Shearlet Based Medical Image Fusion Using Pulse-Coupled Neural Network with Fuzzy Memberships
In this article, we propose a novel multimodal Medical Image Fusion (MIF) method based on a neuro-fuzzy technique in the transform (Non-Subsampled Shearlet Transform (NSST)) domain for spatially registered, multi-modal medical images. The source medical images are first decomposed by NSST. The low-frequency subbands (LFSs) are fused using the Max-selection rule. Fuzzy triangular memberships are derived from a specific neighborhood-region of each high-frequency coefficient. Then they (high-frequency subbands, HFSs) are fused using a biologically inspired neural network (Pulse Coupled Neural Network (PCNN)) according to our newly proposed rule. Then inverse NSST (INSST) is applied to the fused coefficients to get the fused image. Visual and quantitative analysis and comparisons with state-of-the-art MIF techniques show the effectiveness of the proposed scheme in fusing multimodality medical images.
KeywordsImage fusion Fuzzy triangular membership function Non-Subsampled Shearlet Transform (i.e. NSST) Pulse-coupled neural network
The authors would like to thank the anonymous referees for their constructive criticism and valuable suggestions. They also like to thank http://www.imagefusion.org/ and http://www.med.harvard.edu/aanlib/home.html for providing the source medical images. Prof. (Dr.) Amlan Chakrabarti likes to thank “CoE in Systems Biology and Biomedical Engineering, University of Calcutta supported by TEQIP-II Project” for supporting the research work.
- 13.Yang, Y., Park, D.S., Huang, S., Rao, N.: Medical image fusion via an effective wavelet-based approach. EURASIP J. Adv. Sig. Process. 2010, 44:1–44:13 (2010)Google Scholar