用深度学习直接从CBCT算质子放疗剂量，省去繁琐校正步骤。
Neural Network-Driven Direct CBCT-Based Dose Calculation for Head-and-Neck Proton Treatment Planning
- 用xLSTM网络建模质子剂量分布空间依赖性，结合能量标记和视野序列。
- 在5名患者上验证，95.1%的剂量通过2mm/2%伽马分析，误差低于6%。
- 计算时间<3分钟，适合自适应放疗，无需传统图像校正流程。
准确的锥形束计算机断层扫描（CBCT）图像剂量计算对现代质子治疗计划至关重要，尤其在考虑分次间解剖变化的自适应治疗中。传统基于CBCT的剂量计算受限于图像质量，需复杂校正流程。本研究开发并验证了一种基于扩展长短期记忆（xLSTM）神经网络的深度学习方法，实现从CBCT图像直接进行质子剂量计算。使用40例头颈部癌症患者的配对计划CT与治疗期CBCT数据训练了名为CBCT-NN的xLSTM模型，其架构包含能量标记编码与射野视角序列建模，以捕捉质子剂量沉积的空间依赖性。训练采用82,500组配对射野配置及蒙特卡洛生成的真实剂量作为标签。在5名独立患者上进行验证，采用伽马分析、平均百分比剂量误差评估与剂量体积直方图比较。结果显示，使用2mm/2%标准时，伽马通过率为95.1±2.7%；高剂量区（>90%最大剂量）平均误差为2.6±1.4%，全局平均误差为5.9±1.9%。剂量体积直方图分析表明靶区覆盖度（临床靶区V95%差异：-0.6±1.1%）和危及器官约束（腮腺平均剂量差异：-0.5±1.5%）均良好保持。计算时间低于3分钟，且不牺牲蒙特卡洛级精度。本研究证明了使用xLSTM神经网络实现直接CBCT质子剂量计算的可行性，该方法免除了传统校正流程，具备可比精度与计算效率，适用于自适应治疗方案。
原文摘要 · Abstract (English)
Accurate dose calculation on cone beam computed tomography (CBCT) images is essential for modern proton treatment planning workflows, particularly when accounting for inter-fractional anatomical changes in adaptive treatment scenarios. Traditional CBCT-based dose calculation suffers from image quality limitations, requiring complex correction workflows. This study develops and validates a deep learning approach for direct proton dose calculation from CBCT images using extended Long Short-Term Memory (xLSTM) neural networks. A retrospective dataset of 40 head-and-neck cancer patients with paired planning CT and treatment CBCT images was used to train an xLSTM-based neural network (CBCT-NN). The architecture incorporates energy token encoding and beam's-eye-view sequence modelling to capture spatial dependencies in proton dose deposition patterns. Training utilized 82,500 paired beam configurations with Monte Carlo-generated ground truth doses. Validation was performed on 5 independent patients using gamma analysis, mean percentage dose error assessment, and dose-volume histogram comparison. The CBCT-NN achieved gamma pass rates of 95.1 $\pm$ 2.7% using 2mm/2% criteria. Mean percentage dose errors were 2.6 $\pm$ 1.4% in high-dose regions ($>$90% of max dose) and 5.9 $\pm$ 1.9% globally. Dose-volume histogram analysis showed excellent preservation of target coverage metrics (Clinical Target Volume V95% difference: -0.6 $\pm$ 1.1%) and organ-at-risk constraints (parotid mean dose difference: -0.5 $\pm$ 1.5%). Computation time is under 3 minutes without sacrificing Monte Carlo-level accuracy. This study demonstrates the proof-of-principle of direct CBCT-based proton dose calculation using xLSTM neural networks. The approach eliminates traditional correction workflows while achieving comparable accuracy and computational efficiency suitable for adaptive protocols.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。