Radiation Medicine and Applied Sciences, University of California, La Jolla, San Diego, California, USA.
Med Phys. 2024 Oct;51(10):7453-7463. doi: 10.1002/mp.17326. Epub 2024 Aug 1.
The quality of treatment plans for breast cancer can vary greatly. This variation could be reduced by using dose prediction to automate treatment planning. Our work investigates novel methods for training deep-learning models that are capable of producing high-quality dose predictions for breast cancer treatment planning.
The goal of this work was to compare the performance impact of two novel techniques for deep learning dose prediction models for tangent field treatments for breast cancer. The first technique, a "glowing" mask algorithm, encodes the distance from a contour into each voxel in a mask. The second, a gradient-weighted mean squared error (MSE) loss function, emphasizes the error in high-dose gradient regions in the predicted image.
Four 3D U-Net deep learning models were trained using the planning CT and contours of the heart, lung, and tumor bed as inputs. The dataset consisted of 305 treatment plans split into 213/46/46 training/validation/test sets using a 70/15/15% split. We compared the impact of novel "glowing" anatomical mask inputs and a novel gradient-weighted MSE loss function to their standard counterparts, binary anatomical masks, and MSE loss, using an ablation study methodology. To assess performance, we examined the mean error and mean absolute error (ME/MAE) in dose across all within-body voxels, the error in mean dose to heart, ipsilateral lung, and tumor bed, dice similarity coefficient (DSC) across isodose volumes defined by 0%-100% prescribed dose thresholds, and gamma analysis (3%/3 mm).
The combination of novel glowing masks and gradient weighted loss function yielded the best-performing model in this study. This model resulted in a mean ME of 0.40%, MAE of 2.70%, an error in mean dose to heart and lung of -0.10 and 0.01 Gy, and an error in mean dose to the tumor bed of -0.01%. The median DSC at 50/95/100% isodose levels were 0.91/0.87/0.82. The mean 3D gamma pass rate (3%/3 mm) was 93%.
This study found the combination of novel anatomical mask inputs and loss function for dose prediction resulted in superior performance to their standard counterparts. These results have important implications for the field of radiotherapy dose prediction, as the methods used here can be easily incorporated into many other dose prediction models for other treatment sites. Additionally, this dose prediction model for breast radiotherapy has sufficient performance to be used in an automated planning pipeline for tangent field radiotherapy and has the major benefit of not requiring a PTV for accurate dose prediction.
乳腺癌的治疗计划质量差异很大。通过使用剂量预测来实现治疗计划自动化，可以减少这种差异。我们的工作旨在研究训练深度学习模型的新方法，这些模型能够为乳腺癌治疗计划生成高质量的剂量预测。
本研究旨在比较两种用于乳腺癌切线野治疗的深度学习剂量预测模型的新型技术对性能的影响。第一种技术是“发光”掩模算法，它将距离轮廓的距离编码到掩模中的每个体素中。第二种是梯度加权均方误差（MSE）损失函数，它强调预测图像中高剂量梯度区域的误差。
使用规划 CT 和心脏、肺和肿瘤床的轮廓作为输入，训练了四个 3D U-Net 深度学习模型。数据集由 305 个治疗计划组成，使用 70/15/15%的分割方法将其分为 213/46/46 个训练/验证/测试集。我们通过消融研究方法比较了新型“发光”解剖掩模输入和新型梯度加权 MSE 损失函数与其标准对应物、二进制解剖掩模和 MSE 损失的影响。为了评估性能，我们检查了所有体内体素的剂量平均误差和平均绝对误差（ME/MAE）、心脏、同侧肺和肿瘤床的平均剂量误差、定义为 0%-100%处方剂量阈值的等剂量体积的骰子相似系数（DSC）以及伽马分析（3%/3 毫米）。
在这项研究中，新型发光掩模和梯度加权损失函数的组合产生了表现最佳的模型。该模型的平均 ME 为 0.40%，MAE 为 2.70%，心脏和肺的平均剂量误差为-0.10 和 0.01 Gy，肿瘤床的平均剂量误差为-0.01 Gy。50/95/100%等剂量水平的中位数 DSC 分别为 0.91/0.87/0.82。3D 伽马通过率（3%/3 毫米）的平均值为 93%。
本研究发现，新型解剖掩模输入和剂量预测损失函数的组合比其标准对应物的性能更好。这些结果对放疗剂量预测领域具有重要意义，因为这里使用的方法可以很容易地应用于其他治疗部位的许多其他剂量预测模型。此外，这种用于乳腺癌放疗的剂量预测模型具有足够的性能，可以用于切线野放疗的自动化计划流程，并且具有不需要 PTV 即可进行准确剂量预测的主要优点。
