Chen Liting, Sun Hongfei, Wang Zhongfei, Zhang Te, Zhang Hailang, Wang Wei, Sun Xiaohuan, Duan Jie, Gao Yue, Zhao Lina
Department of Radiation Oncology, Xijing Hospital, Air Force Medical University, No.169 Changle West Road, Xi'an, 710032, Shaanxi, China.
Ministry of Education Key Laboratory of Intelligent and Network Security, Faculty of Electronics and Information Engineering, Xi'an Jiaotong University, No.28, Xianning West Road, Xi'an, 710049, Shaanxi, China.
Phys Eng Sci Med. 2024 Dec;47(4):1501-1512. doi: 10.1007/s13246-024-01462-5. Epub 2024 Aug 5.
Intensity-modulated radiation therapy (IMRT) has been widely used in treating head and neck tumors. However, due to the complex anatomical structures in the head and neck region, it is challenging for the plan optimizer to rapidly generate clinically acceptable IMRT treatment plans. A novel deep learning multi-scale Transformer (MST) model was developed in the current study aiming to accelerate the IMRT planning for head and neck tumors while generating more precise prediction of the voxel-level dose distribution. The proposed end-to-end MST model employs the shunted Transformer to capture multi-scale features and learn a global dependency, and utilizes 3D deformable convolution bottleneck blocks to extract shape-aware feature and compensate the loss of spatial information in the patch merging layers. Moreover, data augmentation and self-knowledge distillation are used to further improve the prediction performance of the model. The MST model was trained and evaluated on the OpenKBP Challenge dataset. Its prediction accuracy was compared with three previous dose prediction models: C3D, TrDosePred, and TSNet. The predicted dose distributions of our proposed MST model in the tumor region are closest to the original clinical dose distribution. The MST model achieves the dose score of 2.23 Gy and the DVH score of 1.34 Gy on the test dataset, outperforming the other three models by 8%-17%. For clinical-related DVH dosimetric metrics, the prediction accuracy in terms of mean absolute error (MAE) is 2.04% for , 1.54% for , 1.87% for , 1.87% for , 1.89% for , respectively, superior to the other three models. The quantitative results demonstrated that the proposed MST model achieved more accurate voxel-level dose prediction than the previous models for head and neck tumors. The MST model has a great potential to be applied to other disease sites to further improve the quality and efficiency of radiotherapy planning.
调强放射治疗（IMRT）已广泛应用于头颈部肿瘤的治疗。然而，由于头颈部区域解剖结构复杂，计划优化器要快速生成临床可接受的IMRT治疗计划具有挑战性。在本研究中开发了一种新型深度学习多尺度Transformer（MST）模型，旨在加速头颈部肿瘤的IMRT计划，同时生成更精确的体素级剂量分布预测。所提出的端到端MST模型采用分流Transformer来捕获多尺度特征并学习全局依赖性，并利用3D可变形卷积瓶颈块来提取形状感知特征并补偿补丁合并层中空间信息的损失。此外，使用数据增强和自知识蒸馏来进一步提高模型的预测性能。MST模型在OpenKBP挑战数据集上进行了训练和评估。将其预测准确性与之前的三个剂量预测模型进行了比较：C3D、TrDosePred和TSNet。我们提出的MST模型在肿瘤区域的预测剂量分布最接近原始临床剂量分布。MST模型在测试数据集上的剂量评分为2.23 Gy，DVH评分为1.34 Gy，比其他三个模型高出8%-17%。对于临床相关的DVH剂量学指标，平均绝对误差（MAE）方面的预测准确性分别为 2.04%、 1.54%、 1.87%、 1.87%、 1.89%，优于其他三个模型。定量结果表明，所提出的MST模型在头颈部肿瘤的体素级剂量预测方面比之前的模型更准确。MST模型具有很大的潜力应用于其他疾病部位，以进一步提高放射治疗计划的质量和效率。
