SCATGAN for Reconstruction of Ultrasound Scatterers Using Generative Adversarial Networks
This work addresses the challenge of generating realistic ultrasound simulations for training sonographers, but it is incremental as it applies existing GAN methods to a specific domain problem.
The authors tackled the problem of estimating ultrasound scatterer maps from B-mode images, which is nontrivial and essential for realistic simulation, by using Generative Adversarial Networks for image translation, achieving robust reconstruction results invariant to imaging settings and running orders of magnitude faster than optimization-based techniques.
Computational simulation of ultrasound (US) echography is essential for training sonographers. Realistic simulation of US interaction with microscopic tissue structures is often modeled by a tissue representation in the form of point scatterers, convolved with a spatially varying point spread function. This yields a realistic US B-mode speckle texture, given that a scatterer representation for a particular tissue type is readily available. This is often not the case and scatterers are nontrivial to determine. In this work we propose to estimate scatterer maps from sample US B-mode images of a tissue, by formulating this inverse mapping problem as image translation, where we learn the mapping with Generative Adversarial Networks, using a US simulation software for training. We demonstrate robust reconstruction results, invariant to US viewing and imaging settings such as imaging direction and center frequency. Our method is shown to generalize beyond the trained imaging settings, demonstrated on in-vivo US data. Our inference runs orders of magnitude faster than optimization-based techniques, enabling future extensions for reconstructing 3D B-mode volumes with only linear computational complexity.