Multi-view radiomics and dosiomics analysis with machine learning for predicting acute-phase weight loss in lung cancer patients treated with radiotherapy
Multi-view radiomics and dosiomics analysis with machine learning for predicting acute-phase weight loss in lung cancer patients treated with radiotherapy
复制标题
DOI：
10.1088/1361-6560/ab8531
复制
发表时间：
2020-10-07
影响因子：
3.5
通讯作者：
Lee, Junghoon
中科院分区：
文献类型：
--
作者：
Lee, Sang Ho;Han, Peijin;Lee, Junghoon
我们提出了一种使用放射组学和剂量组学（R&D）纹理特征预测肺癌放疗急性期体重减轻（WL）的多视图数据分析方法。388名接受调强放射治疗（IMRT）的患者的基线体重在IMRT开始前一个月和开始后一周测量。分析IMRT开始后一周至两个月的体重变化，并以5% WL进行二分。每位患者均行计划CT及总肿瘤体积（GTV）和食道（ESO）等高线。共提取临床参数（CP）、GTV和ESO （GTV&ESO）剂量-体积直方图（DVH）、GTV放射组学和GTV&ESO剂量组学特征355个特征。研发特征分为一级（L1）、二级（L2）、高阶（L3）统计，以及L1 + L2、L2 + L3和L1 + L2 + L3三个组合组。采用多视图纹理分析方法识别最优R&D输入特征。在训练集（194例早期患者）中，使用Boruta算法进行特征选择，然后基于方差膨胀因子进行共线性去除。利用拉普拉斯核支持向量机（lpSVM）、深度神经网络（DNN）及其平均集成分类器建立机器学习模型。在一个独立的测试集（194个最近的患者）上测试预测性能，并在7种不同的输入条件下进行比较：CP-only, DVH-only, R&D-only, DVH + CP, R&D + CP， R&D + DVH和R&D + DVH + CP。综合GTV L1 + L2 + L3放射组学和GTV& eso L3剂量组学被认为是最优输入特征，使用集成分类器获得最佳性能（AUC = 0.710），与DVH和/或CP特征相比具有统计学意义上更高的可预测性（p < 0.05）。当将此性能与反映传统单视图数据的完全r&d特征进行比较时，差异有统计学意义（p < 0.05）。与使用传统DVH和/或CP特征相比，使用优化的多视图R&D输入特征有助于预测肺癌放疗中的早期WL，从而提高性能。
We propose a multi-view data analysis approach using radiomics and dosiomics (R&D) texture features for predicting acute-phase weight loss (WL) in lung cancer radiotherapy. Baseline weight of 388 patients who underwent intensity modulated radiation therapy (IMRT) was measured between one month prior to and one week after the start of IMRT. Weight change between one week and two months after the commencement of IMRT was analyzed, and dichotomized at 5% WL. Each patient had a planning CT and contours of gross tumor volume (GTV) and esophagus (ESO). A total of 355 features including clinical parameter (CP), GTV and ESO (GTV&ESO) dose-volume histogram (DVH), GTV radiomics, and GTV&ESO dosiomics features were extracted. R&D features were categorized as first- (L1), second- (L2), higher-order (L3) statistics, and three combined groups, L1 + L2, L2 + L3 and L1 + L2 + L3. Multi-view texture analysis was performed to identify optimal R&D input features. In the training set (194 earlier patients), feature selection was performed using Boruta algorithm followed by collinearity removal based on variance inflation factor. Machine-learning models were developed using Laplacian kernel support vector machine (lpSVM), deep neural network (DNN) and their averaged ensemble classifiers. Prediction performance was tested on an independent test set (194 more recent patients), and compared among seven different input conditions: CP-only, DVH-only, R&D-only, DVH + CP, R&D + CP, R&D + DVH and R&D + DVH + CP. Combined GTV L1 + L2 + L3 radiomics and GTV&ESO L3 dosiomics were identified as optimal input features, which achieved the best performance with an ensemble classifier (AUC = 0.710), having statistically significantly higher predictability compared with DVH and/or CP features (p < 0.05). When this performance was compared to that with full R&D-only features which reflect traditional single-view data, there was a statistically significant difference (p < 0.05). Using optimized multi-view R&D input features is beneficial for predicting early WL in lung cancer radiotherapy, leading to improved performance compared to using conventional DVH and/or CP features.