A Multimodality Medical Image Fusion Algorithm Based on Wavelet Transform

Abstract

Abstract. According to the characteristics of a medical image, this paper presents a multimodality medical image fusion algorithm based on wavelet transform. For the low-frequency coefficients of the medical image, the fusion algorithm adopts the fusion rule of pixel absolute value maximization; for the high-frequency coefficients, the fusion algorithm uses the fusion rule that combines the regional information entropy contrast degree selection with the weighted averaging method. Then the fusion algorithm obtains the fused medical image with inverse wavelet transform. We select two groups of CT/MRI images and PET/ MRI images to simulate our fusion algorithm and compare its simulation results with the commonly-used wavelet transform fusion algorithm. The simulation results show that our fusion algorithm cannot only preserve more information on a source medical image but also greatly enhance the characteristic and brightness information of a fused medical image, thus being an effective and feasible medical image fusion algorithm.

Medical image fusion: A survey of the state of the art

“…Similar to neural network, the kernel based operators such as support vector machines (SVM) can be used along with wavelets to achieve image fusion at feature levels [66]. Considering wavelets as a fusion operator, several feature processing methods can be combined such as wavelet-SVM [66], wavelet-texture measure [29], wavelet-MRA [30,67], wavelet-self adaptive operator [69], wavelet-resolution-entropy [70,72], nonlinear wavelet-shift invariant imaging [71], ICA-wavelet [86], wavelet-edge feature [75], waveletgenetic [59], wavelet-contourlet transform [81], neuro-fuzzy-wavelet [82] and wavelet-entropy [84].…”

A Survey on Multimodal Medical Image Fusion

“…The primary concept used by the wavelet based image fusion [26][27], [59,[61][62][63][64][65][66][67][68][69], [40], [70][71][72][73][74][75][76][77][78][79][80][81][82][83][84], [29,30,[32][33][34] is to extract the detail information from one image and inject it into another. The detail information in images is usually in the high frequency and wavelets would have the ability to select the frequencies in both space and time.…”

“…Similar to neural network, the kernel based operators such as support vector machines (SVM) can be used along with wavelets to achieve image fusion at feature levels [66]. Considering wavelets as a fusion operator, several feature processing methods can be combined such as wavelet-SVM [66], wavelet-texture measure [29], wavelet-MRA [30,67], wavelet-self adaptive operator [69], wavelet-resolution-entropy [70,72], nonlinear wavelet-shift invariant imaging [71], ICA-wavelet [86], waveletedge feature [75], wavelet-genetic [59], wavelet-contourlet transform [81], neuro-fuzzy-wavelet [82] and wavelet-entropy [84].…”

Medical image fusion using combination of PCA and wavelet analysis

“…Wavelets are oscillatory function with finite duration having zero average value. The irregularity and good localization are the properties that provide a good platform for the analysis of signal with discontinuities [34].…”