Super Resolution MRI Using Generative Adversarial Networks

Abstract

This paper proposes a new frame for MRI Image Enhancement from a low-resolution (LR) image obtain from an early used MRI machine to generate a high-resolution (HR) MRI image. For this we use Generative Adversarial Networks, which have proven well in image recovery task. Here we simultaneously train two models which is Generative model that captures the data distribution in the LR MRI images, and a discriminative model that estimates the probability that a sample came from the training data rather than generator. For training generator, we have to maximize the probability of discriminator of making a mistake in comparing the fake image. For discriminator the adversarial loss uses least squares in order to stabilize the training and for generator the function is a combination of a least square adversarial loss and a content term based on mean square error and image gradient to improve the quality of generated images of MRI.