Enhancing Surgical Robots with Embodied Intelligence for Autonomous Ultrasound Scanning

TL;DR

This paper introduces an embodied intelligence system for ultrasound robots that combines large language models with domain knowledge, enabling autonomous, efficient, and high-quality ultrasound scanning based on verbal commands.

Contribution

The paper presents a novel system integrating LLMs with ultrasound domain knowledge and a dynamic planning strategy, advancing autonomous ultrasound scanning capabilities.

Findings

Significantly improved scan efficiency and quality.

Effective verbal command-based control of ultrasound robots.

Enhanced adaptability during scanning procedures.

Abstract

Ultrasound robots are increasingly used in medical diagnostics and early disease screening. However, current ultrasound robots lack the intelligence to understand human intentions and instructions, hindering autonomous ultrasound scanning. To solve this problem, we propose a novel Ultrasound Embodied Intelligence system that equips ultrasound robots with the large language model (LLM) and domain knowledge, thereby improving the efficiency of ultrasound robots. Specifically, we first design an ultrasound operation knowledge database to add expertise in ultrasound scanning to the LLM, enabling the LLM to perform precise motion planning. Furthermore, we devise a dynamic ultrasound scanning strategy based on a \textit{think-observe-execute} prompt engineering, allowing LLMs to dynamically adjust motion planning strategies during the scanning procedures. Extensive experiments demonstrate that our system significantly improves ultrasound scan efficiency and quality from verbal commands. This advancement in autonomous medical scanning technology contributes to non-invasive diagnostics and streamlined medical workflows.