Verification of the machine delivery parameters of a treatment plan via deep learning.
Verification of the machine delivery parameters of a treatment plan via deep learning.
复制标题
通过深度学习验证治疗方案的机器交付参数。
DOI：
10.1088/1361-6560/aba165
复制
发表时间：
2020-09-30
影响因子：
3.5
通讯作者：
Yang Y
中科院分区：
文献类型：
--
作者：
Fan J;Xing L;Ma M;Hu W;Yang Y
我们开发了一种基于生成对抗网络（GAN）的深度学习方法，用于从给定的3D剂量分布中估计多叶准直器（MLC）孔径和相应的监视器单元（MU）。对抗网络的拟议设计将残差块集成到pix 2 pix框架中，联合训练一个类似于“U-Net”的架构作为生成器，并将卷积“PatchGAN”分类器作为训练器。199例患者，包括鼻咽，肺和直肠，接受调强放射治疗和调容弧治疗技术用于训练网络。另外47名患者被用来测试所提出的深度学习模型的预测准确性。计算Dice相似系数（DSC），以评价从治疗计划系统（TPS）获得的MLC孔径形状与深度学习预测之间的相似性。计算TPS生成的MU和预测的MU之间的偏差的平均值和标准差，以评价MU预测准确度。此外，还比较了TPS和深度学习预测的MLC叶位置之间的差异。47例受试者DSC的平均值和标准差为0.94 ± 0.043。对于所有测试患者，预测MU与归一化到每个射束或弧的计划MU的平均偏差在2%以内。对于所有测试患者，预测MLC叶位置的平均偏差约为一个像素。我们的结果证明了所提出的方法的可行性和可靠性。所提出的技术具有很强的潜力，以提高病人计划质量保证过程的效率和准确性。
We developed a generative adversarial network (GAN)-based deep learning approach to estimate the multileaf collimator (MLC) aperture and corresponding monitor units (MUs) from a given 3D dose distribution. The proposed design of the adversarial network, which integrates a residual block into pix2pix framework, jointly trains a ‘U-Net’-like architecture as the generator and a convolutional ‘PatchGAN’ classifier as the discriminator. 199 patients, including nasopharyngeal, lung and rectum, treated with intensity-modulated radiotherapy and volumetric-modulated arc therapy techniques were utilized to train the network. An additional 47 patients were used to test the prediction accuracy of the proposed deep learning model. The Dice similarity coefficient (DSC) was calculated to evaluate the similarity between the MLC aperture shapes obtained from the treatment planning system (TPS) and the deep learning prediction. The average and standard deviation of the bias between the TPS-generated MUs and predicted MUs was calculated to evaluate the MU prediction accuracy. In addition, the differences between TPS and deep learning-predicted MLC leaf positions were compared. The average and standard deviation of DSC was 0.94 ± 0.043 for 47 testing patients. The average deviation of predicted MUs from the planned MUs normalized to each beam or arc was within 2% for all the testing patients. The average deviation of the predicted MLC leaf positions was around one pixel for all the testing patients. Our results demonstrated the feasibility and reliability of the proposed approach. The proposed technique has strong potential to improve the efficiency and accuracy of the patient plan quality assurance process.
登录
查看更多内容
影响因子：
3.8
作者：
Nelms, Benjamin E.;Chan, Maria F.;Feygelman, Vladimir
通讯作者：
Feygelman, Vladimir
基于深度学习技术预测三维剂量分布的自动治疗计划
影响因子：
3.8
作者：
Fan, Jiawei;Wang, Jiazhou;Hu, Weigang
通讯作者：
Hu, Weigang
影响因子：
3.8
作者：
Zhen, Heming;Nelms, Benjamin E.;Tomeacute, Wolfgang A.
通讯作者：
Tomeacute, Wolfgang A.
影响因子：
5.7
作者：
BRAHME, A
通讯作者：
BRAHME, A
影响因子：
3.5
作者：
Wang L;Kielar KN;Mok E;Hsu A;Dieterich S;Xing L
通讯作者：
Xing L