An Improved Medical Image Fusion Method Based on Nonsubsampled Contourlet Transform

Abstract:

In order to further improve the quality of medical image fusion,an improved medical image fusion method, based on nonsubsampled contourlet transform (NSCT),is proposed in the paper. A fusion rule based on the improved pulse coupled neural network (PCNN) is adopted in low frequency sub-band coefficient. Because human visual is more sensitive to all local region pixels instead of single pixel,it is more reasonable that the region information stimulates PCNN instead of single pixel. Each neuron of PCNN model is stimulated by the region spatial frequency of low frequency sub-band coefficient .Low frequency sub-band coefficient is determined by the times of firing. When choosing the bandpass directional sub-band coefficients, the directional characteristics of NSCT has been made best use of in the paper.A fusion rule based on sum-modified Laplacian is presented in bandpass directional sub-band cosfficients.The experiment results show that the proposed method can greatly improve the quality of fusion image compared with traditional fusion methods.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 1082-1087
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.1082
• Online since: July 2014
• Authors: Yan Chun Yang*, Jian Wu Dang, Yang Ping Wang
• Keywords: Medical Image Fusion, Nonsubsampled Contourlet Transform (NSCT), Pulse Coupled Neural Network (PCNN), Region Spatial Frequency, Sum-Modified Laplacian

References

[1] Bhatnagar G, Wu Q. M. J, Liu Zheng. Human visual system inspired multi-modal medical image fusion framework [J]. Expert Systems With Applications, 2013, 40(5): 1708-1720.

DOI: 10.1016/j.eswa.2012.09.011

[2] HillP R, BullD R, C N. Canagarajah. Image fusion using a new framework for complexwavelet transforms[A]. In: Proceedings IEEE Interational Con- ference on Image Processing[C], Genova, Italy 2005, 2: 1338-1341.

[3] L. Yang B.L. Guo,W. Ni. Multimodality medical image fusion based on multiscale geometric analysis of contourlet transform[J]. Neurocomputing, 2008, 72(8): 203-211.

DOI: 10.1016/j.neucom.2008.02.025

[4] Da Cunha A L, Zhou J P, Do M N. The nonsubsampled contourlet transform：theory, design, and applications[J]. IEEE Transactions on Image Processing(S1057-7149), 2006, 15(10)：3089-3101.

DOI: 10.1109/tip.2006.877507

[5] Wei Huang, Zhong Liang-jing. Multi-focus image fusion using pulse coupled neural network [J]. Patter Recognition Letters, 2007, 28(9)：1123-1132.

DOI: 10.1016/j.patrec.2007.01.013

[6] Chen Hao. Study on multi-source image fusion based on multi-scale transform[D]. [Doctoral dissertation], Changchun: Chinese Academy of Science, (2010).

[7] Xia Jia-xing, Duan Xian-hua, Wei Shi-chao. Application of adaptive PCNN based on neighborhood to medical image fusion[J]. Application Research of Computers, 2011, 28(10): 3929-3933.

[8] Kong Jun, Zheng Kai-yuan, Zhang Jing-bo, et al. Multi-focus image fusion using spatial frequency and genetic algorithm [J]. International Journal of Computer Science and Network Security, 2008, 8(2) : 220-224.

[9] Wei Huang, Zhong Liang-jing. Evaluation of focus measures in multi-focus image fusion[J]. Pattern Recognition Letters(S0167-8655), 2007, 28(4)：493-500.

DOI: 10.1016/j.patrec.2006.09.005

[10] Pajares G, Cruzm. A wavelet-based image fusion tutorial[J]. Pattern Recognition, 2004, 37 (9) : 1855-1872.

DOI: 10.1016/j.patcog.2004.03.010

[11] Jia Jian, Jiao Li-chen, Sun Qiang. The Nonsubsampled Contourlet Transform in Multisensor Images Fusion[J]. ACTA ELECTRONICA SINICA, 2007 , 35(10): 1934-(1938).

[12] Guo Chuan-qi, Wang Wen-ge, Chu Bin-bin. Improved image fusion algorithm based on PCNN[J]. Computer Engineering and Applications, 2011, 47(19): 176-178.

[13] Xydeas C S, Petrovic V. Objective image fusion performance measure. Electronics Letters, 2000, 36(4): 308-309.

DOI: 10.1049/el:20000267