This paper presents an artificial intelligence-based ultrasound simulator suitable for medical simulation and clinical training. Particularly, we propose a machine learning approach to realistically simulate ultrasound images based on generative adversarial networks (GANs). Using B-mode ultrasound images simulated by a known ultrasound simulator, Field II, an "image-to-image" ultrasound simulator was trained. Then, through evaluations, we found that the GAN-based simulator can generate B-mode images following Rayleigh scattering. Our preliminary study demonstrated that ultrasound B-mode images from anatomies inferred from magnetic resonance imaging (MRI) data were feasible. While some image blurring was observed, ultrasound B- mode images obtained were both visually and quantitatively comparable to those obtained using the Field II simulator. It is also important to note that the GAN-based ultrasound simulator was computationally efficient and could achieve a frame rate of 15 frames/second using a regular laptop computer. In the future, the proposed GAN-based simulator will be used to synthesize more realistic looking ultrasound images with artifacts such as shadowing.

A Real-Time Medical Ultrasound Simulator Based on a Generative Adversarial Network Model

Monte-Carlo ray tracing, which enables realistic simulation of ultrasound-tissue interactions such as soft shadows and fuzzy reflections, has been used to simulate ultrasound images. The main technical challenge presented with Monte-Carlo ray tracing is its computational efficiency. In this study, we investigated the use of a commercially-available ray-tracing engine (NVIDIA’s Optix 6.0), which provides a simple, recursive, and flexible pipeline for accelerating ray tracing algorithms. Our preliminary results show that our ultrasound simulation algorithm accelerated by the Optix engine can achieve a frame of 25 frames/second using an Nvidia RTX 2060 card. Furthermore, we compare ultrasound simulations built on the proposed Monte-Carlo ray-tracing algorithm with a deep-learning generative adversarial network (GANs)-based ultrasound simulator and a physics-based ultrasound simulator (Field II). The proposed ultrasound simulator was able to better visualize small-sized structures while the other two above-mentioned simulators could not. Our future work includes integration of our proposed simulator with a virtual reality platform and expansion to other ultrasound modalities such as elastography and flow imaging.

A Real-time Ultrasound Simulator Using Monte-Carlo Path Tracing in Conjunction with Optix Engine

Ultrasound Image Generation and Modality Conversion Based on Deep Learning

A fast method for simulating ultrasound image from patient-specific CT data

Ultrasound imaging is one of the most preferred modalities for image-guided procedures due to its low-cost, non-ionizing nature, and real-time capability. However, if patient-specific ultrasound images can be simulated before the actual procedure, it may aid in better implementation of the procedure planned using pre-planning image data. For this reason, ultrasound simulations from CT data have gained much interest over the past few years. Recent approaches combine ultrasound echo reflection image, intensity transmission map, and scatter image of the region of interest to form the final ultrasound image. However, the scatter image is simulated from Field II, which is computationally very intensive. In this paper, we propose combining the traditional convolution model for scatter map simulation with ray tracing approaches to simulate an ultrasound image. The obtained results suggest that using convolution model instead of Field II reduces significantly the computational time without affecting the image quality.

B. Anila Satheesh

Papers

A fast method for simulating ultrasound image from patient-specific CT data

A method of ultrasound simulation from patient-specific CT image data: A preliminary simulation study