Department of Radiation Oncology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts.
Korean Advanced Institute of Science and Technology, Daejeon, South Korea.
Int J Radiat Oncol Biol Phys. 2023 Aug 1;116(5):1234-1243. doi: 10.1016/j.ijrobp.2023.01.055. Epub 2023 Feb 4.
Our objective was to develop an externally validated model for predicting liver toxicity after radiation therapy in patients with hepatocellular carcinoma (HCC) that can integrate both photon and proton dose distributions with patient-specific characteristics.
Training data consisted of all patients with HCC treated between 2008 and 2019 at our institution (n = 117, 60%/40% photon/proton). We developed a shallow convolutional neural network (CNN) to predict posttreatment liver dysfunction from the differential dose-volume histogram (DVH) and baseline liver metrics. To reduce bias and improve robustness, we used ensemble learning (CNNE). After a preregistered study analysis plan, we evaluated stability using internal bootstrap resampling and generalizability using a data set from a different institution (n = 88). Finally, we implemented a class activation map method to characterize the critical DVH subregions and benchmarked the model against logistic regression and XGBoost. The models were evaluated using the area under the receiver operating characteristic curve and area under the precision-recall curve.
The CNNE model showed similar internal performance and robustness compared with the benchmarks. CNNE exceeded the benchmark models in external validation, with an area under the receiver operating characteristic curve of 0.78 versus 0.55 to 0.70, and an area under the precision-recall curve of 0.6 versus 0.43 to 0.52. The model showed improved predictive power in the photon group, excellent specificity in both modalities, and high sensitivity in the photon high-risk group. Models built solely on DVHs confirm outperformance of the CNNE and indicate that the proposed structure efficiently abstracts features from both proton and photon dose distributions. The activation map method demonstrates the importance of the low-dose bath and its interaction with low liver function at baseline.
We developed and externally validated a patient-specific prediction model for hepatic toxicity based on the entire DVH and clinical factors that can integrate both photon and proton therapy cohorts. This model complements the new American Society for Radiation Oncology clinical practice guidelines and could support value-driven integration of proton therapy into the management of HCC.
我们的目标是开发一种能够整合光子和质子剂量分布与患者特征的模型，用于预测肝细胞癌（HCC）患者放射治疗后的肝毒性。
训练数据来自于 2008 年至 2019 年在我院接受治疗的所有 HCC 患者（n=117，光子/质子比例为 60%/40%）。我们开发了一个浅层卷积神经网络（CNN），根据剂量体积直方图（DVH）和基线肝脏指标来预测治疗后肝功能障碍。为了减少偏差和提高鲁棒性，我们使用了集成学习（CNNE）。在预先注册的研究分析计划之后，我们使用内部引导重采样评估了稳定性，并使用来自另一机构的数据（n=88）评估了可推广性。最后，我们实施了类激活图方法来描述关键的 DVH 子区域，并将模型与逻辑回归和 XGBoost 进行了基准测试。使用接收器操作特征曲线下面积和精度-召回曲线下面积评估了模型。
与基准模型相比，CNNE 模型具有相似的内部性能和鲁棒性。在外部验证中，CNNE 优于基准模型，其接收器操作特征曲线下面积为 0.78，而 0.55 至 0.70，精度-召回曲线下面积为 0.6，而 0.43 至 0.52。该模型在光子组中显示出了更好的预测能力，在两种模式下均具有出色的特异性，并且在光子高危组中具有较高的敏感性。仅基于 DVH 构建的模型证实了 CNNE 的卓越性能，并表明所提出的结构能够有效地从光子和质子剂量分布中提取特征。激活图方法表明低剂量浴及其与基线低肝功能之间的相互作用的重要性。
我们开发并验证了一种基于全剂量体积直方图和临床因素的患者特异性肝毒性预测模型，该模型可以整合光子和质子治疗队列。该模型补充了美国放射肿瘤学会的新临床实践指南，并为质子治疗纳入 HCC 管理提供了价值驱动的支持。
