A medical image fusion method based on SIST and adaptive PCNN

In order to improve the performance of medical image fusion, a novel medical image fusion method is proposed based on Shift-invariant Shearlet Transform (SIST) and adaptive Pulse coupled neural network (PCNN). Firstly, SIST is employed to decompose source images respectively, to get one low-pass sub-image and some band-pass directional sub-band images, which have the same size as source images. Secondly, the fusion rule based on the local energy and the local variance is used to fuse low frequency coefficients, meanwhile, the fusion rule based on adaptive PCNN is used to fuse band-pass directional sub-band coefficients, here, the improved spatial frequency(SF) in SIST domain is used as the input of PCNN model, and the gradient energy (EOG) is used as the link strength of the PCNN model. Finally, the final fused image is obtained by the inverse SIST. Compared with other methods, this proposed can not only well preserve the useful information from the source images, but also improve the accuracy of the fusion image effectively.

[1]  Chun-Liang Hsu,et al.  EOG-based Human-Computer Interface system development , 2010, Expert Syst. Appl..

[2]  Shuai Ding,et al.  Image Fusion Algorithm Based on Nonsubsampled Contourlet Transform , 2013 .

[3]  Lei Wang,et al.  Multi-modal medical image fusion using the inter-scale and intra-scale dependencies between image shift-invariant shearlet coefficients , 2014, Inf. Fusion.

[4]  Yu Liu,et al.  Multi-focus image fusion with a deep convolutional neural network , 2017, Inf. Fusion.

[5]  M. Hossny,et al.  Comments on 'Information measure for performance of image fusion' , 2008 .

[6]  W. Kong,et al.  Technique for infrared and visible image fusion based on non-subsampled shearlet transform and spiking cortical model , 2015 .

[7]  X. Li,et al.  Efficient fusion for infrared and visible images based on compressive sensing principle , 2011 .

[8]  Miao Qiguang.  Fusion algorithm of infrared and visible light images based on NSCT transform , 2008 .

[9]  Vinod Kumar,et al.  Nonsubsampled shearlet based CT and MR medical image fusion using biologically inspired spiking neural network , 2015, Biomed. Signal Process. Control..

[10]  Huiqian Du,et al.  Multimodality medical image fusion algorithm based on gradient minimization smoothing filter and pulse coupled neural network , 2016, Biomed. Signal Process. Control..

[11]  Vinod Kumar,et al.  CT and MR Image Fusion Scheme in Nonsubsampled Contourlet Transform Domain , 2014, Journal of Digital Imaging.

[12]  Yide Ma,et al.  A new adaptive filtering method for removing salt and pepper noise based on multilayered PCNN , 2016, Pattern Recognit. Lett..

[13]  G. Easley,et al.  Sparse directional image representations using the discrete shearlet transform , 2008 .

[14]  Minh N. Do,et al.  The Nonsubsampled Contourlet Transform: Theory, Design, and Applications , 2006, IEEE Transactions on Image Processing.

[15]  Demetrio Labate,et al.  Optimally Sparse Multidimensional Representation Using Shearlets , 2007, SIAM J. Math. Anal..

[16]  Zheng We.  Thyroid Image Fusion Based on Shearlet Transform and Sparse Representation , 2015 .

[17]  Hari Om,et al.  Medical Image Fusion Based on Wavelet Transform , 2014 .