Research On Multimodal Medical Image Fusion Method Based On Sparse Representation

Due to the diversity of medical image imaging mechanisms,the tissue information reflected by different modality medical images is quite different.For example,computed tomography?CT?images can clearly show dense structures such as bones,while magnetic resonance?MR?images can provide high-resolution anatomical information for soft tissues,but they each have their own fixed defects.In this case,multimodal medical image fusion becomes an effective solution,which can extract complementary information from different modal images and fuse them into a complete image,making it more significant.Features and auxiliary information helpful for diagnosis play a key role in medical diagnosis and clinical operation and become a powerful technology.In this paper,through the in-depth study of multimodal medical image fusion theory and sparse representation theory,the improvements and main research contents to address its disadvantages are as follows:The fusion of multimodal medical images is an important medical imaging method that integrates complementary information from multimodal images to produce new composite images.Sparse representation has achieved great success in medical image fusion in the past few years.However,given that the sparse representation method is based on sliding window technology,the ability to preserve the details of the fused image is insufficient.Therefore,a multimodal medical image fusion method based on convolution sparse representation double dictionary learning and adaptive PCNN is proposed.According to the low-rank and sparsity characteristics of the image,the method decomposes the source image into two parts,and constructs a double dictionary based on convolution sparse representation.The sparse component contains a large amount of detail textures,and the low-rank component contains basic information such as contour brightness.First,the low-rank feature and sparse feature are extracted from the training image to form two basic dictionaries to represent the test image.The dictionary learning model is improved by adding low-rank and sparse constraints to the low-rank component and the sparse component,respectively,to enhance the discriminability of the double dictionary.In the process of dictionary learning,the method of alternating iterative updating is divided into three parts,auxiliary variable update,sparse coding,and dictionary updates.A convolutional sparse and convoluted low-rank sub-dictionary for the training image is obtained by a three-part cyclic update.Then,the total variation regularization is incorporated into the image decomposition model,and the Fourier domain-based alternating direction multiplier method is used to obtain the representation coefficients of the source image sparse component and the low-rank component in the respective sub-dictionaries.The process is alternately divided into two parts iteratively,namely,convolution sparse coefficient update and convolution low-rank coefficient update.Second,the sparse component of the source image is obtained by convolving the convolutional sparse coefficient with the corresponding sub-dictionary.Similarly,the convolution low-rank coefficient is convolved with the corresponding sub-dictionary to obtain the low-rank component of the source image.The novel sum-modified spatial frequency of the sparse component is calculated as the external excitation of the pulse-coupled neural network to preserve the details of the image,and the link strength is adaptively determined by the regional average gradient to obtain a firing map of the sparse component.The novel sum-modified Laplacian of the low-rank component is calculated as the external excitation of the pulse coupled neural network,and the link strength is adaptively determined by the regional average gradient to obtain the firing map.The fused sparse components are obtained by comparing the number of firings of different sparse components,Similarly,the low-rank components of different source images are fused through the firing map.Finally,the fused image is obtained by combining convolution sparse and convolution low-rank components,thereby further improving the quality of the fused image.Through experimental simulation of grayscale and color images and comparison with other fusion methods,compared with other sparse representation methods,the proposed algorithm effectively improves the quality of multimodal medical image fusion,better preserves the detailed information of the source image,riches the information of the fused image and conforms to the visual characteristics of the human eye,thereby effectively assisting doctors in diagnosing diseases.Aiming at the problem of low single-dictionary expression ability and insufficient detail preservation ability for fusion image based on multi-scale medical image fusion method,the fusion method based on sparse representation has a combination of multi-scale and convolution sparseness.A multimodal medical image fusion method represented.The method firstly performs NSST decomposition on the registered source image,and uses sub-images of different scales as training images respectively,and uses the alternating direction multiplier method?ADMM?to solve the sub-dictionary;then the sub-dictions of different scales The image is convolutionally sparsely encoded to obtain the sparse coefficients of different sub-images.Secondly,the high-frequency sub-image coefficients are modified by the l₁-norm and the improved spatial frequency?novs sum-modified SF,NMSF?.The image is fused by the improved ₁l-norm combined with the regional energy;finally,the final fused image is obtained by inverse NSST.The experimental results show that the proposed method has good performance in contrast enhancement,detail extraction and information retention,and improves the quality of fused images.For the two improved methods proposed above,relevant experiments were performed using MATLAB platform and Python,and the results were compared with the latest fusion methods in recent literature.From the objective indicators of the experimental results and subjective visual analysis,the methods in this paper are has a good performance,indicating the advanced nature of this method.