Agentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform forHigh Dose Rate (HDR) Brachytherapy

2026-08-08

AI Summary

Traditional high-dose-rate (HDR) vaginal cylinder brachytherapy training is constrained by limitations in anatomical fidelity, radiation safety protocols, and clinical resource availability, making it difficult to provide a repeatable, immersive hands-on environment. This work proposes the first seamless integration of a knowledge-aware retrieval-augmented generation (RAG) AI agent into a virtual reality (VR) training system, creating a high-fidelity, risk-free platform powered by Meta Quest 3 and local GPU acceleration. The system enables hands-free natural language interaction and real-time procedural guidance. Preliminary evaluation of the prototype demonstrates strong performance in end-to-end latency, contextual accuracy, and response relevance, confirming the feasibility of this architecture in meeting clinical education demands for both high-quality responsiveness and immersive user experience.

Abstract

The convergence of the Metaverse and Large Language Model (LLM)-based AI agent is catalyzing a shift toward autonomous, immersive, and personalized pedagogical frameworks in medical education. This paper presents a novel agentic AI-driven immersive simulation specifically designed for High Dose Rate (HDR) vaginal cylinder (VC) brachytherapy in cancer care. By integrating Virtual Reality (VR) and mobile computing, the system establishes a high-fidelity, risk-free environment that allows trainees to master complex procedural skills without the facility or safety constraints posed by physical anatomy or live radioactive sources. A core contribution of this work is the seamless integration of a knowledge-aware assistant leveraging Retrieval-Augmented Generation (RAG) to ground agent interactions in authoritative clinical guidelines. This architecture also enables an interactive agent to provide natural language interfaces and hands-free, real-time guidance during intricate medical maneuvers. We validate the proposed system through a prototype deployment comprising a Meta Quest 3 interface linked to a local GPU-accelerated AI backend, demonstrating a feasible architecture for HDR brachytherapy simulation. Experimental results indicate that the system maintains suitable end-to-end latency and high context precision, answer completeness, and relevance in the RAG-enhanced pedagogical support.

Problem

• HDR brachytherapy
• immersive simulation
• medical education
• virtual training
• procedural skills

Innovation

• Agentic AI
• Immersive Simulation
• Retrieval-Augmented Generation (RAG)
• High Dose Rate Brachytherapy
• Knowledge-Aware Assistant