发表机构
Medical University of Vienna; Christian Doppler Laboratory for Image and Knowledge Driven Precision Radiation Oncology; Umeå University（维也纳医科大学; 克里斯蒂安·多普勒图像与知识驱动精准放射肿瘤学实验室; 于默奥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出结合卷积残差校正网络的GPU笔形束引擎PyDoseRT Proton，用于快速质子剂量计算，在DoseRAD2026任务中实现了高精度剂量预测。
AI 中文摘要
本文提出了一种混合方法：基于物理的解析笔形束（PB）剂量引擎，辅以3D卷积残差校正网络（RepVGG-U-Net）。研究人员利用PyDoseRT Proton解决DoseRAD2026质子剂量预测任务，该引擎基于PyTorch实现，具备GPU加速能力，通过学习残差逼近蒙特卡洛（MC）的计算精度。研究人员分两个阶段将双高斯PB核校准至GATE/Geant4在水中的积分深度剂量：首先进行经典的单能曲线拟合，再通过PyTorch物理引擎对全3D剂量进行基于梯度的拟合，该引擎保留了可微执行路径，支持对剂量相关目标进行基于梯度的优化。该引擎在射线视角（BEV）格点上计算每个射束段，采用方差保留高斯拆分、解析核晕及Fermi-Eyges异质性项，再将结果旋转至患者坐标系。此外，一个紧凑的残差U-Net在BEV空间预测加性校正，其条件为体素级材料标签嵌入、离散能量嵌入及射斑大小，同一模型适用于所有解剖部位（胸部和腹部）。模型采用患者空间L1损失训练，重点关注高分高剂量区域及多尺度BEV深度监督。提交的CT配置获得初步测试结果：射束段平均绝对误差（MAE）0.0066，图像z方向积分深度剂量（IDD）距离0.0025，计划MAE 0.0049，1%/1mm标准下伽马通过率98.30%，剂量体积直方图（DVH）误差0.460。
英文摘要
Architecture category. Hybrid method: a physics-based analytical pencil-beam (PB) dose engine followed by a 3-D convolutional residual-correction network (RepVGG-U-Net). We addressed the DoseRAD2026 proton dose-prediction task with PyDoseRT Proton, a GPU-accelerated engine implemented in PyTorch and augmented by a learned residual toward Monte Carlo (MC) accuracy. A double-Gaussian PB kernel was calibrated to GATE/Geant4 integrated depth doses in water in two stages: a classical per-energy curve fit, then a gradient-based fit of the full 3-D dose through the PyTorch physics engine as it retains a differentiable execution path for gradient-based optimization of dose-dependent objectives. The engine computes each beamlet on a beam's-eye-view (BEV) lattice with variance-preserving Gaussian splitting, an analytic nuclear halo, and a Fermi-Eyges heterogeneity term, then rotates the result into the patient frame. Additionally, a compact residual U-Net predicts an additive correction in BEV space. It is conditioned on voxelwise material-label embeddings, a discrete energy embedding and spot size. The same model was used for all anatomical sites (thoracic and abdominal). It was trained with a patient-space L1 objective emphasizing the scored high-dose region and multi-scale BEV deep supervision. The submitted CT configuration obtained preliminary-test beamlet MAE 0.0066, image-z IDD distance 0.0025, plan MAE 0.0049, 98.30\% gamma pass rate (1\%/1 mm), and DVH error 0.460.
CommentsDoseRAD 2026 report - Team DoseHappens
