A study on performance of reconstruction techniques using radon transform in medical imaging modalities

There are a number of medical imaging modalities available today involving X-Ray, Computed Tomography, Ultrasound imaging which are used in medical field for disease diagnosis and treatment planning. These imaging modalities reflect the state of the internal anatomy and dynamic body functions. In many medical imaging modalities, image reconstruction is a key component. For reconstruction of images, sufficient number of projections is required to compute a high quality image. In this paper, Radon Transform, which is able to transform lines inside an image into a domain of possible line parameters, is used to reconstruct the medical images. Since undesired effects such as noise can not be completely eliminated from the images, various filtering techniques are applied on the images to improve their performance. The quality of the images is measured by Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) to find the performance of the reconstructed images.