Site-agnostic 3D dose distribution prediction with deep learning neural networks.
Site-agnostic 3D dose distribution prediction with deep learning neural networks.
复制标题
作者：
通常，当前的剂量预测模型仅限于少量数据，并且需要针对特定部位进行重新训练，这通常导致次优性能。我们提出了一种使用深度学习的位置不可知的三维剂量分布预测模型，该模型可以利用来自任何治疗部位的数据，从而增加可用于训练模型的总数据。将我们提出的模型应用于新的目标治疗部位仅需要对模型进行简单的微调以适应新的数据，并且不涉及对模型输入通道或其参数的修改。因此，它可以有效地适应不同的治疗部位，即使是小的训练数据集。本研究使用两个独立的数据集/治疗部位：来自接受调强放射治疗（IMRT）的前列腺癌患者的数据（源数据），以及来自接受体积调强弧形治疗（VMAT）的头颈癌患者的数据（目标数据）。我们首先开发了一个具有3D UNet架构的源模型，从源数据的随机初始权重进行训练。我们在源数据上评估了该模型的性能。然后，我们通过迁移学习研究了模型对新目标数据集的泛化能力。为此，我们又构建了三个模型，它们都具有相同的3D UNet架构：目标模型，适应模型和组合模型。源模型和目标模型分别在源数据和目标数据上从随机初始权重进行训练。调整后的模型通过使用目标数据将源模型微调到目标域。最后，在由目标和源数据集组成的组合数据池上从随机初始权重训练组合模型。我们在靶数据集上测试了所有四种模型，并评估了计划靶体积（PTV）和危及器官（OAR）的定量剂量体积直方图（DVH）指标。当在源治疗部位进行测试时，源模型准确预测了剂量分布，相对于处方剂量的平均（平均值，最大值）绝对剂量误差为（0.32%±0.14，2.37%±0.93）（PTV），最高平均剂量误差为1.68%±0.76，最高最大剂量误差为5.47%± 3.31（右侧股骨头）。D98、D95和D 02的PTV剂量覆盖预测误差分别为3.21%±1.51、3.04%±1.69和1.83%±1.01。对所有OAR进行平均，源模型预测OAR平均剂量在1.38%范围内，OAR最大剂量在3.64%范围内。对于靶治疗部位，靶模型相对于PTV处方剂量的平均（均值，最大）绝对剂量误差为（1.08%±0.95，2.90%±1.35）。左侧耳蜗的平均和最大剂量误差最高，分别为5.37%±5.82和8.33%±8.88。D98和D95的PTV剂量覆盖率预测误差分别为2.88%±1.59和2.55%±1.28。在所有OAR中，目标模型可预测OAR平均剂量在2.43%范围内，OAR最大剂量在4.33%范围内。我们开发了一种用于三维剂量预测的部位不可知模型，并通过迁移学习测试了其对新靶治疗部位的适应性。我们提出的模型可以用有限的训练数据做出准确的预测。
Typically, the current dose prediction models are limited to small amounts of data and require re-training for a specific site, often leading to suboptimal performance. We propose a site-agnostic, three dimensional dose distribution prediction model using deep learning that can leverage data from any treatment site, thus increasing the total data available to train the model. Applying our proposed model to a new target treatment site requires only a brief fine-tuning of the model to the new data and involves no modifications to the model input channels or its parameters. Thus, it can be efficiently adapted to a different treatment site, even with a small training dataset. This study uses two separate datasets/treatment sites: data from patients with prostate cancer treated with intensity-modulated radiation therapy (IMRT) (source data), and data from patients with head-and-neck cancer treated with volumetric modulated arc therapy (VMAT) (target data). We first developed a source model with 3D UNet architecture, trained from random initial weights on the source data. We evaluated the performance of this model on the source data. We then studied the generalizability of the model to the new target dataset via transfer learning. To do this, we built three more models, all with the same 3D UNet architecture: target model, adapted model, and combined model. The source and target models were trained on the source and target data from random initial weights, respectively. The adapted model fine-tuned the source model to the target domain by using the target data. Finally, the combined model was trained from random initial weights on a combined data pool consisting of both target and source datasets. We tested all four models on the target dataset and evaluated quantitative dose-volume-histogram (DVH) metrics for the planning target volume (PTV) and organs at risk (OARs). When tested on the source treatment site, the source model accurately predicted the dose distributions with average (mean, max) absolute dose errors of (0.32%±0.14, 2.37%±0.93) (PTV) relative to the prescription dose, and highest mean dose error of 1.68%±0.76, and highest max dose error of 5.47%± 3.31 for femoral head right. The error in PTV dose coverage prediction is 3.21%±1.51 for D98, 3.04%±1.69 for D95 and 1.83%±1.01 for D02. Averaging across all OARs, the source model predicted the OAR mean dose within 1.38% and the OAR max dose within 3.64%. For the target treatment site, the target model average (mean, max) absolute dose errors relative to the prescription dose for the PTV were (1.08%±0.95, 2.90%±1.35). Left cochlea had the highest mean and max dose errors of 5.37%±5.82 and 8.33%±8.88, respectively. The errors in PTV dose coverage prediction for D98 and D95 were 2.88%±1.59 and 2.55%±1.28, respectively. The target model can predict the OAR mean dose within 2.43% and the OAR max dose within 4.33% on average across all OARs. We developed a site-agnostic model for three dimensional dose prediction and tested its adaptability to a new target treatment site via transfer learning. Our proposed model can make accurate predictions with limited training data.
登录
查看更多内容
影响因子：
3.8
作者：
Barragan-Montero, Ana Maria;Dan Nguyen;Jiang, Steve
通讯作者：
Jiang, Steve
影响因子：
4.6
作者：
Dan Nguyen;Long, Troy;Jiang, Steve
通讯作者：
Jiang, Steve
影响因子：
1.2
作者：
McGarry, Conor K.;Bokrantz, Rasmus;Hounsell, Alan R.
通讯作者：
Hounsell, Alan R.
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：
5.7
作者：
BRAHME, A
通讯作者：
BRAHME, A