Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA 94305, United States of America.
Department of Electrical Engineering, Stanford University, Stanford, CA 94305, United States of America.
Phys Med Biol. 2022 Jun 13;67(12). doi: 10.1088/1361-6560/ac6b10.
. Dose distribution data plays a pivotal role in radiotherapy treatment planning. The data is typically represented using voxel grids, and its size ranges from 10to 10. A concise representation of the treatment plan is of great value in facilitating treatment planning and downstream applications. This work aims to develop an implicit neural representation of 3D dose distribution data.. Instead of storing the dose values at each voxel, in the proposed approach, the weights of a multilayer perceptron (MLP) are employed to characterize the dosimetric data for plan representation and subsequent applications. We train a coordinate-based MLP with sinusoidal activations to map the voxel spatial coordinates to the corresponding dose values. We identify the best architecture for a given parameter budget and use that to train a model for each patient. The trained MLP is evaluated at each voxel location to reconstruct the dose distribution. We perform extensive experiments on dose distributions of prostate, spine, and head and neck tumor cases to evaluate the quality of the proposed representation. We also study the change in representation quality by varying model size and activation function.. Using coordinate-based MLPs with sinusoidal activations, we can learn implicit representations that achieve a mean-squared error of 10and peak signal-to-noise ratio greater than 50 dB at a target bitrate of ∼1 across all the datasets, with a compression ratio of ∼32. Our results also show that model sizes with a bitrate of 1-2 achieve optimal accuracy. For smaller bitrates, performance starts to drop significantly.. The proposed model provides a low-dimensional, implicit, and continuous representation of 3D dose data. In summary, given a dose distribution, we systematically show how to find a compact model to fit the data accurately. This study lays the groundwork for future applications of neural representations of dose data in radiation oncology.
剂量分布数据在放射治疗计划中起着至关重要的作用。该数据通常使用体素网格表示，其大小范围为 10 到 10。治疗计划的简洁表示对于促进治疗计划和下游应用具有重要价值。本工作旨在开发一种 3D 剂量分布数据的隐式神经表示。
在提出的方法中，不是在每个体素存储剂量值，而是使用多层感知机（MLP）的权重来表征剂量数据，以用于计划表示和随后的应用。我们使用基于坐标的正弦激活 MLP 来将体素空间坐标映射到相应的剂量值。我们为给定的参数预算确定最佳架构，并使用该架构为每个患者训练一个模型。在每个体素位置评估训练好的 MLP，以重建剂量分布。我们在前列腺、脊柱和头颈部肿瘤病例的剂量分布上进行了广泛的实验，以评估所提出表示的质量。我们还研究了通过改变模型大小和激活函数来改变表示质量的变化。
使用基于坐标的正弦激活 MLP，我们可以学习隐式表示，在所有数据集上，在目标比特率约为 1 时，均方误差达到 10，峰值信噪比大于 50dB，压缩比约为 32。我们的结果还表明，比特率为 1-2 的模型大小具有最佳的准确性。对于较小的比特率，性能开始显著下降。
所提出的模型为 3D 剂量数据提供了一种低维、隐式和连续的表示。总之，给定一个剂量分布，我们系统地展示了如何找到一个紧凑的模型来准确拟合数据。本研究为神经表示剂量数据在放射肿瘤学中的未来应用奠定了基础。
