Perceptual cGAN for MRI Super-resolution

TL;DR

This paper introduces a perceptual cGAN-based super-resolution method for MRI images, enhancing detail and resolution in low-quality scans to aid faster, more accurate medical diagnoses.

Contribution

It proposes a novel conditional GAN with perceptual loss tailored for MRI super-resolution, improving detail preservation in both isotropic and anisotropic images.

Findings

Enhanced image sharpness and detail in super-resolved MRI images

Improved performance over existing methods in quantitative metrics

Effective for both isotropic and anisotropic MRI data

Abstract

Capturing high-resolution magnetic resonance (MR) images is a time consuming process, which makes it unsuitable for medical emergencies and pediatric patients. Low-resolution MR imaging, by contrast, is faster than its high-resolution counterpart, but it compromises on fine details necessary for a more precise diagnosis. Super-resolution (SR), when applied to low-resolution MR images, can help increase their utility by synthetically generating high-resolution images with little additional time. In this paper, we present a SR technique for MR images that is based on generative adversarial networks (GANs), which have proven to be quite useful in generating sharp-looking details in SR. We introduce a conditional GAN with perceptual loss, which is conditioned upon the input low-resolution image, which improves the performance for isotropic and anisotropic MRI super-resolution.