Ślusarz Krystian, Buchwald Mikolaj, Szczeszek Adrian, Kupinski Szymon, Gramek-Jedwabna Anna, Andrzejewski Wojciech, Pukacki Juliusz, Pękal Robert, Ruchała Marek, Czepczyński Rafał, Mazurek Cezary
Department of Nuclear Medicine, Affidea, Poznan, Poland.
Poznan Supercomputing and Networking Center, Polish Academy of Science, Poznan, Poland.
EJNMMI Res. 2025 Apr 11;15(1):39. doi: 10.1186/s13550-025-01228-4.
The number of thyroid cancer diagnoses has been increasing for several decades, with a significant part of cases being detected incidentally (thyroid incidentaloma, TI) by imaging studies performed for reasons other than thyroid disease, including PET/CT with [F]FDG. The chacteristics of the detected TI cannot be determined solely on the basis of conventional parameters used in everyday clinical practice, such as SUV. In recent years, there has been a growing interest in radiomics, which is a quantitative method of analyzing radiological images based on the analysis of image texture. Textural analysis may be helpful, as it allows to characterize features invisible to the physician with the naked eye.
Of the 54 patients who presented focal [F]FDG-avid TI and had subsequent fine needle aspiration biopsy, 4 patients were excluded from the analysis due to the unavailability of the final diagnostic information. Hence, in the final analysis, data from 50 patients were used (39 females and 11 males) with a mean age of 58.5 ± 11.26. Of these 50 patients, 11 (22.0%) [F]FDG-avid nodules were diagnosed as malignant. The performance of the XGBoost model in assessing [F]FDG-avid TI was similar (0.846 [confidence interval, CI, 95% 0.737-0.956]) to SUV (0.797 [CI 95%: 0.622-0.973]; p = 0.60).
With an AI-based algorithm using radiomics features it is possible to detect the malignancy of thyroid nodule. However, no statistically significant differences were observed between the AI and radiomics approach, and when using a conventional measure, i.e., SUV.
几十年来，甲状腺癌的诊断数量一直在增加，其中很大一部分病例是在因甲状腺疾病以外的原因进行的影像学检查中偶然发现的（甲状腺偶发瘤，TI），包括使用[F]FDG的PET/CT。仅根据日常临床实践中使用的传统参数（如SUV）无法确定检测到的TI的特征。近年来，人们对放射组学的兴趣日益浓厚，放射组学是一种基于图像纹理分析的放射学图像定量分析方法。纹理分析可能会有所帮助，因为它可以对医生肉眼不可见的特征进行表征。
在54例出现局灶性[F]FDG摄取的TI并随后进行细针穿刺活检的患者中，4例因无法获得最终诊断信息而被排除在分析之外。因此，在最终分析中，使用了50例患者的数据（39名女性和11名男性），平均年龄为58.5±11.26岁。在这50例患者中，11个（22.0%）[F]FDG摄取结节被诊断为恶性。XGBoost模型在评估[F]FDG摄取的TI方面的表现（0.846[置信区间，CI，95% 0.737 - 0.956]）与SUV（0.797[CI 95%：0.622 - 0.973]；p = 0.60）相似。
使用基于人工智能的算法并结合放射组学特征可以检测甲状腺结节的恶性程度。然而，在人工智能和放射组学方法之间以及与使用传统指标即SUV之间均未观察到统计学上的显著差异。
