J Radiat Res. 2022 Jan 20;63(1):71-79. doi: 10.1093/jrr/rrab097.
In this article, we highlight the fundamental importance of the simultaneous use of dose-volume histogram (DVH) and dose-function histogram (DFH) features based on functional images calculated from 4-dimensional computed tomography (4D-CT) and deformable image registration (DIR) in developing a multivariate radiation pneumonitis (RP) prediction model. The patient characteristics, DVH features and DFH features were calculated from functional images by Hounsfield unit (HU) and Jacobian metrics, for an RP grade ≥ 2 multivariate prediction models were computed from 85 non-small cell lung cancer patients. The prediction model is developed using machine learning via a kernel-based support vector machine (SVM) machine. In the patient cohort, 21 of the 85 patients (24.7%) presented with RP grade ≥ 2. The median area under curve (AUC) was 0.58 for the generated 50 prediction models with patient clinical features and DVH features. When HU metric and Jacobian metric DFH features were added, the AUC improved to 0.73 and 0.68, respectively. We conclude that predictive RP models that incorporate DFH features were successfully developed via kernel-based SVM. These results demonstrate that effectiveness of the simultaneous use of DVH features and DFH features calculated from 4D-CT and DIR on functional image-guided radiotherapy.
在本文中，我们强调了基于四维 CT（4D-CT）和形变图像配准（DIR）计算的功能图像的剂量-体积直方图（DVH）和剂量-函数直方图（DFH）特征的同时使用的重要性，这些特征在开发多变量放射性肺炎（RP）预测模型中具有基础性作用。我们从 85 名非小细胞肺癌患者的功能图像中，通过 Hounsfield 单位（HU）和雅可比度量法计算了患者特征、DVH 特征和 DFH 特征，为 RP 分级≥2 的患者构建了多变量预测模型。通过核支持向量机（SVM）机器，我们使用机器学习来开发预测模型。在患者队列中，85 名患者中有 21 名（24.7%）出现了 RP 分级≥2。对于使用患者临床特征和 DVH 特征生成的 50 个预测模型，其曲线下面积（AUC）中位数为 0.58。当加入 HU 度量和雅可比度量 DFH 特征后，AUC 分别提高到 0.73 和 0.68。我们得出结论，通过核 SVM 成功开发了包含 DFH 特征的预测 RP 模型。这些结果表明，4D-CT 和 DIR 计算的 DVH 特征和 DFH 特征的同时使用在功能图像引导放疗中是有效的。
