PlanningCopilot: An agentic framework integrating ESAPI modules for autonomous treatment planning in lung radiotherapy.
TL;DR
PlanCopilot consistently satisfies clinical dosimetric requirements across varying anatomical complexities and improves optimization efficiency through self-learning from prior optimization history.
Abstract
Background
Consistently generating clinically acceptable plans without human intervention remains a challenge in radiotherapy. Rule-based automation provides deterministic execution, and knowledge-based planning (KBP) provides statistical dose estimation, but both often require manual refinement. Large language models (LLMs) offer clinical reasoning capability, but effective autonomous planning also requires a mechanism to execute complex planning actions within the treatment planning system (TPS).
Purpose
To develop and evaluate PlanningCopilot, an agentic system that utilizes the reasoning capability of LLM and a validated Eclipse Scripting API (ESAPI) optimization module integrating KBP initialization ("PlanAct") to autonomously generate treatment plans. This study evaluates the system's ability to produce clinically acceptable plans for locally advanced non-small cell lung cancer (LA-NSCLC) and assesses its potential to refine performance by self-learning.
Methods
PlanningCopilot was implemented as a multi-agent framework linked to the TPS through PlanAct API. It comprises four specialized GPT-4.1 agents that iteratively interact with the TPS: (1) an Evaluator agent that accesses the plan and generates plan quality reports, (2) a Supervisor agent that validates these reports before passing them to a Planner agent, (3) the Planner agent that executes initialization and optimization tasks through PlanAct API and planning guidelines, and (4) an optional Learner agent that synthesizes optimization history into Planner-facing prompt addendums. We retrospectively analyzed 62 patients with conventionally fractionated LA-NSCLC and compared original clinical plans with autonomous plans with and without the Learner agent. Measurement-based patient-specific quality assurance (PSQA) was performed on the first 21 autonomous IMRT plans in planning order.
Results
All autonomous plans met clinical dosimetric requirements, including those not achieved in the clinical plans and KBP (RapidPlan) plans. Paired Wilcoxon signed-rank tests showed no significant differences between autonomous and clinical plans for Lungs Dmean (p = 0.371), Lungs V20Gy (p = 0.449), Lungs V5Gy (p = 0.309), Heart D50% (p = 0.175), Esophagus Dmean (p = 0.750), Spinal Cord D0.03cc (p = 0.422), and Plan D0.03cc (p = 0.941). Furthermore, autonomous plans achieved significantly lower Esophagus D0.03cc (p = 0.027). Compared with RapidPlan initialization, PlanningCopilot improved multiple dosimetric endpoints, including Lungs Dmean (p < 0.001), Lungs V20Gy (p < 0.001), Lungs V5Gy (p = 0.004), Heart D50% (p = 0.037), and Plan D0.03cc (p < 0.001), with the cost of higher Esophagus Dmean (p < 0.001) and Esophagus D0.03cc (p < 0.001). In a subset of 18 cases requiring at least two iterations, applying Learner-derived knowledge reduced required iterations by an average of 11.8% while maintaining comparable plan quality (p > 0.05). All 21 autonomous IMRT plans passed measurement-based PSQA.
Conclusion
PlanningCopilot enables autonomous generation of clinically acceptable and deliverable treatment plans for LA-NSCLC. It consistently satisfies clinical dosimetric requirements across varying anatomical complexities and improves optimization efficiency through self-learning from prior optimization history.
