Dai Zhenhui, Zhang Yiwen, Zhu Lin, Tan Junwen, Yang Geng, Zhang Bailin, Cai Chunya, Jin Huaizhi, Meng Haoyu, Tan Xiang, Jian Wanwei, Yang Wei, Wang Xuetao
Department of Radiation Therapy, The Second Affiliated Hospital, Guangzhou University of Chinese Medicine, Guangzhou, China.
School of Biomedical Engineering, Southern Medical University, Guangzhou, China.
Front Oncol. 2021 Nov 9;11:725507. doi: 10.3389/fonc.2021.725507. eCollection 2021.
We developed a deep learning model to achieve automatic multitarget delineation on planning CT (pCT) and synthetic CT (sCT) images generated from cone-beam CT (CBCT) images. The geometric and dosimetric impact of the model was evaluated for breast cancer adaptive radiation therapy.
We retrospectively analyzed 1,127 patients treated with radiotherapy after breast-conserving surgery from two medical institutions. The CBCT images for patient setup acquired utilizing breath-hold guided by optical surface monitoring system were used to generate sCT with a generative adversarial network. Organs at risk (OARs), clinical target volume (CTV), and tumor bed (TB) were delineated automatically with a 3D U-Net model on pCT and sCT images. The geometric accuracy of the model was evaluated with metrics, including Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95). Dosimetric evaluation was performed by quick dose recalculation on sCT images relying on gamma analysis and dose-volume histogram (DVH) parameters. The relationship between ΔD95, ΔV95 and DSC-CTV was assessed to quantify the clinical impact of the geometric changes of CTV.
The ranges of DSC and HD95 were 0.73-0.97 and 2.22-9.36 mm for pCT, 0.63-0.95 and 2.30-19.57 mm for sCT from institution A, 0.70-0.97 and 2.10-11.43 mm for pCT from institution B, respectively. The quality of sCT was excellent with an average mean absolute error (MAE) of 71.58 ± 8.78 HU. The mean gamma pass rate (3%/3 mm criterion) was 91.46 ± 4.63%. DSC-CTV down to 0.65 accounted for a variation of more than 6% of V95 and 3 Gy of D95. DSC-CTV up to 0.80 accounted for a variation of less than 4% of V95 and 2 Gy of D95. The mean ΔD90/ΔD95 of CTV and TB were less than 2Gy/4Gy, 4Gy/5Gy for all the patients. The cardiac dose difference in left breast cancer cases was larger than that in right breast cancer cases.
The accurate multitarget delineation is achievable on pCT and sCT deep learning. The results show that dose distribution needs to be considered to evaluate the clinical impact of geometric variations during breast cancer radiotherapy.
我们开发了一种深度学习模型，以实现对基于锥形束CT（CBCT）图像生成的计划CT（pCT）和合成CT（sCT）图像进行自动多目标勾画。评估了该模型对乳腺癌自适应放射治疗的几何和剂量学影响。
我们回顾性分析了来自两家医疗机构的1127例保乳手术后接受放射治疗的患者。利用光学表面监测系统引导屏气获取的患者摆位CBCT图像，通过生成对抗网络生成sCT。使用3D U-Net模型在pCT和sCT图像上自动勾画危及器官（OAR）、临床靶区（CTV）和瘤床（TB）。通过包括骰子相似系数（DSC）和95%豪斯多夫距离（HD95）等指标评估模型的几何准确性。通过基于伽马分析和剂量体积直方图（DVH）参数对sCT图像进行快速剂量重新计算来进行剂量学评估。评估ΔD95、ΔV95与DSC-CTV之间的关系，以量化CTV几何变化的临床影响。
对于pCT，DSC范围为0.73-0.97，HD95范围为2.22-9.36mm；来自机构A的sCT，DSC范围为0.63-0.95，HD95范围为2.30-19.57mm；来自机构B的pCT，DSC范围为0.70-0.97，HD95范围为2.10-11.43mm。sCT质量优异，平均平均绝对误差（MAE）为71.58±8.78HU。平均伽马通过率（3%/3mm标准）为91.46±4.63%。DSC-CTV降至0.65时，V95变化超过6%，D95变化3Gy。DSC-CTV高达0.80时，V95变化小于4%，D95变化2Gy。所有患者CTV和TB的平均ΔD90/ΔD9平均小于2Gy/4Gy、4Gy/5Gy。左乳腺癌病例的心脏剂量差异大于右乳腺癌病例。
在pCT和sCT上通过深度学习可实现准确的多目标勾画。结果表明，在乳腺癌放疗期间评估几何变化的临床影响时需要考虑剂量分布。
