Fukui Yusuke, Baba Shogo, Ohashi Kohei, Nagatani Yukihiro, Kobashi Kazumasa, Watanabe Yoshiyuki, Iguchi Harumi
Department of Radiology, Shiga University of Medical Science Hospital, Otsu, Japan.
Information Technology Center, Seinan Gakuin University, Fukuoka, Japan.
Ann Nucl Med. 2025 Sep;39(9):982-993. doi: 10.1007/s12149-025-02063-2. Epub 2025 Jun 16.
Owing to the revision of the Medical Care Act in 2020, managing and recording radiation doses in PET-CT examinations have become mandatory. In this study, we investigated unsupervised anomaly detection methods as a potential solution to minimize input errors in dose recordings.
We analyzed data extracted from our database, including patient body weight, positron emission tomography (PET) dose, and dose length product (DLP). Several anomaly detection models, such as one-class support vector machine (OCSVM), Hotelling's T2 method, multivariate statistical process control (MSPC), isolation forest, and local outlier factor (LOF), were applied and compared. The dataset included 3509 entries for model training and 499 entries for evaluation. Anomalies that could be potential input errors were evaluated using metrics, such as precision, recall, F1 score, receiver operating characteristics-area under the curve (ROC-AUC), and precision-recall-AUC (PR-AUC).
We demonstrated that Hotelling's T2 method and MSPC's T statistic outperformed other models, achieving a recall of 1.0 and AUCs of 1.0, effectively detecting input errors in radiation dose records. Furthermore, our findings suggest that unsupervised anomaly detection can not only identify input errors but also detect excessively high or low radiation doses, contributing to improved dose management in PET-CT examinations.
These findings suggest that unsupervised anomaly detection is a promising approach to improve the accuracy of dose management in PET-CT examinations, enhancing patient safety and compliance with regulatory standards.
由于2020年《医疗保健法》的修订，在PET-CT检查中管理和记录辐射剂量已成为强制性要求。在本研究中，我们研究了无监督异常检测方法，作为尽量减少剂量记录中输入错误的潜在解决方案。
我们分析了从数据库中提取的数据，包括患者体重、正电子发射断层扫描（PET）剂量和剂量长度乘积（DLP）。应用并比较了几种异常检测模型，如一类支持向量机（OCSVM）、霍特林T2方法、多元统计过程控制（MSPC）、孤立森林和局部离群因子（LOF）。数据集包括3509条用于模型训练的记录和499条用于评估的记录。使用精度、召回率、F1分数、受试者工作特征-曲线下面积（ROC-AUC）和精确召回率-AUC（PR-AUC）等指标评估可能是潜在输入错误的异常情况。
我们证明，霍特林T2方法和MSPC的T统计量优于其他模型，召回率达到1.0，AUC为1.0，有效地检测了辐射剂量记录中的输入错误。此外，我们的研究结果表明，无监督异常检测不仅可以识别输入错误，还可以检测过高或过低的辐射剂量，有助于改善PET-CT检查中的剂量管理。
这些研究结果表明，无监督异常检测是一种有前景的方法，可以提高PET-CT检查中剂量管理的准确性，增强患者安全性并符合监管标准。
