Hybrid Deep Reinforcement Learning for Radio Tracer Localisation in Robotic-assisted Radioguided Surgery

2025-03-11

AI Summary

In robot-assisted radioguided surgery, conventional radioactive tracer localization relies heavily on surgeon expertise and suffers from poor inter-trial consistency. To address this, we propose an autonomous localization framework integrating Proximal Policy Optimization (PPO)-based deep reinforcement learning (DRL) with adaptive grid scanning. The method jointly models gamma-ray signal dynamics and constructs a task-specific state representation, enabling initial directional estimation and real-time path optimization of a detection probe on the da Vinci Research Kit (dVRK) platform. Compared to manual or rule-based approaches, our framework significantly reduces dependence on operator experience while enhancing navigation robustness and procedural reproducibility. In simulation, the system achieves 95% success rate; on the physical dVRK platform, it attains 80%, with marked improvements in both localization accuracy and navigation efficiency. To our knowledge, this is the first DRL–adaptive scanning co-design paradigm for radioguided surgery, establishing a novel pathway toward intelligent, operator-independent surgical navigation.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Radioguided surgery, such as sentinel lymph node biopsy, relies on the precise localization of radioactive targets by non-imaging gamma/beta detectors. Manual radioactive target detection based on visual display or audible indication of gamma level is highly dependent on the ability of the surgeon to track and interpret the spatial information. This paper presents a learning-based method to realize the autonomous radiotracer detection in robot-assisted surgeries by navigating the probe to the radioactive target. We proposed novel hybrid approach that combines deep reinforcement learning (DRL) with adaptive robotic scanning. The adaptive grid-based scanning could provide initial direction estimation while the DRL-based agent could efficiently navigate to the target utilising historical data. Simulation experiments demonstrate a 95% success rate, and improved efficiency and robustness compared to conventional techniques. Real-world evaluation on the da Vinci Research Kit (dVRK) further confirms the feasibility of the approach, achieving an 80% success rate in radiotracer detection. This method has the potential to enhance consistency, reduce operator dependency, and improve procedural accuracy in radioguided surgeries.

Problem

• Autonomous radiotracer detection in robotic-assisted surgeries.
• Combines deep reinforcement learning with adaptive robotic scanning.
• Improves efficiency and robustness in radioguided surgeries.

Innovation

• Hybrid deep reinforcement learning for autonomous navigation
• Adaptive grid-based scanning for initial direction estimation
• Integration with da Vinci Research Kit for real-world validation