Department of Gynecology and Obstetrics, Department of Gynecology, The Second Hospital of HeBei Medical University, Affiliated Hospital of Chengde Medical University, Shijiazhuang, China.
Department of Nuclear Medicine, Affiliated Hospital of Chengde Medical University, Chengde, China.
Cancer Rep (Hoboken). 2024 Oct;7(10):e70030. doi: 10.1002/cnr2.70030.
Ovarian cancer (OC) is an aggressive gynecological tumor usually diagnosed with malignant ascites and even observed widespread metastasis or distant spread.
We aimed to develop and identify radiomics models according to computed tomography (CT) for preoperative prediction of CXCL10 expression and prognosis in patients with OC.
Genomic data with CT images and corresponding clinicopathological parameters were extracted from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA). To analyze the prognosis, we carried out the univariate Cox regression analysis (UCRA), multivariate Cox regression analysis (MCRA), and Kaplan-Meier (KM) analysis. For the data reduction, logistic regression, operator regression, least absolute shrinkage selection, radiomic feature construction, and feature selection were utilized. The predictive performance of the radiomic signatures was assessed using the analyses of the receiver operating characteristic (ROC) curve, decision curve (DCA), and precision-recall (PR) curve. To evaluate the correlation between the radiomic score (Rad-score) and CXCL10 expression, the Wilcoxon rank-sum test was applied.
Three radiomics models effectively predicted CXCL10 expression levels (AUC = 0.791, 0.748, and 0.718 for the set of training; AUC = 0.761, 0.746, and 0.701 for the set of validation). A higher Rad-score significantly correlated with upregulated CXCL10 expression.
CXCL10 expression can be predicted noninvasively and preoperatively via radiomic signatures based on contrast-enhanced CT images.
卵巢癌（OC）是一种侵袭性妇科肿瘤，通常通过恶性腹水诊断，甚至观察到广泛的转移或远处转移。
我们旨在根据计算机断层扫描（CT）开发和识别放射组学模型，以预测 OC 患者的 CXCL10 表达和预后。
从癌症成像档案（TCIA）和癌症基因组图谱（TCGA）中提取带有 CT 图像和相应临床病理参数的基因组数据。为了分析预后，我们进行了单变量 Cox 回归分析（UCRA）、多变量 Cox 回归分析（MCRA）和 Kaplan-Meier（KM）分析。为了进行数据缩减，利用了逻辑回归、操作员回归、最小绝对收缩选择、放射组学特征构建和特征选择。使用接收者操作特征（ROC）曲线、决策曲线（DCA）和精度-召回（PR）曲线分析评估放射组学特征的预测性能。为了评估放射组学评分（Rad-score）与 CXCL10 表达之间的相关性，应用了 Wilcoxon 秩和检验。
三个放射组学模型有效地预测了 CXCL10 表达水平（在训练集的 AUC 分别为 0.791、0.748 和 0.718；在验证集的 AUC 分别为 0.761、0.746 和 0.701）。较高的 Rad-score 与上调的 CXCL10 表达显著相关。
通过基于增强 CT 图像的放射组学特征，可以非侵入性和术前预测 CXCL10 表达。
