How to realize Multimodal Anatomical Image Fusion based on matlab contrast and structure extraction
This article mainly explains "how to realize multimodal anatomical image fusion based on matlab contrast and structure extraction". Interested friends may wish to have a look. The method introduced in this paper is simple, fast and practical. Let's let the editor take you to learn how to achieve multimodal anatomical image fusion based on matlab contrast and structure extraction.
A brief introduction to image fusion
The application of multimodal image registration and fusion technology can combine different medical images organically and provide more information for clinical diagnosis and treatment. The concept, method and significance of multimodal medical image registration and fusion are introduced. Finally, the analysis method of wavelet transform is briefly introduced.
Part of the source code clear; close all; clc; warning off%% A Novel Multi-Modality Anatomical Image FusionMethod Based on Contrast and Structure Extraction% F = fuseImage (I mulyi-modal anatomical image sequence%scale scale)% Inputs:%I-a mulyi-modal anatomical image sequence%scale-scale factor of dense SIFT, the default value is 16%% load images from the folder that contain multi-modal image to be fused%I=load_images ('. / Dataset\ CT-MRI\ Pair 1'); I=load_images ('. / Dataset\ MR-T1-MR-T2\ Pair 1') % I=load_images ('. / Dataset\ MR-Gad-MR-T1\ Pair 1');% Show source input images figure;no_of_images = size (IMagne4); for I = 1:no_of_images subplot (2jinglagi); imshow (I (:, I)); endsuptitle ('Source Images');% F=fuseImage (IMagne16);% Output: F-the fused imageF=rgb2gray (F); figure;imshow (F); function [F] = fuseImage (iMagazine) addpath (' Pyramid_Decomposition') Addpath ('Guided_Filter'); addpath (' Dense_SIFT'); tic%% = size (I); imgs=im2double (I); IA=zeros (Hreco Wpenc C penny N); for i=1:NIA (:, I) = enhnc (imgs (:, I)); end%%imgs_gray=zeros (HMagre WJE N); for iRefer1 imgs N imgs_gray (:,:, I) = rgb2gray (IA (:, I)) End%%% dense sift calculationdsifts=zeros (Hrecinct Wreco 32dint N, 'single'); for ionomer 1D N img=imgs_gray (:,:, I); ext_img=img_extend (img,scale/2-1); [dsifts (:, I)] = DenseSIFT (ext_img, scale, 1); end%%%local contrastcontrast_map=zeros (HrecoverWrect N); for ionomer N contrast_map (:,:, I) = sum (dsifts (:, I), 3) End%winner-take-all weighted average strategy for local contrast [x, labels] = max (contrast_map, [], 3); clear x-machine for ionome1max N mono=zeros (HMague W); mono (labels==i) = 1; contrast_map (:,:, I) = mono;end%% Structure h = [1-1]; structure_map=zeros (HJEO WJN) For i=1:Nstructure_map (:,:, I) = abs (conv2 (imgs_gray (:,:, I)) + abs (conv2 (imgs_gray (:,:, I);% EQ 13 end%winner-take-all weighted average strategy for structure [a, label] = max (structure_map, [], 3); clear x position for iMagn1N monoo=zeros (HMague W); monoo (label==i) = 1; structure_map (:,:, I) = monoo N weight_map (:,:, I) = fastGF (weight_map (:,:, I), 12 weight_map (:,:, I); end% normalizing weight maps%weight_map = weight_map + 10 ^-25;% avoids division by zeroweight_map = weight_map./repmat (sum (weight_map,3), [1 N]) % Pyramid Decomposition% create empty pyramidpyr = gaussian_pyramid (zeros (HPowerWMagol 3)); nlev = length (pyr);% multiresolution blendingfor i = 1V N% construct pyramid from each input image% blend for b = 1:nlev w = repmat (pyrW {b}, [113]); pyr {b} = pyr {b} + w. * pyrI {b}; end end% reconstructF = reconstruct_laplacian_pyramid (pyr); tocend III, run result
At this point, I believe you have a deeper understanding of "how to achieve multimodal anatomical image fusion based on matlab contrast and structure extraction". You might as well do it in practice. Here is the website, more related content can enter the relevant channels to inquire, follow us, continue to learn!
