Wavelet-Based High-Frequency Texture Fusion Low Energy CT/MRI Images

ABSTRACT: Most of wavelet-based texture fusion of CT/MRI images image fusion methods aim at obtaining as many as information from the different modality images. The fusion criterion is to minimize different error between the fused image and the input images. With respect to the medical diagnosis, the edges and outlines of the interested objects is more important than other information. Therefore, how to preserve the edge-like features is worthy of investigating for medical image fusion. As we know, the image with higher schemes, especially for medical diagnosis. Magnetic resonance imaging (MRI) is to obtain more information from the CT and extract energy and regional information entropy of texture features from images. In the process of fusion, we adopt the fusion rule of energy maximum for the wavelet low-frequency coefficients; give the fusion rule according to the comparison of energy and regional information entropy contrast between CT/MRI images for the wavelet high frequency coefficients. Finally, obtain the fused contrast contain more edge-like features. In term of this view, we proposed a new medical image fusion scheme based on an improved wavelet coefficient contrast, which is defined as the ratio of the maximum of detail components to the local mean of the corresponding approximate component. The visual experiments and quantitative assessments demonstrate the effectiveness of this method compared to present image fusio