DosimeTron: Automating Personalized Monte Carlo Radiation Dosimetry in PET/CT with Agentic AI

2026-04-07

AI Summary

This work addresses the cumbersome and labor-intensive nature of patient-specific internal dosimetry in PET/CT imaging by introducing DosimeTron, the first end-to-end automated system powered by a reasoning agent. Leveraging GPT-5.2 as its inference engine, DosimeTron integrates 23 specialized tools orchestrated through four Model Context Protocol servers to autonomously perform DICOM metadata extraction, image preprocessing, organ segmentation, Monte Carlo simulation, and dose report generation. Evaluated on 597 PSMA-PET/CT studies, the system achieved zero failure runs, demonstrating excellent agreement with OpenDose3D (median Pearson’s r = 0.997; median concordance correlation coefficient = 0.996). For 19 out of 22 organs, the mean absolute percentage error was below 5%, with an average processing time of approximately 32.3 minutes per case.

Abstract

Purpose: To develop and evaluate DosimeTron, an agentic AI system for automated patient-specific MC internal radiation dosimetry in PET/CT examinations. Materials and Methods: In this retrospective study, DosimeTron was evaluated on a publicly available PSMA-PET/CT dataset comprising 597 studies from 378 male patients acquired on three scanner models (18-F, n = 369; 68-Ga, n = 228). The system uses GPT-5.2 as its reasoning engine and 23 tools exposed via four Model Context Protocol servers, automating DICOM metadata extraction, image preprocessing, MC simulation, organ segmentation, and dosimetric reporting through natural-language interaction. Agentic performance was assessed using diverse prompt templates spanning single-turn instructions of varying specificity and multi-turn conversational exchanges, monitored via OpenTelemetry traces. Dosimetric accuracy was validated against OpenDose3D across 114 cases and 22 organs using Pearson's r, Lin's concordance correlation coefficient (CCC), and Bland-Altman analysis. Results: Across all prompt templates and all runs, no execution failures, pipeline errors, or hallucinated outputs were observed. Pearson's r ranged from 0.965 to 1.000 (median 0.997; all p < 0.001) and CCC from 0.963 to 1.000 (median 0.996). Mean absolute percentage difference was below 5% for 19 of 22 organs (median 2.5%). Total per-study processing time (SD) was 32.3 (6.0) minutes. Conclusion: DosimeTron autonomously executed complex dosimetry pipelines across diverse prompt configurations and achieved high dosimetric agreement with OpenDose3D at clinically acceptable processing times, demonstrating the feasibility of agentic AI for patient-specific Monte Carlo dosimetry in PET/CT.

Problem

• personalized dosimetry
• Monte Carlo radiation dosimetry
• PET/CT
• internal radiation dosimetry
• automated dosimetry

Innovation

• agentic AI
• Monte Carlo dosimetry
• patient-specific
• PET/CT
• automated pipeline