Projection image-to-image translation in hybrid X-ray/MR imaging

TL;DR

This paper introduces a novel method for translating MR projection images into X-ray projections using a modified image generator network with a gradient-based loss, enhancing high-frequency detail reproduction in hybrid imaging.

Contribution

The work presents a specialized image-to-image translation approach tailored for MR to X-ray projections, incorporating a gradient map in the loss function for improved detail.

Findings

Generated X-ray images have natural appearance.

The method outperforms baseline approaches.

Enhanced high-frequency detail reproduction.

Abstract

The potential benefit of hybrid X-ray and MR imaging in the interventional environment is large due to the combination of fast imaging with high contrast variety. However, a vast amount of existing image enhancement methods requires the image information of both modalities to be present in the same domain. To unlock this potential, we present a solution to image-to-image translation from MR projections to corresponding X-ray projection images. The approach is based on a state-of-the-art image generator network that is modified to fit the specific application. Furthermore, we propose the inclusion of a gradient map in the loss function to allow the network to emphasize high-frequency details in image generation. Our approach is capable of creating X-ray projection images with natural appearance. Additionally, our extensions show clear improvement compared to the baseline method.