Institute of Radiation Medicine, Chinese Academy of Medical Sciences and Peking Union Medical College, Tianjin, China.
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
J Appl Clin Med Phys. 2023 Jul;24(7):e13942. doi: 10.1002/acm2.13942. Epub 2023 Mar 3.
Intensity-Modulated Radiation Therapy (IMRT) has been the standard of care for many types of tumors. However, treatment planning for IMRT is a time-consuming and labor-intensive process.
To alleviate this tedious planning process, a novel deep learning based dose prediction algorithm (TrDosePred) was developed for head and neck cancers.
The proposed TrDosePred, which generated the dose distribution from a contoured CT image, was a U-shape network constructed with a convolutional patch embedding and several local self-attention based transformers. Data augmentation and ensemble approach were used for further improvement. It was trained based on the dataset from Open Knowledge-Based Planning Challenge (OpenKBP). The performance of TrDosePred was evaluated with two mean absolute error (MAE) based scores utilized by OpenKBP challenge (i.e., Dose score and DVH score) and compared to the top three approaches of the challenge. In addition, several state-of-the-art methods were implemented and compared to TrDosePred.
The TrDosePred ensemble achieved the dose score of 2.426 Gy and the DVH score of 1.592 Gy on the test dataset, ranking at 3rd and 9th respectively in the leaderboard on CodaLab as of writing. In terms of DVH metrics, on average, the relative MAE against the clinical plans was 2.25% for targets and 2.17% for organs at risk.
A transformer-based framework TrDosePred was developed for dose prediction. The results showed a comparable or superior performance as compared to the previous state-of-the-art approaches, demonstrating the potential of transformer to boost the treatment planning procedures.
调强放射治疗（IMRT）已成为许多类型肿瘤的标准治疗方法。然而，IMRT 的治疗计划是一个耗时且劳动密集型的过程。
为了减轻这个繁琐的规划过程，我们开发了一种新的基于深度学习的剂量预测算法（TrDosePred），用于头颈部癌症。
所提出的 TrDosePred 从轮廓 CT 图像生成剂量分布，是一个具有卷积补丁嵌入和几个基于局部自注意力的转换器的 U 形网络。数据增强和集成方法用于进一步改进。它是基于 Open Knowledge-Based Planning Challenge（OpenKBP）数据集进行训练的。TrDosePred 的性能通过 OpenKBP 挑战赛中使用的两个基于平均绝对误差（MAE）的分数进行评估（即剂量分数和 DVH 分数），并与挑战赛的前三名方法进行比较。此外，还实现了几种最先进的方法，并与 TrDosePred 进行了比较。
TrDosePred 集成在测试数据集上获得了 2.426 Gy 的剂量分数和 1.592 Gy 的 DVH 分数，在 CodaLab 的排行榜上分别排名第 3 位和第 9 位。在 DVH 指标方面，平均而言，与临床计划相比，目标的相对 MAE 为 2.25%，危及器官的相对 MAE 为 2.17%。
我们开发了一种基于转换器的框架 TrDosePred 用于剂量预测。结果表明，与以前的最先进方法相比，性能相当或更优，证明了转换器在提高治疗计划程序方面的潜力。
