通过炎症生物标志物和放射组学指标进行唾液腺肿瘤鉴别诊断的支持工具：一项初步研究
Support Tools in the Differential Diagnosis of Salivary Gland Tumors through Inflammatory Biomarkers and Radiomics Metrics: A Preliminary Study.
作者信息
Committeri Umberto, Barone Simona, Salzano Giovanni, Arena Antonio, Borriello Gerardo, Giovacchini Francesco, Fusco Roberta, Vaira Luigi Angelo, Scarpa Alfonso, Abbate Vincenzo, Ugga Lorenzo, Piombino Pasquale, Ionna Franco, Califano Luigi, Orabona Giovanni Dell'Aversana
机构信息
Maxillofacial Surgery Operative Unit, Department of Neurosciences, Reproductive and Odontostomatological Sciences, Federico II University of Naples, 80131 Naples, Italy.
Department of Maxillo-Facial Medicine Surgery, Hospital of Perugia, 06132 Perugia, Italy.
出版信息
Cancers (Basel). 2023 Mar 21;15(6):1876. doi: 10.3390/cancers15061876.
BACKGROUND
The purpose of this study was to investigate how the systemic inflammation response index (SIRI), systemic immune-inflammation index (SII), neutrophil/lymphocyte ratio (NLR) and platelet/lymphocyte ratio (PLR), and radiomic metrics (quantitative descriptors of image content) extracted from MRI sequences by machine learning increase the efficacy of proper presurgical differentiation between benign and malignant salivary gland tumors.
METHODS
A retrospective study of 117 patients with salivary gland tumors was conducted between January 2015 and November 2022. Univariate analyses with nonparametric tests and multivariate analyses with machine learning approaches were used.
RESULTS
Inflammatory biomarkers showed statistically significant differences ( < 0.05) in the Kruskal-Wallis test based on median values in discriminating Warthin tumors from pleomorphic adenoma and malignancies. The accuracy of NLR, PLR, SII, and SIRI was 0.88, 0.74, 0.76, and 0.83, respectively. Analysis of radiomic metrics to discriminate Warthin tumors from pleomorphic adenoma and malignancies showed statistically significant differences ( < 0.05) in nine radiomic features. The best multivariate analysis result was obtained from an SVM model with 86% accuracy, 68% sensitivity, and 91% specificity for six features.
CONCLUSIONS
Inflammatory biomarkers and radiomic features can comparably support a pre-surgical differential diagnosis.
背景
本研究旨在探讨全身炎症反应指数（SIRI）、全身免疫炎症指数（SII）、中性粒细胞/淋巴细胞比值（NLR）和血小板/淋巴细胞比值（PLR），以及通过机器学习从MRI序列中提取的放射组学指标（图像内容的定量描述符）如何提高涎腺肿瘤良恶性术前正确鉴别诊断的效能。
方法
对2015年1月至2022年11月期间的117例涎腺肿瘤患者进行回顾性研究。采用非参数检验进行单变量分析，采用机器学习方法进行多变量分析。
结果
基于中位数的Kruskal-Wallis检验显示，炎症生物标志物在鉴别沃辛瘤与多形性腺瘤和恶性肿瘤方面具有统计学显著差异（<0.05）。NLR、PLR、SII和SIRI的准确率分别为0.88、0.74、0.76和0.83。对鉴别沃辛瘤与多形性腺瘤和恶性肿瘤的放射组学指标分析显示，9个放射组学特征具有统计学显著差异（<0.05）。最佳多变量分析结果来自一个支持向量机（SVM）模型，该模型对6个特征的准确率为86%，灵敏度为68%，特异性为91%。
结论
炎症生物标志物和放射组学特征可以同等程度地支持术前鉴别诊断。
Zotero 插件