B. Anila Satheesh

Bio: B. Anila Satheesh is an academic researcher from Indian Institute of Technology Madras. The author has contributed to research in topics: Ray tracing (graphics) & Region of interest. The author has an hindex of 1, co-authored 2 publications receiving 2 citations.

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

Abstract: Introduction and problem statement Ultrasound imaging is one of the most preferred modalities for image-guided procedures owing to its low-cost, non-ionizing nature, and real-time capability. However, its interpretation is complex, and hence considerable research has gone into developing methods that can help improve the interpretation of ultrasound images. One such solution is to use ultrasound simulation tools that can generate patient-specific ultrasound images from image data obtained from other modalities during pre-planning stage. Use of such tools can aid the user to have enough practice before the actual image-guided procedure. In this regard, ultrasound simulation from CT data has gained much interest over the past few years. Methodology One of the most recent ways of simulating ultrasound images from CT is to combine the ultrasound echo reflection image, the transmission intensity map, and the scatter image of the region of interest from the CT image. However, the scatter image is simulated using Field II program, which is computationally very intensive. In this paper, we propose combining the traditional convolution method for scatter map generation along with ray tracing approaches to simulate an ultrasound image. The methodology is tested on CT data from Visible Human Project (VHP) in simulations and validated on multi-modality tissue-mimicking phantom in vitro. Simulation is done for a curvilinear array transducer at 2.5 MHz frequency and an imaging depth of 180 mm. Results and conclusion The results obtained from simulation suggests that using convolution method reduces the computation time significantly, from almost 2.4 h to about 17 s for a chosen region of interest in VHP data of dimensions 180 mm x 60 mm x 1 mm without affecting the image quality. In case of in-vitro phantom, the computation time is reduced from almost 3 h to about 10 s for a chosen region of interest of dimensions 180 mm x 60 mm x 1.25 mm. Thus, convolution method may be preferred over Field II for generating ultrasound scatter image since the method provides a comparable image to that of real-time images, but takes only significantly less computation time.

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

Abstract: 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.

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

Abstract: 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 Ultrasound Simulator Using Monte-Carlo Path Tracing in Conjunction with Optix Engine

Abstract: 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.