Automated stereotactic radiosurgery planning using a human-in-the-loop reasoning large language model agent

TL;DR

This study introduces SAGE, an LLM-based automated planning agent for stereotactic radiosurgery that uses chain-of-thought reasoning to produce plans comparable to human experts while enhancing transparency and safety.

Contribution

The paper presents SAGE, a novel LLM-based planning system that incorporates reasoning for improved transparency and clinical safety in automated SRS treatment planning.

Findings

Reasoning model achieved comparable dosimetry to human plans.

Reasoning model reduced cochlear dose below human baseline.

Deliberative behaviors like constraint verification were systematically demonstrated.

Abstract

Stereotactic radiosurgery (SRS) demands precise dose shaping around critical structures, yet black-box AI systems have limited clinical adoption due to opacity concerns. We tested whether chain-of-thought reasoning improves agentic planning in a retrospective cohort of 41 patients with brain metastases treated with 18 Gy single-fraction SRS. We developed SAGE (Secure Agent for Generative Dose Expertise), an LLM-based planning agent for automated SRS treatment planning. Two variants generated plans for each case: one using a non-reasoning model, one using a reasoning model. The reasoning variant showed comparable plan dosimetry relative to human planners on primary endpoints (PTV coverage, maximum dose, conformity index, gradient index; all p > 0.21) while reducing cochlear dose below human baselines (p = 0.022). When prompted to improve conformity, the reasoning model demonstrated systematic planning behaviors including prospective constraint verification (457 instances) and trade-off deliberation (609 instances), while the standard model exhibited none of these deliberative processes (0 and 7 instances, respectively). Content analysis revealed that constraint verification and causal explanation concentrated in the reasoning agent. The optimization traces serve as auditable logs, offering a path toward transparent automated planning.