arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.06280physics.med-phcs.AI
收藏

DosimeTron：利用代理AI自动化PET/CT中的个性化蒙特卡洛辐射剂量学

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

Division of Radiology, Department for Clinical Science, Intervention and Technology (CLINTEC), Karolinska Institutet（卡罗林斯卡学院临床科学、干预与技术系放射学部门）；Artificial Intelligence and Translational Imaging (ATI) Lab, Department of Radiology, School of Medicine, University of Crete（克里特大学医学院放射学系人工智能与转化影像实验室）；Department of Nuclear Medicine and Medical Physics, Section Nuclear Medicine Huddinge, Karolinska University Hospital（卡罗林斯卡大学医院核医学与医学物理系胡丁厄核医学部门）；Department of Nuclear Medicine and Medical Physics, Theranostics Trial Center, Karolinska University Hospital（卡罗林斯卡大学医院核医学与医学物理系治疗诊断试验中心）；Computational Biomedicine Laboratory, Institute of Computer Science Foundation for Research and Technology Hellas (ICS - FORTH)（研究与技术基金会计算机科学研究所计算生物医学实验室）

Eleftherios Tzanis, Michail E. Klontzas, Antonios Tzortzakakis

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出DosimeTron，一种基于代理AI的系统，用于自动化PET/CT检查中的患者特定蒙特卡洛内部辐射剂量学，通过自然语言交互实现DICOM元数据提取、图像预处理、MC模拟、器官分割和剂量报告，验证了其在114例病例和22个器官上的高精度与临床可行性。

摘要：

目的：开发并评估DosimeTron，一种用于PET/CT检查中自动化患者特定蒙特卡洛内部辐射剂量学的代理AI系统。材料和方法：在回顾性研究中，DosimeTron在公开可用的PSMA-PET/CT数据集上进行评估，该数据集包含来自378名男性患者、3种扫描仪型号（18-F，n=369；68-Ga，n=228）的597例研究。系统使用GPT-5.2作为推理引擎，并通过四个Model Context Protocol服务器暴露23个工具，通过自然语言交互实现DICOM元数据提取、图像预处理、MC模拟、器官分割和剂量报告。代理性能通过涵盖单轮指令和多轮对话交换的多种提示模板评估，通过OpenTelemetry追踪监控。剂量学准确性通过Pearson's r、Lin's一致性相关系数（CCC）和Bland-Altman分析在114例病例和22个器官上验证。结果：在所有提示模板和所有运行中，未观察到执行失败、管道错误或幻觉输出。Pearson's r范围从0.965到1.000（中位数0.997；所有p < 0.001），CCC范围从0.963到1.000（中位数0.996）。19个器官的平均绝对百分比差异低于5%（中位数2.5%）。总单例处理时间（SD）为32.3（6.0）分钟。结论：DosimeTron能够自主执行复杂剂量学管道，跨多样提示配置实现了与OpenDose3D的高剂量学一致性，在可接受的处理时间内证明了代理AI在PET/CT中患者特定蒙特卡洛剂量学的可行性。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑