Deep Kernel and Image Quality Estimators for Optimizing Robotic Ultrasound Controller using Bayesian Optimization

Ultrasound is a commonly used medical imaging modality that requires expert sonographers to manually maneuver the ultrasound probe based on the acquired image. Autonomous Robotic Ultrasound (A-RUS) is an appealing alternative to this manual procedure in order to reduce sonographers' workload. The key challenge to A-RUS is optimizing the ultrasound image quality for the region of interest across different patients. This requires knowledge of anatomy, recognition of error sources and precise probe position, orientation and pressure. Sample efficiency is important while optimizing these parameters associated with the robotized probe controller. Bayesian Optimization (BO), a sample-efficient optimization framework, has recently been applied to optimize the 2D motion of the probe. Nevertheless, further improvements are needed to improve the sample efficiency for high-dimensional control of the probe. We aim to overcome this problem by using a neural network to learn a low-dimensional kernel in BO, termed as Deep Kernel (DK). The neural network of DK is trained using probe and image data acquired during the procedure. The two image quality estimators are proposed that use a deep convolution neural network and provide real-time feedback to the BO. We validated our framework using these two feedback functions on three urinary bladder phantoms. We obtained over 50% increase in sample efficiency for 6D control of the robotized probe. Furthermore, our results indicate that this performance enhancement in BO is independent of the specific training dataset, demonstrating inter-patient adaptability.

I. Introduction

Ultrasound imaging delivers instantaneous, non-invasive access to the human body to effectively visualize anatomy and pathology [1]. Ultrasound stands out among other imaging modalities, such as MRI or CT scan, because it is low-cost, non-radiating, and suitable for use in rural or underserved communities. However, unlike other modalities, ultrasound is not a plug-and-play technology. Acquiring quality images relies heavily on the expertise of the trained sonographer who ensures optimal ultrasound probe contact location, pressure, angle, and gel condition between the probe and skin [2]. In addition, the sonographer must integrate the visual feedback from the image with a mental model of anatomical structure(s) to continuously improve the probing process.