Dondi Francesco, Pasinetti Nadia, Gatta Roberto, Albano Domenico, Giubbini Raffaele, Bertagna Francesco
Nuclear Medicine, Università degli Studi di Brescia and ASST Spedali Civili Brescia, 25123 Brescia, Italy.
Radiation Oncology Department, ASST Valcamonica Esine and Università degli Studi di Brescia, 25040 Brescia, Italy.
J Clin Med. 2022 Jan 26;11(3):615. doi: 10.3390/jcm11030615.
The aim of this study was to compare two different tomographs for the evaluation of the role of semiquantitative PET/CT parameters and radiomics features (RF) in the prediction of thyroid incidentalomas (TIs) at F-FDG imaging. A total of 221 patients with the presence of TIs were retrospectively included. After volumetric segmentation of each TI, semiquantitative parameters and RF were extracted. All of the features were tested for significant differences between the two PET scanners. The performances of all of the features in predicting the nature of TIs were analyzed by testing three classes of final logistic regression predictive models, one for each tomograph and one with both scanners together. Some RF resulted significantly different between the two scanners. PET/CT semiquantitative parameters were not able to predict the final diagnosis of TIs while GLCM-related RF (in particular GLCM entropy_log2 e GLCM entropy_log10) together with some GLRLM-related and GLZLM-related features presented the best predictive performances. In particular, GLCM entropy_log2, GLCM entropy_log10, GLZLM SZHGE, GLRLM HGRE and GLRLM HGZE resulted the RF with best performances. Our study enabled the selection of some RF able to predict the final nature of TIs discovered at F-FDG PET/CT imaging. Classic semiquantitative and volumetric PET/CT parameters did not reveal these abilities. Furthermore, a good overlap in the extraction of RF between the two scanners was underlined.
本研究的目的是比较两种不同的断层扫描仪，以评估半定量PET/CT参数和放射组学特征（RF）在F-FDG成像中预测甲状腺偶发瘤（TI）的作用。共回顾性纳入了221例存在TI的患者。对每个TI进行体积分割后，提取半定量参数和RF。对所有特征进行测试，以检验两台PET扫描仪之间是否存在显著差异。通过测试三类最终逻辑回归预测模型，分析了所有特征在预测TI性质方面的性能，每个断层扫描仪各一个模型，还有一个模型是将两台扫描仪的数据合并在一起。两台扫描仪之间的一些RF存在显著差异。PET/CT半定量参数无法预测TI的最终诊断，而与灰度共生矩阵（GLCM）相关的RF（特别是GLCM熵_log2 e、GLCM熵_log10）以及一些与灰度游程长度矩阵（GLRLM）相关和与灰度区域长度矩阵（GLZLM）相关的特征表现出最佳的预测性能。特别是，GLCM熵_log2、GLCM熵_log10、GLZLM SZHGE、GLRLM HGRE和GLRLM HGZE是表现最佳的RF。我们的研究筛选出了一些能够预测在F-FDG PET/CT成像中发现的TI最终性质的RF。经典的半定量和体积PET/CT参数并未显示出这些能力。此外，还强调了两台扫描仪在RF提取方面有良好的重叠性。
