Combination of wavelet and contourlet transforms for PET and MRI image fusion

Image fusion is a widely used technique for enhancing the interpretation quality of images in medical application, which use different medical imaging sensors. This paper presents an image fusion framework for images acquired by using two distinct medical imaging sensor modalities (i.e. PET and MRI) using a combination of Stationary Wavelet Transform (SWT) and Non Sub-sampled Contourlet Transform (NSCT). We use a cascaded combination of SWT and NSCT to benefit advantages of SWT at the first step of the proposed method. Then, to decrease the SWT's drawbacks such as shift variance, poor directionality and absence of phase information, we employ Principal Component Analysis (PCA) algorithm in the SWT domain to minimize the redundancy. In the second step the maximum fusion rule is used in the NSCT domain to enhance the diagnostic features. The experimental results demonstrate that the proposed method is better than various existing transform-based and spatial based fusion methods and some other hybrid methods, in terms of both subjective and objective evaluations.