Brain MRI super-resolution using 3D generative adversarial networks

TL;DR

This paper introduces a 3D GAN-based method for enhancing the resolution of MRI scans, leveraging volumetric data and adversarial training to produce higher quality images from low-resolution inputs.

Contribution

It presents a novel 3D GAN architecture for MRI super-resolution, combining adversarial and content losses, and explores different upsampling strategies for improved results.

Findings

Outperforms classical interpolation methods

Demonstrates potential for clinical 3D medical imaging enhancement

Provides open-source implementation for reproducibility

Abstract

In this work we propose an adversarial learning approach to generate high resolution MRI scans from low resolution images. The architecture, based on the SRGAN model, adopts 3D convolutions to exploit volumetric information. For the discriminator, the adversarial loss uses least squares in order to stabilize the training. For the generator, the loss function is a combination of a least squares adversarial loss and a content term based on mean square error and image gradients in order to improve the quality of the generated images. We explore different solutions for the upsampling phase. We present promising results that improve classical interpolation, showing the potential of the approach for 3D medical imaging super-resolution. Source code available at https://github.com/imatge-upc/3D-GAN-superresolution