Cardiac ultrasound simulation for autonomous ultrasound navigation

TL;DR

The paper presents a GPU-accelerated ultrasound simulation pipeline that converts segmentation maps from CT/MRI into fast, patient-specific US images using NanoVDB volumes, OptiX ray tracing, and Monte Carlo path tracing. It validates the approach with phantom experiments showing accurate geometry, contrast, and speckle statistics, and demonstrates its utility by pre-training a transthoracic echocardiography view classifier on synthetic data to reduce the amount of real data required. The method enables large-scale synthetic data generation (over 10k images per hour) across thousands of CT datasets, facilitating robust learning for navigation tasks in ultrasound. Limitations include the absence of non-linear propagation and tissue heterogeneity in current segmentation-based models; future work points to integrating generative models, motion/deformation modeling, and extending to other modalities such as TEE/ICE to broaden applicability.

Abstract

Ultrasound is well-established as an imaging modality for diagnostic and interventional purposes. However, the image quality varies with operator skills as acquiring and interpreting ultrasound images requires extensive training due to the imaging artefacts, the range of acquisition parameters and the variability of patient anatomies. Automating the image acquisition task could improve acquisition reproducibility and quality but training such an algorithm requires large amounts of navigation data, not saved in routine examinations. Thus, we propose a method to generate large amounts of ultrasound images from other modalities and from arbitrary positions, such that this pipeline can later be used by learning algorithms for navigation. We present a novel simulation pipeline which uses segmentations from other modalities, an optimized volumetric data representation and GPU-accelerated Monte Carlo path tracing to generate view-dependent and patient-specific ultrasound images. We extensively validate the correctness of our pipeline with a phantom experiment, where structures' sizes, contrast and speckle noise properties are assessed. Furthermore, we demonstrate its usability to train neural networks for navigation in an echocardiography view classification experiment by generating synthetic images from more than 1000 patients. Networks pre-trained with our simulations achieve significantly superior performance in settings where large real datasets are not available, especially for under-represented classes. The proposed approach allows for fast and accurate patient-specific ultrasound image generation, and its usability for training networks for navigation-related tasks is demonstrated.

Figures (4)

• Figure 1: Simulation Pipeline. Using input segmentations from other modalities, transducer and tissue acoustic properties (a), we convert the segmentation to a NanoVDB volume (b.1) for ray tracing on the GPU. (b.2) shows a volume rendering of the ray tracing scene with various organs and the transducer's fan geometry. We model the sound waves as rays and perform ray tracing to simulate their propagation (c.1). We then generate a scattering volume (c.2) and compute the RF lines (c.3). Time-gain compensation and scan conversion are performed to yield the final simulation (d). A real ultrasound is shown for qualitative comparison (e).
• Figure 2: Overview of the pre-processing pipeline. A segmentation volume containing $N$ labels (one for each organ) is converted to a NanoVDB volume (iii) for use on the GPU. On the one hand, $S$ is directly converted to a grid containing all the labels (iii-1). On the other hand, for each label, an OpenVDB grid (i) containing only voxels belonging to the given label is created. In (ii), the SDF w.r.t the organ boundary is computed and used later during traversal to obtain surface normals (v). The final NanoVDB volume contains for each label, the corresponding voxel (iii-2) and SDF (iii-3) grids. Pointers to each grid are stored in the Shader Binding Table for access on the GPU (iv).
• Figure 5: Real (left column) and simulated (right column) Apical 5, 4, 3 chambers views (top to bottom, not paired). The orange box denotes papillary muscles and fine cardiac structures which are not captured by the simulations, making the ventricles' borders sharper in the synthetic images.
• Figure 8: Rayleigh distribution fit. The histogram shown is from a random run out of 10. We obtain a mean sum-of-squared Errors of $1.89e^{-5}$ w.r.t the fitted Rayleigh distribution and a SNR of $1.89 \pm 0.01$, which is in the ranges reported in the literature gao2009gao2012salehi2015