MRI and PET Image Fusion by Using Curvelet Transform

The fusion of medical images is very useful for clinical application. Generally,the PET image indicates the function of tissue and the MRI image shows theanatomy of tissue. In this article we fused MRI and PET images and the purpose isadding structural information from MRI to PET image. The images decomposedwith Curvelet Transform, and then two images fused with applying fusion rules. Weused MATLAB software for fused images and evaluated the result. The data setconsists 34 images of color PET images and high resolution MRI images. The brainimages are classified into two groups, normal (Coronal, Sagittal and Transaxial)and Alzeimer’s disease dataset images. Finally we used visual and quantitativecriteria to evaluate the fusion result. In quantitative evaluation we used entropy,discrepancy and overall performance. Results show the amount of entropy, achievedby the proposed method, was the highest and amount of discrepancy and overallperformance was the lowest. The small amount of discrepancy, overall performanceand high amount of entropy means high quality

MRI and PET Image Fusion by Using Curvelet Transform Keywords:

Image Fusion , Multiscale Geometric Analysis , Curvelet Transform , Fusion Rules