Department of Imaging Center, The First Affiliated Hospital of Xinjiang Medical University, Li Yu Shan Road, No. 137 Urumqi City 830054, China.
Huiying Medical Technology Co., Ltd., Room A206, B2, Dongsheng Science and Technology Park, HaiDian District, Beijing City 100192, China.
Biomed Res Int. 2021 Apr 9;2021:6681092. doi: 10.1155/2021/6681092. eCollection 2021.
To evaluate the role of radiomics based on magnetic resonance imaging (MRI) in the biological activity of hepatic alveolar echinococcosis (HAE).
In this study, 90 active and 46 inactive cases of HAE patients were analyzed retrospectively. All the subjects underwent MRI and positron emission tomography computed tomography (PET-CT) before surgery. A total of 1409 three-dimensional radiomics features were extracted from the T2-weighted MR images (T2WI). The inactive group in the training cohort was balanced via the synthetic minority oversampling technique (SMOTE) method. The least absolute shrinkage and selection operator (LASSO) regression method was used for feature selection. The machine learning (ML) classifiers were logistic regression (LR), multilayer perceptron (MLP), and support vector machine (SVM). We used a fivefold cross-validation strategy in the training cohorts. The classification performance of the radiomics signature was evaluated using receiver operating characteristic curve (ROC) analysis in the training and test cohorts.
The radiomics features were significantly associated with the biological activity, and 10 features were selected to construct the radiomics model. The best performance of the radiomics model for the biological activity prediction was obtained by MLP (AUC = 0.830 ± 0.053; accuracy = 0.817; sensitivity = 0.822; specificity = 0.811).
We developed and validated a radiomics model as an adjunct tool to predict the HAE biological activity by combining T2WI images, which achieved results nearly equal to the PET-CT findings.
评估基于磁共振成像（MRI）的放射组学在肝泡型包虫病（HAE）生物学活性中的作用。
本研究回顾性分析了 90 例活动期和 46 例静止期 HAE 患者。所有患者均在术前接受 MRI 和正电子发射断层扫描计算机断层扫描（PET-CT）检查。从 T2 加权磁共振图像（T2WI）中提取了总共 1409 个三维放射组学特征。通过合成少数过采样技术（SMOTE）方法平衡训练队列中的静止组。采用最小绝对值收缩和选择算子（LASSO）回归方法进行特征选择。机器学习（ML）分类器为逻辑回归（LR）、多层感知器（MLP）和支持向量机（SVM）。我们在训练队列中使用了五重交叉验证策略。在训练和测试队列中，使用接收者操作特征曲线（ROC）分析评估放射组学特征的分类性能。
放射组学特征与生物学活性显著相关，选择 10 个特征构建放射组学模型。MLP 对放射组学模型进行生物学活性预测的性能最佳（AUC=0.830±0.053；准确性=0.817；敏感度=0.822；特异性=0.811）。
我们开发并验证了一种基于 T2WI 图像的放射组学模型，作为预测 HAE 生物学活性的辅助工具，其结果与 PET-CT 结果相当。
