Reproduce “RAG-RUSS: A Retrieval-Augmented Robotic Ultrasound for Autonomous Carotid Examination” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Dianye Huang, Ziping Cong, Nassir Navab, Zhongliang Jiang
The system guides carotid ultrasound scanning by retrieving annotated examples and using current and previous images to identify the scan stage, explain an anatomical cue, and propose the next probe instruction. In simulation on four unseen prerecorded volunteer scans, its two-example version averaged 79.1% across six stage categories, versus 71.7% for the VLM-only baseline, but scored 25.0% on “Return completed.”
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.