Pastor-Serrano Oscar, Perkó Zoltán
Delft University of Technology, Department of Radiation Science and Technology, Delft, The Netherlands.
Phys Med Biol. 2022 May 9;67(10). doi: 10.1088/1361-6560/ac692e.
Next generation online and real-time adaptive radiotherapy workflows require precise particle transport simulations in sub-second times, which is unfeasible with current analytical pencil beam algorithms (PBA) or Monte Carlo (MC) methods. We present a deep learning based millisecond speed dose calculation algorithm (DoTA) accurately predicting the dose deposited by mono-energetic proton pencil beams for arbitrary energies and patient geometries.Given the forward-scattering nature of protons, we frame 3D particle transport as modeling a sequence of 2D geometries in the beam's eye view. DoTA combines convolutional neural networks extracting spatial features (e.g. tissue and density contrasts) with a transformer self-attention backbone that routes information between the sequence of geometry slices and a vector representing the beam's energy, and is trained to predict low noise MC simulations of proton beamlets using 80 000 different head and neck, lung, and prostate geometries.Predicting beamlet doses in 5 ± 4.9 ms with a very high gamma pass rate of 99.37 ± 1.17% (1%, 3 mm) compared to the ground truth MC calculations, DoTA significantly improves upon analytical pencil beam algorithms both in precision and speed. Offering MC accuracy 100 times faster than PBAs for pencil beams, our model calculates full treatment plan doses in 10-15 s depending on the number of beamlets (800-2200 in our plans), achieving a 99.70 ± 0.14% (2%, 2 mm) gamma pass rate across 9 test patients.Outperforming all previous analytical pencil beam and deep learning based approaches, DoTA represents a new state of the art in data-driven dose calculation and can directly compete with the speed of even commercial GPU MC approaches. Providing the sub-second speed required for adaptive treatments, straightforward implementations could offer similar benefits to other steps of the radiotherapy workflow or other modalities such as helium or carbon treatments.
下一代在线实时自适应放射治疗工作流程需要在亚秒级时间内进行精确的粒子输运模拟，这对于当前的解析笔形束算法（PBA）或蒙特卡罗（MC）方法来说是不可行的。我们提出了一种基于深度学习的毫秒级速度剂量计算算法（DoTA），它能够准确预测任意能量和患者几何形状下单能质子笔形束沉积的剂量。考虑到质子的前向散射特性，我们将三维粒子输运构建为在束眼视图中对一系列二维几何形状进行建模。DoTA将提取空间特征（如组织和密度对比度）的卷积神经网络与一个变压器自注意力主干相结合，该主干在几何切片序列和表示束能量的向量之间传递信息，并经过训练以使用80000种不同的头颈部、肺部和前列腺几何形状来预测质子微束的低噪声MC模拟结果。与真实的MC计算相比，DoTA在5±4.9毫秒内预测微束剂量，具有99.37±1.17%（1%，3毫米）的非常高的伽马通过率，在精度和速度方面都比解析笔形束算法有显著提高。对于笔形束，我们的模型提供比PBA快100倍的MC精度，根据微束数量（我们的计划中有800 - 2200个），在10 - 15秒内计算完整的治疗计划剂量，在9名测试患者中实现了99.70±0.14%（2%，2毫米）的伽马通过率。DoTA优于所有先前的解析笔形束和基于深度学习的方法，代表了数据驱动剂量计算的新的技术水平，并且在速度上甚至可以直接与商业GPU MC方法竞争。DoTA提供了自适应治疗所需的亚秒级速度，其简单的实现方式可以为放射治疗工作流程的其他步骤或其他治疗方式（如氦或碳治疗）带来类似的益处。
