Abstract
Multimodal medical image fusion (MMIF) plays critical roles in image-guided clinical diagnostics and treatment. Pulse coupled neural network (PCNN) has been applied in image fusion for several years. In the schemes of image fusion based on PCNN, the authors have adjusted variables manually, so that it is difficult to get satisfying effects which limit in dealing with medical images with different modalities. This paper presents a quality-guided adaptive optimization method for MMIF, which is based on PCNN optimized by multi-swarm fruit fly optimization algorithm (MFOA). To reduce the implementation cost and improve the performance of the MFOA, quality assessment for multimodal medical image fusion was chosen to be the hybrid fitness function. Guided by such quality measurement, the adaptive PCNN using the MFOA (PCNN-MFOA) is proposed, which could automatically fit the optimal variables to the source images and enhance the fusion effect. The experimental results visually and quantitatively show that the proposed fusion strategy is more effective than the state-of-the-art methods and it is more effective in processing medical images with different modalities.
Highlights
Image fusion integrates different sensory information into a visual enhanced representational format [1]–[3]
To evaluate the effectiveness of the Pulse coupled neural network (PCNN)-multi-swarm fruit fly optimization algorithm (MFOA) strategy, the following fusion algorithms are used as comparison experiments, including convolutional sparse representation (CSR) [26], non-subsampled contourlet transform (NSCT) and PCNN with modified spatial frequency (NSCT-PCNN-SF) [13], guided filtering (GFF) [27], laplace transform and sparse representation (LP-SR) [28], union laplacian pyramid with multiple features (ULP-MF) [29], neuro-fuzzy (NF) [30], parameter-adaptive PCNN in non-subsampled shearlet transform (NSST) (NSST-PAPCNN) [16], local laplacian filtering and information of interest (LLF-II) [31], parallel saliency features (PSF) [32], where GFF, LP-SR are generally used to fuse anatomical- anatomical image, LLF-II, PSF are for anatomical-functional image, CSR, NSCT-PCNN-SF, ULP-MF, NF, NSST-PAPCNN are used to fuse anatomical-anatomical image, and to fuse anatomical-functional image
The choice of fitness function is determined by experiments
Summary
Image fusion integrates different sensory information into a visual enhanced representational format [1]–[3]. Multimodal medical image fusion (MMIF) provides a promising solution approach by integrating information of different modality images into a visual enhanced fused images, it aids radiologists in significant clinical diagnosis [6], [7]. MFOA is a global optimization approach, aiming to find the optimal solution search space by iteration This motivates us to exploit a quality-guided adaptive optimization to automatically determine the optimal parameters for fusing multimodal medical images. This paper proposes a quality-guided adaptive optimization method based on PCNN-MFOA. To the best of our knowledge, this is the first time that the QMMIF model is used as quality-guided adaptive optimization in the field of medical image fusion. Experimental results visually and quantitatively show that the proposed fusion strategy is more effective than state-of-the-art methods in processing medical images with different modalities. VL and αL represent normalizing constants. β is the linking parameter, which the weight of linking field. αθ and Vθ denote attenuation coefficient and threshold magnitude coefficient, respectively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
