Adaptive Gradient Balancing for Undersampled MRI Reconstruction and Image-to-Image Translation

TL;DR

This paper introduces an adaptive gradient balancing technique within a GAN framework for undersampled MRI reconstruction, improving image sharpness and detail preservation, and extends its application to image-to-image translation tasks.

Contribution

It proposes a novel Adaptive Gradient Balancing method combined with a Conditional Wasserstein GAN and a Densely Connected Network for enhanced MRI reconstruction and image translation.

Findings

Sharper MRI images with fewer artifacts

Effective recovery from sub-optimal adversarial training weights

Versatile application to image-to-image translation

Abstract

Recent accelerated MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning. However, these techniques sometimes struggle to reconstruct sharp images that preserve fine detail while maintaining a natural appearance. In this work, we enhance the image quality by using a Conditional Wasserstein Generative Adversarial Network combined with a novel Adaptive Gradient Balancing (AGB) technique that automates the process of combining the adversarial and pixel-wise terms and streamlines hyperparameter tuning. In addition, we introduce a Densely Connected Iterative Network, which is an undersampled MRI reconstruction network that utilizes dense connections. In MRI, our method minimizes artifacts, while maintaining a high-quality reconstruction that produces sharper images than other techniques. To demonstrate the general nature of our method, it is further evaluated on a battery of image-to-image translation experiments, demonstrating an ability to recover from sub-optimal weighting in multi-term adversarial training.