Three-Band MRI Image Fusion: A Curvelet Transform Approach

Abstract

In magnetic resonance imaging (MRI), there are three bands of images (“MRI triplet”) available, which are T1-, T2- and PD%weighted images. The three images of a MRI triplet provide complementary structure information and therefore it is useful for diagnosis and subsequent analysis to combine three-band images into one. We propose an Curvelet transform approach for three-band MRI image fusion and Curvelet transform approach is further optimized utilizing quantitative fusion metrics such as the Entropy, Difference Entropy, Standard Deviation, image quality index (IQI) and ratio spatial frequency error (rSFe). We fused and analyzed several MRI triplets datasets from the Philips HealthCare, Bangalore, India. We have also performed fusion of the MRI triplets dataset with the CT image such that all the four images are fused to produce a multi-modality image.This fused images can significantly benefit medical diagnosis and also the further image processing such as, visualization (colorization), segmentation, classification and computer-aided diagnosis (CAD).