Content-Preserving Unpaired Translation from Simulated to Realistic Ultrasound Images

TL;DR

This paper introduces ConPres, a novel framework for unpaired ultrasound image translation that preserves anatomical content while enhancing realism, bridging the gap between simulated and real ultrasound images using contrastive learning and class-conditional generation.

Contribution

The paper presents a new content-preserving translation method that combines contrastive learning, auxiliary segmentation tasks, and class-conditional generators for improved ultrasound image realism.

Findings

Outperforms state-of-the-art unpaired translation methods

Maintains anatomical content while improving realism

Demonstrates superior qualitative and quantitative results

Abstract

Interactive simulation of ultrasound imaging greatly facilitates sonography training. Although ray-tracing based methods have shown promising results, obtaining realistic images requires substantial modeling effort and manual parameter tuning. In addition, current techniques still result in a significant appearance gap between simulated images and real clinical scans. Herein we introduce a novel content-preserving image translation framework (ConPres) to bridge this appearance gap, while maintaining the simulated anatomical layout. We achieve this goal by leveraging both simulated images with semantic segmentations and unpaired in-vivo ultrasound scans. Our framework is based on recent contrastive unpaired translation techniques and we propose a regularization approach by learning an auxiliary segmentation-to-real image translation task, which encourages the disentanglement of content and style. In addition, we extend the generator to be class-conditional, which enables the incorporation of additional losses, in particular a cyclic consistency loss, to further improve the translation quality. Qualitative and quantitative comparisons against state-of-the-art unpaired translation methods demonstrate the superiority of our proposed framework.