Technical Note: A feasibility study on deep learning-based radiotherapy dose calculation.
Technical Note: A feasibility study on deep learning-based radiotherapy dose calculation.
复制标题
DOI：
10.1002/mp.13953
复制
发表时间：
2020-02
期刊：
影响因子：
3.8
通讯作者：
Jiang S
中科院分区：
文献类型：
--
作者：
Xing Y;Nguyen D;Lu W;Yang M;Jiang S
各种剂量计算算法可用于癌症患者的放射治疗。然而，这些算法面临着效率和准确性之间的权衡。快速算法通常不太准确，而准确的剂量引擎通常是耗时的。在这项工作中，我们试图通过探索深度学习（DL）来解决这个难题。我们开发了一个新的放射治疗剂量计算引擎的基础上修改的层次密集连接的U网（HD U网）模型，并测试其可行性与前列腺调强放射治疗（IMRT）的情况下。从IMRT注量图域到3D剂量域的映射需要复杂架构的深度神经网络和庞大的训练数据集。为了解决这个问题，我们首先使用宽束射线跟踪算法将注量图投影到剂量域，然后使用HD U-网络将射线跟踪剂量分布映射到使用塌陷圆锥卷积/叠加（CS）算法计算的准确剂量分布。该模型在70名患者上进行了5倍交叉验证训练，并在单独的8名患者上进行了测试。对于典型的7射野前列腺调强放射治疗计划，计算3D剂量分布大约需要1秒，通过优化网络可以进一步减少，以实现实时剂量计算。8名测试患者的DL和CS剂量分布之间的平均伽马通过率在1 mm/1%和2 mm/2%时分别为98.5%（±1.6%）和99.9%（±0.1%）。对于两种剂量分布之间IMRT计划的各种临床评价标准（剂量-体积点）的比较，剂量标准的平均差异小于0.25戈伊，而体积标准的平均差异小于0.16%，表明DL剂量分布与CS剂量分布在临床上相同。我们已经表明，使用DL计算放射治疗剂量分布的高精度和效率的可行性。
Various dose calculation algorithms are available for radiation therapy for cancer patients. However, these algorithms are faced with the tradeoff between efficiency and accuracy. The fast algorithms are generally less accurate, while the accurate dose engines are often time consuming. In this work, we try to resolve this dilemma by exploring deep learning (DL) for dose calculation. We developed a new radiotherapy dose calculation engine based on a modified Hierarchically Densely Connected U-net (HD U-net) model and tested its feasibility with prostate intensity-modulated radiation therapy (IMRT) cases. Mapping from an IMRT fluence map domain to a 3D dose domain requires a deep neural network of complicated architecture and a huge training dataset. To solve this problem, we first project the fluence maps to the dose domain using a broad beam ray-tracing algorithm, and then we use the HD U-net to map the ray-tracing dose distribution into an accurate dose distribution calculated using a collapsed cone convolution/superposition (CS) algorithm. The model is trained on 70 patients with 5-fold cross validation, and tested on a separate 8 patients. It takes about one second to compute a 3D dose distribution for a typical 7-field prostate IMRT plan, which can be further reduced to achieve real-time dose calculation by optimizing the network. The average Gamma passing rate between DL and CS dose distributions for the 8 test patients are 98.5% (±1.6%) at 1mm/1% and 99.9% (±0.1%) at 2mm/2%. For comparison of various clinical evaluation criteria (dose-volume points) for IMRT plans between two dose distributions, the average difference for dose criteria is less than 0.25 Gy while for volume criteria is less than 0.16%, showing that the DL dose distributions are clinically identical to the CS dose distributions. We have shown the feasibility of using DL for calculating radiotherapy dose distribution with high accuracy and efficiency.
登录
查看更多内容
影响因子：
3.5
作者：
Lu, Weiguo;Chen, Mingli
通讯作者：
Chen, Mingli
影响因子：
3.8
作者：
AHNESJO, A
通讯作者：
AHNESJO, A
影响因子：
3.5
作者：
Dan Nguyen;Jia, Xun;Jiang, Steve
通讯作者：
Jiang, Steve
影响因子：
3.5
作者：
Ulmer, W;Pyyry, J;Kaissl, W
通讯作者：
Kaissl, W
影响因子：
3.5
作者：
Ulmer, W;Kaissl, W
通讯作者：
Kaissl, W