A fast deep learning approach for beam orientation optimization for prostate cancer treated with intensity-modulated radiation therapy.
A fast deep learning approach for beam orientation optimization for prostate cancer treated with intensity-modulated radiation therapy.
复制标题
DOI：
10.1002/mp.13986
复制
发表时间：
2020-03
期刊：
影响因子：
3.8
通讯作者：
Nguyen D
中科院分区：
文献类型：
--
作者：
Sadeghnejad Barkousaraie A;Ogunmolu O;Jiang S;Nguyen D
无论是手动还是基于方案的光束方向选择，都是目前放射治疗治疗计划的临床标准，但它繁琐且可能产生不理想的结果。由于光束取向对治疗计划质量的影响，许多算法被设计用于优化光束取向选择，但这些算法存在所有候选光束剂量影响矩阵计算缓慢的问题。我们提出了一种基于深度学习神经网络（DNN）的快速光束方向选择方法，能够开发出与最先进的柱生成方法开发的计划相当的计划。我们的模型的新颖之处在于它的监督学习结构（使用柱生成来教导网络）、深度神经网络架构，以及从解剖特征中学习的能力，从而在不使用候选光束的剂量学信息的情况下预测适合的光束方向。这可以节省数小时的计算。训练有监督深度神经网络来模拟列生成算法，该算法在每次迭代时根据Karush-Kush-Tucker最优条件计算梁的适应度值，依次迭代选择梁的方向。DNN学习预测这些值。该数据集包含70名前列腺癌患者- 50名训练患者，7名验证患者和13名测试患者-用于开发和测试模型。每位患者的数据包含6个轮廓：PTV、身体、膀胱、直肠、左右股骨头。使用基于gpu的Chambolle-Pock算法（一阶原对偶近类算法）实现列生成，以创建6270个平面。DNN训练了400多个epoch，每个epoch有2500步，批大小为1，使用Adam优化器以1 × 10−5的学习率和6倍交叉验证技术进行训练。训练、验证和测试损失函数的平均值和标准差分别为0.62±0.09%、1.04±0.06%和1.44±0.11%。使用列生成和监督DNN，我们为测试集中的每个场景生成了两组计划。该方法最多需要1.5秒来选择一组5个光束方向，300秒来计算5个光束的剂量影响矩阵，最后20秒来求解通量图优化。然而，柱生成需要大约15小时来计算所有光束的剂量影响矩阵，并且至少需要400秒来解决光束方向选择和通量图优化问题。柱生成和DNN生成的PTV的剂量覆盖率差异为0.2%。各脏器接受的平均剂量差异在1 ~ 6%之间，其中膀胱的平均剂量差异最小（0.956±1.184%），其次是直肠（2.44±2.11%）、左股骨头（6.03±5.86%）和右股骨头（5.885±5.515%）。机体接受的剂量在产生的治疗方案之间的平均差异为0.10±0.1%。我们开发了一种基于深度神经网络的快速光束方向选择方法，该方法可以在几秒内选择光束方向，因此适合临床常规。在该方法的训练阶段，该模型根据患者的解剖特征学习合适的光束方向，并省略了所有可能候选光束的剂量影响矩阵的耗时计算。求解通量图优化以得到最终的治疗方案，只需要计算所选光束的剂量影响矩阵。
Beam orientation selection, whether manual or protocol-based, is the current clinical standard in radiation therapy treatment planning, but it is tedious and can yield suboptimal results. Many algorithms have been designed to optimize beam orientation selection because of its impact on treatment plan quality, but these algorithms suffer from slow calculation of the dose influence matrices of all candidate beams. We propose a fast beam orientation selection method, based on deep learning neural networks (DNN), capable of developing a plan comparable to those developed by the state-of-the-art column generation method. Our model’s novelty lies in its supervised learning structure (using column generation to teach the network), DNN architecture, and ability to learn from anatomical features to predict dosimetrically suitable beam orientations without using dosimetric information from the candidate beams. This may save hours of computation. A supervised DNN is trained to mimic the column generation algorithm, which iteratively chooses beam orientations one-by-one by calculating beam fitness values based on Karush-Kush-Tucker optimality conditions at each iteration. The DNN learns to predict these values. The dataset contains 70 prostate cancer patients—50 training, 7 validation, and 13 test patients—to develop and test the model. Each patient’s data contains 6 contours: PTV, body, bladder, rectum, and left and right femoral heads. Column generation was implemented with a GPU-based Chambolle-Pock algorithm, a first-order primal-dual proximal-class algorithm, to create 6270 plans. The DNN trained over 400 epochs, each with 2500 steps and a batch size of 1, using the Adam optimizer at a learning rate of 1 × 10−5 and a 6-fold cross-validation technique. The average and standard deviation of training, validation, and testing loss functions among the 6-folds were 0.62±0.09%, 1.04±0.06%, and 1.44±0.11%, respectively. Using column generation and supervised DNN, we generated two sets of plans for each scenario in the test set. The proposed method took at most 1.5 seconds to select a set of five beam orientations and 300 second to calculate the dose influence matrices for 5 beams and finally 20 seconds to solve the fluence map optimization. However, column generation needed around 15 hours to calculate the dose influence matrices of all beams and at least 400 seconds to solve both the beam orientation selection and fluence map optimization problems. The differences in the dose coverage of PTV between plans generated by column generation and by DNN were 0.2%. The average dose differences received by organs at risk were between 1 and 6 percent: Bladder had the smallest average difference in dose received (0.956±1.184%), then Rectum (2.44±2.11%), Left Femoral Head (6.03±5.86%), and Right Femoral Head (5.885±5.515%). The dose received by Body had an average difference of 0.10± 0.1% between the generated treatment plans. We developed a fast beam orientation selection method based on a DNN that selects beam orientations in seconds and is therefore suitable for clinical routines. In the training phase of the proposed method, the model learns the suitable beam orientations based on patients’ anatomical features and omits time intensive calculations of dose influence matrices for all possible candidate beams. Solving the fluence map optimization to get the final treatment plan requires calculating dose influence matrices only for the selected beams.
登录
查看更多内容
影响因子：
4.6
作者：
Dan Nguyen;Long, Troy;Jiang, Steve
通讯作者：
Jiang, Steve
影响因子：
3.8
作者：
Dan Nguyen;Dong, Peng;Sheng, Ke
通讯作者：
Sheng, Ke
影响因子：
3.8
作者：
Amit, Guy;Purdie, Thomas G.;Pekar, Vladimir
通讯作者：
Pekar, Vladimir
DOI：
10.1016/j.ijrobp.2005.11.005
发表时间：
2006-03-01
影响因子：
7
作者：
Aoyama, H;Westerly, DC;Mehta, MP
通讯作者：
Mehta, MP
影响因子：
1.8
作者：
Aleman, Dionne M.;Kumar, Arvind;Dempsey, James F.
通讯作者：
Dempsey, James F.