Deep Network for Scatterer Distribution Estimation for Ultrasound Image Simulation
This work addresses the need for realistic ultrasound image simulation for training purposes, representing an incremental improvement over existing methods.
The authors tackled the ill-posed inverse problem of estimating scatterer distributions from ultrasound images for realistic simulation, demonstrating that their convolutional neural network approach synthesizes images that closely match observations under varying acquisition parameters.
Simulation-based ultrasound training can be an essential educational tool. Realistic ultrasound image appearance with typical speckle texture can be modeled as convolution of a point spread function with point scatterers representing tissue microstructure. Such scatterer distribution, however, is in general not known and its estimation for a given tissue type is fundamentally an ill-posed inverse problem. In this paper, we demonstrate a convolutional neural network approach for probabilistic scatterer estimation from observed ultrasound data. We herein propose to impose a known statistical distribution on scatterers and learn the mapping between ultrasound image and distribution parameter map by training a convolutional neural network on synthetic images. In comparison with several existing approaches, we demonstrate in numerical simulations and with in-vivo images that the synthesized images from scatterer representations estimated with our approach closely match the observations with varying acquisition parameters such as compression and rotation of the imaged domain.