Department of Obstetrics and Gynecology, The First Affiliated Hospital of Bengbu Medical College, No.287 Changhuai Road, Longzihu District, Bengbu, Anhui, 233004, China.
Department of Radiology, The First Affiliated Hospital of Bengbu Medical College, Bengbu, Anhui, 233004, China.
BMC Med Imaging. 2023 Aug 1;23(1):101. doi: 10.1186/s12880-023-01059-6.
Lymph node metastasis is an important factor affecting the treatment and prognosis of patients with cervical cancer. However, the comparison of different algorithms and features to predict lymph node metastasis is not well understood. This study aimed to construct a non-invasive model for predicting lymph node metastasis in patients with cervical cancer based on clinical features combined with the radiomic features of magnetic resonance imaging (MRI) images.
A total of 180 cervical cancer patients were divided into the training set (n = 126) and testing set (n = 54). In this cross-sectional study, radiomic features of MRI images and clinical features of patients were collected. The least absolute shrinkage and selection operator (LASSO) regression was used to filter the features. Seven machine learning methods, including eXtreme Gradient Boosting (XGBoost), Logistic Regression, Multinomial Naive Bayes (MNB), Support Vector Machine (SVM), Decision Tree, Random Forest, and Gradient Boosting Decision Tree (GBDT) are used to build the models. Receiver operating characteristics (ROC) curve and area under the curve (AUC), accuracy, sensitivity, and specificity were calculated to assess the performance of the models.
Of these 180 patients, 49 (27.22%) patients had lymph node metastases. Five of the 122 radiomic features and 3 clinical features were used to build predictive models. Compared with other models, the MNB model was the most robust, with its AUC, specificity, and accuracy on the testing set of 0.745 (95%CI: 0.740-0.750), 0.900 (95%CI: 0.807-0.993), and 0.778 (95%CI: 0.667-0.889), respectively. Furthermore, the AUCs of the MNB models with clinical features only, radiomic features only, and combined features were 0.698 (95%CI: 0.692-0.704), 0.632 (95%CI: 0.627-0.637), and 0.745 (95%CI: 0.740-0.750), respectively.
The MNB model, which combines the radiomic features of MRI images with the clinical features of the patient, can be used as a non-invasive tool for the preoperative assessment of lymph node metastasis.
淋巴结转移是影响宫颈癌患者治疗和预后的重要因素。然而，不同算法和特征预测淋巴结转移的效果尚不清楚。本研究旨在构建一种基于临床特征和磁共振成像（MRI）图像纹理特征的宫颈癌患者淋巴结转移的无创预测模型。
共纳入 180 例宫颈癌患者，分为训练集（n=126）和测试集（n=54）。本回顾性研究收集了 MRI 图像的纹理特征和患者的临床特征。采用最小绝对收缩和选择算子（LASSO）回归进行特征筛选。采用极端梯度提升（XGBoost）、逻辑回归、多项式朴素贝叶斯（MNB）、支持向量机（SVM）、决策树、随机森林和梯度提升决策树（GBDT）等 7 种机器学习方法构建模型。计算受试者工作特征（ROC）曲线下面积（AUC）、准确率、敏感度和特异度来评估模型性能。
180 例患者中，49 例（27.22%）患者发生淋巴结转移。从 122 个纹理特征和 3 个临床特征中筛选出 5 个特征用于构建预测模型。与其他模型相比，MNB 模型的 AUC、特异度和准确率在测试集上分别为 0.745（95%CI：0.740-0.750）、0.900（95%CI：0.807-0.993）和 0.778（95%CI：0.667-0.889）。此外，仅包含临床特征、仅包含纹理特征和联合特征的 MNB 模型的 AUC 分别为 0.698（95%CI：0.692-0.704）、0.632（95%CI：0.627-0.637）和 0.745（95%CI：0.740-0.750）。
MNB 模型结合 MRI 图像纹理特征和患者临床特征，可作为术前评估淋巴结转移的无创工具。
