RUSOpt: Robotic UltraSound Probe Normalization with Bayesian Optimization for In-Plane and Out-Plane Scanning

The one of the significant challenges faced by autonomous robotic ultrasound systems is acquiring high-quality images across different patients. The proper orientation of the robotized probe plays a crucial role in governing the quality of ultrasound images. To address this challenge, we propose a sample-efficient method to automatically adjust the orientation of the ultrasound probe normal to the point of contact on the scanning surface, thereby improving the acoustic coupling of the probe and resulting image quality. Our method utilizes Bayesian Optimization (BO) based search on the scanning surface to efficiently search for the normalized probe orientation. We formulate a novel objective function for BO that leverages the contact force measurements and underlying mechanics to identify the normal. We further incorporate a regularization scheme in BO to handle the noisy objective function. The performance of the proposed strategy has been assessed through experiments on urinary bladder phantoms. These phantoms included planar, tilted, and rough surfaces, and were examined using both linear and convex probes with varying search space limits. Further, simulation-based studies have been carried out using 3D human mesh models. The results demonstrate that the mean ($\pm$ SD) absolute angular error averaged over all phantoms and 3D models is $2.4\pm 0.7^{\circ}$ and $2.1\pm 1.3^{\circ}$, respectively.

I. Introduction

Ultrasound imaging, also known as sonography, is a widely used medical imaging technique that can provide valuable information about the structure and function of organs and tissues. It is used in a wide range of diagnostic and therapeutic procedures [1]. Ultrasound imaging has several advantages over other imaging techniques such as X-rays or CT scans. For example, it does not use ionizing radiation, making it safer for patients and clinicians. It is also non-invasive and relatively inexpensive compared to other imaging techniques. While ultrasound imaging is a valuable tool in modern medicine, there are also some drawbacks to this technique. The quality of the ultrasound images obtained is highly dependent on the skill and experience of the operator [2]. This dependence on the operator's skill and expertise can lead to variability in image quality, which can affect the accuracy of the diagnosis. Additionally, access to expert sonographers is limited in rural areas, leading to long wait times for patients needing ultrasound imaging. Patients who need these services may have to travel to urban areas, which can result in increased travel costs and time [3], [4]. Fig. 1:

The two rotations carried out to acquire urinary bladder ultrasound images. (a) describe the ideal probe orien-tation normal to the point of contact on phantom; (b) and (c) describe the non-ideal probe orientation during out-plane an in-plane rotation of probe. The ultrasound images acquired in these cases result in artifacts like edge or structure shadowing due to inappropriate acoustic coupling.