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