习的医学图像特征提取与融合[J]. 中国生物医学工程学报, 2014, 33(3): 283-288.
WU Shuang QIU Tian Shuang^#*GAO Shan. Medical Image Features Extraction and Fusion Based on Online Dictionary Learning. journal1, 2014, 33(3): 283-288.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2014. 03.04 或 http://cjbme.csbme.org/CN/Y2014/V33/I3/283

［1］Das S, Kundu MK. NSCTbased multimodal medical image fusion using pulsecoupled neural network and modified spatial frequency ［J］. Medical & Biological Engineering & Computing, 2012, 50(10): 1105-1114.
［2］Pajares G, Cruz J. A waveletbased image fusion tutorial ［J］. Pattern Recognition, 2004, 39(9): 1855-1872.
［3］da Cunha AL, Zhou Jianping, Do MN. The nonsubsampled contourlet transform: theory, design, and Applications ［J］. IEEE Transactions on Image Processing, 2006, 15(10): 3089-3101.
［4］Wang Zhaobin, Ma Yide, Chengk Feiyan, et al. Review of pulsecoupled neural networks ［J］. Image and Vision Computing, 2010, 28(1): 5-13.
［5］Yu Nannan, Qiu Tianshuang, Liu Wenhong. Medical image fusion based on sparse representation with KSVD ［C］// World Congress on Medical Physics and Biomedical Engineering. Beijing: SpringerVerlag, 2013, 39: 550-553. 
［6］余南南, 邱天爽, 毕峰, 等. 基于KSVD的医学图像特征提取和融合［J］. 大连理工大学学报, 2012, 52(4): 605-609.
［7］Aharon M, Elad M, Bruckstein A. KSVD: An algorithm for designing overcomplete dictionaries for sparse representation ［J］. IEEE Transaction on Signal Processing, 2006, 54(11): 4311-4322.
［8］Mairal J, Bach F, Ponce J, et al. Online dictionary learning for sparse coding［C］// Proceedings of the 26th Annual International Conference on Machine Learning. New York: ACM, 2009: 689-696.
［9］Olshausen BA, Field DJ. Emergence of simplecell receptive field properties by learning a sparse code for natural images ［J］. Nature, 1996, 381(13): 607-609.
［10］Singh M, Singh S, Gupta S. An adaptive speckle suppression filter based on local statistics and edgemap for ultrasound images ［J］. Advanced Science Letters, 2013, 19(8): 2375-2379.
［11］Wang Zhou, Bovik AC. A universal image quality index ［J］. IEEE Signal Processing Letters, 2002, 9(3): 81-84.
［12］Qu Guihong, Zhang Dali, Yan Pingfang. Information measure for performance of image fusion ［J］. Electronics Letters, 2002, 38(7): 313-315.
［13］Xydeas CS, Petrovic V. Objective image fusion performance measure ［J］. Electronics Letters, 2000, 36(4): 308-309.
［14］Wang Zhou, Bovik AC, Sheikh HR, et al. Image Quality assessment: from error visibility to structural similarity ［J］. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
［15］马先喜, 彭力,徐红. 基于块同化的空间频率多聚焦图像融合算法研究［J］. 科学技术与工程, 2012, 12(1): 64-67.