Freehand Ultrasound Image Simulation with Spatially-Conditioned Generative Adversarial Networks

TL;DR

This paper introduces a novel spatially-conditioned GAN architecture for realistic ultrasound image simulation at specific 3D locations, enhancing medical training and image registration applications.

Contribution

The paper presents a new neural network architecture that conditionally generates anatomically accurate ultrasound images based on spatial probe position, improving simulation fidelity.

Findings

Generated images are anatomically accurate and realistic.

Quantitative landmark distance metrics show high fidelity.

Usability study indicates distinguishability from real images is low.

Abstract

Sonography synthesis has a wide range of applications, including medical procedure simulation, clinical training and multimodality image registration. In this paper, we propose a machine learning approach to simulate ultrasound images at given 3D spatial locations (relative to the patient anatomy), based on conditional generative adversarial networks (GANs). In particular, we introduce a novel neural network architecture that can sample anatomically accurate images conditionally on spatial position of the (real or mock) freehand ultrasound probe. To ensure an effective and efficient spatial information assimilation, the proposed spatially-conditioned GANs take calibrated pixel coordinates in global physical space as conditioning input, and utilise residual network units and shortcuts of conditioning data in the GANs' discriminator and generator, respectively. Using optically tracked B-mode ultrasound images, acquired by an experienced sonographer on a fetus phantom, we demonstrate the feasibility of the proposed method by two sets of quantitative results: distances were calculated between corresponding anatomical landmarks identified in the held-out ultrasound images and the simulated data at the same locations unseen to the networks; a usability study was carried out to distinguish the simulated data from the real images. In summary, we present what we believe are state-of-the-art visually realistic ultrasound images, simulated by the proposed GAN architecture that is stable to train and capable of generating plausibly diverse image samples.