A Novel Framework for Enhancement of Diagnostic Information in MR Imaging using Super-Resolution

Magnetic resonance imaging (MRI) is the most preferred modality for imaging soft tissues. In spite of several advantages, it has a limitation of slow data acquisition, which restricts its application in high resolution (HR) imaging. One viable solution is the post-processing approach using super-resolution (SR) to generate HR images within a clinically feasible time. The state-of-the-art SR methods are commonly producing good quality HR images, but most of them are not designed for clinical application and also involve high computational time. In this paper, we propose a region-of-interest based framework to enhance the diagnostic information in MR images for pathological use. Several experiments are carried out with pathological MRI datasets to evaluate the performance of the proposed technique. From the experimental results, we can conclude that the proposed method is a clinically feasible solution for the enhancement of diagnostic information in MR images.