Automated segmentation of the esophagus is critical in image-guided/adaptive radiotherapy of lung cancer to minimize radiation-induced toxicities such as acute esophagitis. We have developed a semantic physics-based data augmentation method for segmenting the esophagus in both planning CT (pCT) and cone beam CT (CBCT) using 3D convolutional neural networks. One hundred and ninety-one cases with their pCTs and CBCTs from four independent datasets were used to train a modified 3D U-Net architecture and a multi-objective loss function specifically designed for soft-tissue organs such as the esophagus. Scatter artifacts and noises were extracted from week-1 CBCTs using a power-law adaptive histogram equalization method and induced to the corresponding pCT were reconstructed using CBCT reconstruction parameters. Moreover, we leveraged physics-based artifact induction in pCTs to drive the esophagus segmentation in real weekly CBCTs. Segmentations were evaluated using the geometric Dice coefficient and Hausdorff distance as well as dosimetrically using mean esophagus dose and D _5cc. Due to the physics-based data augmentation, our model trained just on the synthetic CBCTs was robust and generalizable enough to also produce state-of-the-art results on the pCTs and CBCTs, achieving Dice overlaps of 0.81 and 0.74, respectively. It is concluded that our physics-based data augmentation spans the realistic noise/artifact spectrum across patient CBCT/pCT data and can generalize well across modalities, eventually improving the accuracy of treatment setup and response analysis.

食管的自动分割在肺癌的图像引导/自适应放射治疗中至关重要，以最大限度地减少辐射引起的毒性，如急性食管炎。我们开发了一种基于语义物理的数据增强方法，用于使用 3D 卷积神经网络在计划 CT (pCT) 和锥形束 CT (CBCT) 中分割食道。使用来自四个独立数据集的 191 例 pCT 和 CBCT 来训练改进的 3D U-Net 架构和专为食道等软组织器官设计的多目标损失函数。使用幂律自适应直方图均衡方法从第 1 周的 CBCT 中提取散射伪影和噪声，并使用 CBCT 重建参数重建相应的 pCT。而且，我们利用 pCT 中基于物理的伪影诱导来驱动真正的每周 CBCT 中的食道分割。使用几何 Dice 系数和 Hausdorff 距离以及使用平均食道剂量和剂量学来评估分割D _5cc。由于基于物理的数据增强，我们仅在合成 CBCT 上训练的模型具有足够的鲁棒性和泛化性，足以在 pCT 和 CBCT 上产生最先进的结果，分别实现了 0.81 和 0.74 的 Dice 重叠。得出的结论是，我们基于物理的数据增强跨越了患者 CBCT/pCT 数据的真实噪声/伪影谱，并且可以很好地泛化各种模式，最终提高治疗设置和响应分析的准确性。