Department of Radiology, Institute of Medical Science, University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, 108-8639 Tokyo, Japan.
Division of Advanced Medicine Promotion, The Advanced Clinical Research Center, Institute of Medical Science, University of Tokyo, 4-6-1 Shirokanedai, Minato-ku, 108-8639 Tokyo, Japan.
Diagn Interv Imaging. 2018 Oct;99(10):643-651. doi: 10.1016/j.diii.2018.05.008. Epub 2018 Jun 14.
To investigate the impact of random survival forest (RSF) classifier trained by radiomics features over the prediction of the overall survival of patients with resectable hepatocellular carcinoma (HCC).
The dynamic computed tomography data of 127 patients (97 men, 30 women; mean age, 68 years) newly diagnosed with resectable HCC were retrospectively analyzed. After manually setting the region of interest to include the tumor within the slice at its maximum diameter, texture analyses were performed with or without a Laplacian of Gaussian filter. Using the extracted 96 histogram based texture features, RSFs were trained using 5-fold cross-validation to predict the individual risk for each patient on disease free survival (DFS) and overall survival (OS). The associations between individual risk and DFS or OS were evaluated using Kaplan-Meier analysis. The effects of the predicted individual risk and clinical variables upon OS were analyzed using a multivariate Cox proportional hazards model.
Among the 96 histogram based texture features, RSF extracted 8 of high importance for DFS and 15 for OS. The RSF trained by these features distinguished two patient groups with high and low predicted individual risk (P=1.1×10 for DFS, 4.8×10 for OS). Based on the multivariate Cox proportional hazards model, high predicted individual risk (hazard ratio=1.06 per 1% increase, P=8.4×10) and vascular invasion (hazard ratio=1.74, P=0.039) were the only unfavorable prognostic factors.
The combination of radiomics analysis and RSF might be useful in predicting the prognosis of patients with resectable HCC.
利用基于放射组学特征的随机生存森林（RSF）分类器预测可切除肝细胞癌（HCC）患者的总生存期。
回顾性分析 127 例（97 名男性，30 名女性；平均年龄 68 岁）新诊断为可切除 HCC 患者的动态 CT 数据。在手动设置感兴趣区域以包含切片中最大直径的肿瘤后，进行纹理分析，包括或不包括拉普拉斯高斯滤波器。使用提取的 96 个基于直方图的纹理特征，使用 5 折交叉验证通过 RSF 训练来预测每位患者的无病生存率（DFS）和总生存率（OS）的个体风险。使用 Kaplan-Meier 分析评估个体风险与 DFS 或 OS 的相关性。使用多变量 Cox 比例风险模型分析预测的个体风险和临床变量对 OS 的影响。
在 96 个基于直方图的纹理特征中，RSF 提取了 8 个对 DFS 重要的特征和 15 个对 OS 重要的特征。由这些特征训练的 RSF 可区分具有高和低预测个体风险的两组患者（DFS 为 1.1×10，OS 为 4.8×10）。基于多变量 Cox 比例风险模型，高预测个体风险（风险比=每增加 1%，P=8.4×10）和血管侵犯（风险比=1.74，P=0.039）是唯一的不利预后因素。
放射组学分析与 RSF 的结合可能有助于预测可切除 HCC 患者的预后。
