Hou Zhen, Yang Yang, Li Shuangshuang, Yan Jing, Ren Wei, Liu Juan, Wang Kangxin, Liu Baorui, Wan Suiren
State Key Laboratory of Bioelectronics, Laboratory for Medical Electronics, School of Biological Sciences and Medical Engineering, Southeast University, Nanjing 210096, China.
The Comprehensive Cancer Centre of Drum Tower Hospital, Medical School of Nanjing University & Clinical Cancer Institute of Nanjing University, Nanjing 210000, China.
Quant Imaging Med Surg. 2018 May;8(4):410-420. doi: 10.21037/qims.2018.05.01.
To determine the feasibility of radiomic analysis for predicting the therapeutic response of gastric carcinoma (GC) with abdominal cavity metastasis (GCACM) to pulsed low dose rate radiotherapy (PLDRT) using contrast-enhanced computed tomography (CECT) images.
Pretreatment CECT images of 43 GCACM patients were analyzed. Patients with complete response (CR) and partial response (PR) were considered responders, while stable disease (SD) and progressive disease (PD) as non-responders. A total of 1,117 image features were quantified from tumor region that segmented from arterial phase CT images. Intra-class correlation coefficient (ICC) and absolute correlation coefficient (ACC) were calculated for selecting influential feature subset. The capability of each influential feature on treatment response classification was assessed using Kruskal-Wallis test and receiver operating characteristic (ROC) analysis. Moreover, artificial neural network (ANN) and k-nearest neighbor (KNN) predictive models were constructed based on the training set (18 responders, 14 non-responders) and the testing set (6 responders, 5 non-responders) validated the reliability of the models. Comparison between the performances of the models was performed by using McNemar's test.
The analyses showed that 6 features (1 first order-based, 1 texture-based, 1 LoG-based, and 3 wavelet-based) were significantly different between responders and non-responders (AUCs range from 0.686 to 0.728). Both two prediction models based on features extracted from CECT showed potential in predicting the treatment response with higher accuracies (ANN: 0.714, KNN: 0.749 for the training set; ANN: 0.816, KNN: 0.816 for the testing set). No statistical difference was observed between the performance of ANN and KNN (P=0.999).
Pretreatment radiomic analysis using CECT can potentially provide important information regarding the therapeutic response to PLDRT for GCACM, improving risk stratification.
利用对比增强计算机断层扫描（CECT）图像，确定基于影像组学分析预测腹腔转移胃癌（GCACM）对脉冲低剂量率放疗（PLDRT）治疗反应的可行性。
分析43例GCACM患者的治疗前CECT图像。完全缓解（CR）和部分缓解（PR）的患者被视为反应者，疾病稳定（SD）和疾病进展（PD）的患者则视为无反应者。从动脉期CT图像分割出的肿瘤区域中量化了总共1117个图像特征。计算类内相关系数（ICC）和绝对相关系数（ACC）以选择有影响的特征子集。使用Kruskal-Wallis检验和受试者工作特征（ROC）分析评估每个有影响的特征对治疗反应分类的能力。此外，基于训练集（18例反应者，14例无反应者）构建人工神经网络（ANN）和k近邻（KNN）预测模型，并使用测试集（6例反应者，5例无反应者）验证模型的可靠性。通过McNemar检验对模型性能进行比较。
分析表明，反应者和无反应者之间有6个特征（1个基于一阶特征、1个基于纹理特征、1个基于拉普拉斯高斯算子特征和3个基于小波特征）存在显著差异（AUC范围为0.686至0.728）。基于从CECT提取的特征的两种预测模型在预测治疗反应方面均显示出潜力，准确率较高（训练集：ANN为0.714，KNN为0.749；测试集：ANN为0.816，KNN为0.816）。ANN和KNN的性能之间未观察到统计学差异（P = 0.999）。
使用CECT进行治疗前影像组学分析可能为GCACM对PLDRT的治疗反应提供重要信息，改善风险分层。
