sim2real: Cardiac MR Image Simulation-to-Real Translation via Unsupervised GANs

TL;DR

This paper introduces a novel unsupervised GAN-based method to translate simulated cardiac MR images into more realistic images, enhancing their utility for training deep learning models in cardiac image analysis.

Contribution

The work presents a new sim2real translation network that improves the realism of simulated cardiac MR images, addressing the realism gap in virtual datasets.

Findings

Sim2real images improve segmentation performance

Enhanced realism boosts deep learning training effectiveness

Virtual XCAT subjects with varied anatomies used for simulation

Abstract

There has been considerable interest in the MR physics-based simulation of a database of virtual cardiac MR images for the development of deep-learning analysis networks. However, the employment of such a database is limited or shows suboptimal performance due to the realism gap, missing textures, and the simplified appearance of simulated images. In this work we 1) provide image simulation on virtual XCAT subjects with varying anatomies, and 2) propose sim2real translation network to improve image realism. Our usability experiments suggest that sim2real data exhibits a good potential to augment training data and boost the performance of a segmentation algorithm.