Deep Image Translation for Enhancing Simulated Ultrasound Images
This work addresses a domain-specific problem for sonographer training by improving simulated ultrasound image quality without increasing computation time, though it is incremental as it builds on existing image-to-image translation methods.
The paper tackles the trade-off between image quality and interactivity in ultrasound simulation by introducing a deep learning approach that enhances low-quality simulated images, achieving improvements of 7.2% in Fréchet Inception Distance and 8.9% in patch-based Kullback-Leibler divergence.
Ultrasound simulation based on ray tracing enables the synthesis of highly realistic images. It can provide an interactive environment for training sonographers as an educational tool. However, due to high computational demand, there is a trade-off between image quality and interactivity, potentially leading to sub-optimal results at interactive rates. In this work we introduce a deep learning approach based on adversarial training that mitigates this trade-off by improving the quality of simulated images with constant computation time. An image-to-image translation framework is utilized to translate low quality images into high quality versions. To incorporate anatomical information potentially lost in low quality images, we additionally provide segmentation maps to image translation. Furthermore, we propose to leverage information from acoustic attenuation maps to better preserve acoustic shadows and directional artifacts, an invaluable feature for ultrasound image interpretation. The proposed method yields an improvement of 7.2% in Fréchet Inception Distance and 8.9% in patch-based Kullback-Leibler divergence.