Ultrasound Variational Style Transfer to Generate Images Beyond the Observed Domain

Alex Ling Yu Hung, John M. Galeotti

Abstract: The use of deep learning in medical image analysis is hindered by insufficient annotated data and the inability of models to generalize between different imaging settings. We address these problems using a novel variational style-transfer neural network that can sample various styles from a computed latent space to generate images from a broader domain than what was observed. We show that using our generative approach for ultrasound data augmentation and domain adaptation during training improves the performance of the resulting deep learning models, even when tested within the observed domain.