Therapeutic Image Synthesis using Hybridization of Curvelet and Wavelet Transform

In order to recover an image that delivers as much information about the same organ at the same time, medical image fusion is a necessary task. Computed Tomography (CT) images, for example, provide the most accurate depiction of dense structures such as bones and implants and show them with the least amount of distortion, but they are unable to identify physiological changes. Soft tissue can be more clearly seen in an MR image. The determination of therapeutic image synthesis is to produce a richer and more precise description of a target object by combining data from multiple medical picture types. So that radiologists may report CT and MR scans as quickly and accurately as possible, it provides a simple interface. In this study, authors employ a hybridization approach, fusing the discrete wavelet transform with the discrete curvelet transform, to get desirable outcomes. MATLAB simulations are used to test the projected workbench in contradiction of the existing methods, using metrics such as PSNR (peak signal-to-noise ratio), MSE (Mean square error), association, and precision. In addition to low computational burden, the suggested workbench shows promising performance in all other metrics as well.