Nonsubsampled shearlet based CT and MR medical image fusion using biologically inspired spiking neural network. (April 2015)

• Record Type: Journal Article
• Authors: Singh, Sneha; Gupta, Deep; Anand, R.S.; Kumar, Vinod
• Is Part Of: Biomedical signal processing and control. Volume 18(2015)
• Page Start: 91
• Page End: 101
• Publication Date: 2015-04
• Subjects: Computed tomography (CT) -- Image fusion -- Magnetic resonance (MR) -- Nonsubsampled shearlet transform (NSST) -- Pulse coupled neural network; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2014.11.009
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The paper presents an algorithm for fusing the CT and MR medical images. The proposed method is based on the activity level measure and the PCNN model for fusing the image coefficients in nonsubsampled shearlet domain. The proposed method provides better fused images with more detail information compared to others. Abstract: This paper presents a new fusion scheme for the CT and MR medical images that utilizes both the features of the nonsubsampled shearlet transform (NSST) and spiking neural network. As a new image representation with the different features, the NSST is utilized to provide an effective representation of the image coefficients. Firstly, the source CT and MR images are decomposed by the NSST into several subimages. The regional energy is used to fuse the low frequency coefficients. High frequency coefficients are also fused using a pulse coupled neural network model that is used as a biologically inspired type neural network. It also retains the edges and detail information from the source images. Finally, the inverse NSST is used to produce the fused image. The performance of the proposed fusion method is evaluated by conducting several experiments on the different CT and MR medical image datasets. Experimental results demonstrate that the proposed method does not only produce better results by successfully fusing the different CT and MR images, but also ensures an improvement in the various quantitative parameters as compared to other existing methods.