3 March 2017 Comparison of texture synthesis methods for content generation in ultrasound simulation for training
Author Affiliations +
Abstract
Navigation and interpretation of ultrasound (US) images require substantial expertise, the training of which can be aided by virtual-reality simulators. However, a major challenge in creating plausible simulated US images is the generation of realistic ultrasound speckle. Since typical ultrasound speckle exhibits many properties of Markov Random Fields, it is conceivable to use texture synthesis for generating plausible US appearance. In this work, we investigate popular classes of texture synthesis methods for generating realistic US content. In a user study, we evaluate their performance for reproducing homogeneous tissue regions in B-mode US images from small image samples of similar tissue and report the best-performing synthesis methods. We further show that regression trees can be used on speckle texture features to learn a predictor for US realism.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Oliver Mattausch, Elizabeth Ren, Michael Bajka, Kenneth Vanhoey, Orcun Goksel, "Comparison of texture synthesis methods for content generation in ultrasound simulation for training", Proc. SPIE 10135, Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling, 1013523 (3 March 2017); doi: 10.1117/12.2250604; https://doi.org/10.1117/12.2250604
PROCEEDINGS
10 PAGES


SHARE
Back to Top