End-to-End PET/CT Interpretation and Quantification with an LLM-Orchestrated AI Agent: A Real-World Pilot Study

Although deep learning models have improved individual PET analysis, image processing, and quantification tasks, end-to-end automation from raw DICOM data to quantitative clinical reporting remains limited, particularly in heterogeneous real-world settings. Methods: As a proof-of-concept, an autonomous large language model (LLM)-orchestrated multitool agent for end-to-end PET/CT interpretation was developed. A reasoning-based, text-based LLM selected appropriate series from raw DICOM, coordinated registration and SUV conversion, invoked segmentation and detection tools, generated maximum-intensity projections, called a vision-enabled LLM for interpretation, and synthesized structured draft reports. The system was retrospectively evaluated in 170 patients undergoing baseline [¹⁸F]FDG PET/CT for lung cancer staging, with clinical reports serving as the reference standard. Results: The agent successfully completed the full end-to-end workflow from raw DICOM selection to structured draft report generation without human intervention in all 170 examinations. Primary tumor detection achieved 100% sensitivity. For nodal involvement, sensitivity was 84.8% and specificity was 39.4%, whereas distant metastasis detection showed 70.2% sensitivity and 65.0% specificity. Discrepancy analysis of 58 nodal and 57 metastatic mismatch cases revealed systematic false-positive findings related to reactive or physiologic uptake and false-negative findings involving small-volume or anatomically atypical metastases. Conclusion: LLM-orchestrated PET/CT agents enabled workflow-level automation from raw DICOM to quantification and structured draft reporting under real-world conditions. Although primary tumor detection was highly reliable, nodal and metastatic assessment revealed systematic limitations, supporting a collaborative role with continued expert oversight in complex clinical scenarios.