|
Abstract A novel fusion algorithm for medical image based on sparse representation and pulse coupled neural network (PCNN) was proposed to meet the demand of computeraided diagnosis from the medical images. First, the K-SVD algorithm was used to obtain the redundant dictionary of the joint matrix which was obtained by sliding window technique. Next, sparse coefficients for the joint matrix were set up through orthogonal matching pursuit (OMP) algorithm. Then, the sparse coefficients were fused by a PCNN based on their characteristics. At last, the fused image was obtained by transforming the fused matrix which was got by the fused sparse coefficients and redundant dictionary. Ten groups of coaligned medical images were tested by experiments and the quality of the fused image was evaluated by five kinds of commonly used objective criterions. Comparing with the other two popular medical image fusion algorithms, the proposed algorithm was optimal for the four object indexes except for QAB/Findex, the mean of Piella, QAB/F and BSSIM indexes were 0.760 5, 0.877 1 and 0.537 3 respectively. The texture, edge and contrast of fused image were optimal. Subjective and objective analysis of the results showed the advantages of the proposed algorithm.
|
|
|
|
|
[1]Barra V, Boirev JY. A general framework for the fusion of anatomical and functional medical images [J]. NeuroImage, 2001, 13(3): 410-424.
[2]Das S, Kundu MK. NSCT-based multimodal medical image fusion using pulsecoupled neural network and modified spatial frequency [J]. Medical & Biological Engineering & Computing, 2012, 50(10): 1105-1114.
[3]杨谦, 齐翔林, 汪云九. 视皮层V1区简单细胞的稀疏编码策略 [J]. 计算物理, 2001, 18(2): 143-146.
[4]Johnson JL, Padgett ML. PCNN models and applications [J]. IEEE Trans Neural Netw, 1999, 10(3): 480-498.
[5]Li Min, Cai Wei, Zheng Tan. A regionbased multisensor image fusion scheme using pulsecoupled neural network [J]. 2006, 27(16): 1948-1956.
[6]Yang Shuyuan, Wang Min, Lu Yanxiong, et al. Fusion of multiparametric SAR images based on SWnonsubsampled contourlet and PCNN [J].2009,89(12): 2596-2608.
[7]Wang Zhaobin, Ma Yide, Gu J. Multifocus image fusion using PCNN [J]. Pattern Recogn, 2010, 43(6): 2003-2016.
[8]Aharon M, Elad M, Bruckstein A. KSVD: An algorithm for designing overcomplete dictionaries for sparse representation [J]. IEEE Transaction on Signal Processing, 2006, 54(11): 4311-4322.
[9]Yang Bin,Li Shutao. Multifocus image fusion and restoration with sparse representation [J]. IEEE Transactions on Instrumentation and Measurement, 2010, 59(4):884-892.
[10]Wang Zhaobin, Ma Yide, Cheng Feiyan, et al. Review of pulsecoupled neural networks [J]. Image Vision Comput, 2010, 28(1):5-13.
[11]Yang Yong. A Novel DWT Based Multifocus Image Fusion Method [C]// Sumesh EP,eds. Procedia Engineering. Nanjing: Elsevier, 2011: 177-181.
[12]Wang Zhou, Bovik AC. A universal image quality index [J]. IEEE Signal Processing Letters, 2002 ,9(3): 81-84.
[13]Qu Guihong, Zhang Dali, Yan Pingfang. Information measure for performace of image fusion [J]. Electronics Letters, 2002, 38(7): 313-315.
[14]Xydeas CS, Petrovic V. Objective image fusion performancemeasure [J]. Electronics Letters, 2000, 36(4):308-309.
[15]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.
|
|
|