Department of Radiology, The Affiliated Hospital of QingDao University, QingDao, ShanDong, China.
College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, Shandong, China.
Cancer Imaging. 2019 Aug 28;19(1):60. doi: 10.1186/s40644-019-0249-x.
To explore the feasibility of diagnosing microvascular invasion (MVI) with radiomics, to compare the diagnostic performance of different models established by each method, and to determine the best diagnostic model based on radiomics.
A retrospective analysis was conducted with 206 cases of hepatocellular carcinoma (HCC) confirmed through surgery and pathology in our hospital from June 2015 to September 2018. Among the samples, 88 were MVI-positive, and 118 were MVI-negative. The radiomics analysis process included tumor segmentation, feature extraction, data preprocessing, dimensionality reduction, modeling and model evaluation.
A total of 1044 sets of texture feature parameters were extracted, and 21 methods were used for the radiomics analysis. All research methods could be used to diagnose MVI. Of all the methods, the LASSO+GBDT method had the highest accuracy, the LASSO+RF method had the highest sensitivity, the LASSO+BPNet method had the highest specificity, and the LASSO+GBDT method had the highest AUC. Through Z-tests of the AUCs, LASSO+GBDT, LASSO+K-NN, LASSO+RF, PCA + DT, and PCA + RF had Z-values greater than 1.96 (p<0.05). The DCA results showed that the LASSO + GBDT method was better than the other methods when the threshold probability was greater than 0.22.
Radiomics can be used for the preoperative, noninvasive diagnosis of MVI, but different dimensionality reduction and modeling methods will affect the diagnostic performance of the final model. The model established with the LASSO+GBDT method had the optimal diagnostic performance and the greatest diagnostic value for MVI.
探讨基于放射组学诊断微血管侵犯（MVI）的可行性，比较不同方法建立的模型的诊断效能，确定基于放射组学的最佳诊断模型。
回顾性分析 2015 年 6 月至 2018 年 9 月在我院手术病理证实的 206 例肝细胞癌（HCC）患者，其中 MVI 阳性 88 例，MVI 阴性 118 例。放射组学分析过程包括肿瘤分割、特征提取、数据预处理、降维、建模和模型评价。
共提取 1044 组纹理特征参数，使用 21 种方法进行放射组学分析。所有研究方法均可用于诊断 MVI。所有方法中，LASSO+GBDT 方法的准确率最高，LASSO+RF 方法的敏感度最高，LASSO+BPNet 方法的特异度最高，LASSO+GBDT 方法的 AUC 最高。通过 AUC 的 Z 检验，LASSO+GBDT、LASSO+K-NN、LASSO+RF、PCA+DT 和 PCA+RF 的 Z 值大于 1.96（p<0.05）。DCA 结果表明，当阈值概率大于 0.22 时，LASSO+GBDT 方法优于其他方法。
放射组学可用于 MVI 的术前、无创诊断，但不同的降维和建模方法会影响最终模型的诊断性能。LASSO+GBDT 方法建立的模型具有最佳的诊断效能，对 MVI 具有最大的诊断价值。
