RAG-RUSS: A Retrieval-Augmented Robotic Ultrasound for Autonomous Carotid Examination

TL;DR

The paper introduces RAG-RUSS, an interpretable, retrieval-augmented robotic ultrasound system that autonomously performs carotid examinations while explaining its actions, addressing safety and generalization issues in medical robotics.

Contribution

It presents a novel, interpretable framework combining retrieval-augmented generation with robotic ultrasound for autonomous carotid exams, improving safety and transparency.

Findings

Successfully explained current scanning stages

Autonomously planned probe motions for carotid exams

Generalized to unseen volunteer data

Abstract

Robotic ultrasound (US) has recently attracted increasing attention as a means to overcome the limitations of conventional US examinations, such as the strong operator dependence. However, the decision-making process of existing methods is often either rule-based or relies on end-to-end learning models that operate as black boxes. This has been seen as a main limit for clinical acceptance and raises safety concerns for widespread adoption in routine practice. To tackle this challenge, we introduce the RAG-RUSS, an interpretable framework capable of performing a full carotid examination in accordance with the clinical workflow while explicitly explaining both the current stage and the next planned action. Furthermore, given the scarcity of medical data, we incorporate retrieval-augmented generation to enhance generalization and reduce dependence on large-scale training datasets. The method was trained on data acquired from 28 volunteers, while an additional four volumetric scans recorded from previously unseen volunteers were reserved for testing. The results demonstrate that the method can explain the current scanning stage and autonomously plan probe motions to complete the carotid examination, encompassing both transverse and longitudinal planes.