Department of Radiation Oncology, Stanford University, 875 Blake Wilbur Drive, Stanford, CA 94305-5847, United States of America. Department of Radiation Oncology, Fudan University Shanghai Cancer Center; Department of Oncology, Shanghai Medical College Fudan University, Shanghai 200032, People's Republic of China.
Phys Med Biol. 2020 Sep 30;65(19):195007. doi: 10.1088/1361-6560/aba165.
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.
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 剂量分布估计多叶准直器（MLC）孔径和相应的监视器单位（MU）。所提出的对抗网络设计，将残差块集成到 pix2pix 框架中，联合训练了一个类似于“U-Net”的生成器架构和一个卷积“PatchGAN”分类器作为鉴别器。利用 199 名接受调强放疗和容积调强弧形治疗技术治疗的患者来训练网络。另外 47 名患者用于测试所提出的深度学习模型的预测准确性。通过计算 Dice 相似系数（DSC）来评估从治疗计划系统（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 与预测 MU 之间的偏差的平均值和标准偏差，以评估 MU 预测的准确性。此外，还比较了 TPS 和深度学习预测的 MLC 叶片位置之间的差异。对于 47 名测试患者，DSC 的平均值和标准偏差分别为 0.94 ± 0.043。对于所有测试患者，预测 MU 与计划 MU 的归一化偏差的平均值均在 2%以内。对于所有测试患者，预测 MLC 叶片位置的平均偏差约为一个像素。我们的结果证明了所提出方法的可行性和可靠性。所提出的技术具有提高患者计划质量保证过程的效率和准确性的巨大潜力。
