Department of Radiology, Chongqing University Cancer Hospital & Chongqing Cancer Institute & Chongqing Cancer Hospital, Chongqing 400030, People's Republic of China; Key Laboratory for Biorheological Science and Technology of Ministry of Education (Chongqing University), Chongqing University Cancer Hospital & Chongqing Cancer Institute & Chongqing Cancer Hospital, Chongqing 400044, People's Republic of China.
Clinical Science, Philips Healthcare, Shanghai, 200072, People's Republic of China.
Eur J Radiol. 2021 Jan;134:109429. doi: 10.1016/j.ejrad.2020.109429. Epub 2020 Nov 21.
To investigate the predictive value of MRI-based radiomics features for lymph node metastasis (LNM) and vascular endothelial growth factor (VEGF) expression in patients with cervical cancer.
A total of 163 patients with cervical cancer were enrolled in this study. A total of 134 patients were included for LNM differentiation, and 118 were included for VEGF expression discrimination. The patients were randomly assigned to the training group or test group at a ratio of 2:1. Radiomics features were extracted from T1WI enhanced and T2WI MRI scans of each patient, and tumor stage was also documented according to the International Federation of Gynecology and Obstetrics (FIGO) guidelines. The least absolute shrinkage and selection operator algorithm was used for feature selection. The results of 5-fold cross validation were applied to select the best classification models. The performances of the constructed models were further evaluated with the test group.
Sixteen radiomics features and the FIGO stage were selected to construct the LNM discrimination model. The LNM prediction model achieved the best diagnostic performance, with areas under the receiver operating curve (AUCs) of 0.95 and 0.88 in the training group and test group, respectively. Nine radiomics characteristics were screened to build the VEGF prediction model, with AUCs of 0.82 and 0.70 in the training group and test group, respectively. Decision curve analysis confirmed their clinical usefulness.
The presented radiomics prediction models demonstrated potential to noninvasively differentiate LNM and VEGF expression in cervical cancer.
探究基于 MRI 的放射组学特征对宫颈癌患者淋巴结转移（LNM）和血管内皮生长因子（VEGF）表达的预测价值。
本研究共纳入 163 例宫颈癌患者。其中 134 例患者用于 LNM 鉴别，118 例患者用于 VEGF 表达鉴别。患者按照 2:1 的比例随机分配至训练组或测试组。从每位患者的 T1WI 增强和 T2WI MRI 扫描中提取放射组学特征，并根据国际妇产科联盟（FIGO）指南记录肿瘤分期。采用最小绝对收缩和选择算子算法进行特征选择。应用 5 折交叉验证的结果选择最佳分类模型。使用测试组进一步评估所构建模型的性能。
选择了 16 个放射组学特征和 FIGO 分期来构建 LNM 鉴别模型。LNM 预测模型的诊断性能最佳，在训练组和测试组的受试者工作特征曲线（AUC）下面积分别为 0.95 和 0.88。筛选了 9 个放射组学特征来构建 VEGF 预测模型，在训练组和测试组的 AUC 分别为 0.82 和 0.70。决策曲线分析证实了它们的临床实用性。
所提出的放射组学预测模型具有潜在的能力，可以无创地区分宫颈癌的 LNM 和 VEGF 表达。
