Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, Georgia, USA.
Med Phys. 2022 Dec;49(12):7545-7554. doi: 10.1002/mp.15875. Epub 2022 Aug 3.
A quality assurance (QA) CT scans are usually acquired during cancer radiotherapy to assess for any anatomical changes, which may cause an unacceptable dose deviation and therefore warrant a replan. Accurate and rapid deformable image registration (DIR) is needed to support contour propagation from the planning CT (pCT) to the QA CT to facilitate dose volume histogram (DVH) review. Further, the generated deformation maps are used to track the anatomical variations throughout the treatment course and calculate the corresponding accumulated dose from one or more treatment plans.
In this study, we aim to develop a deep learning (DL)-based method for automatic deformable registration to align the pCT and the QA CT. Our proposed method, named dual-feasible framework, was implemented by a mutual network that functions as both a forward module and a backward module. The mutual network was trained to predict two deformation vector fields (DVFs) simultaneously, which were then used to register the pCT and QA CT in both directions. A novel dual feasible loss was proposed to train the mutual network. The dual-feasible framework was able to provide additional DVF regularization during network training, which preserves the topology and reduces folding problems. We conducted experiments on 65 head-and-neck cancer patients (228 CTs in total), each with 1 pCT and 2-6 QA CTs. For evaluations, we calculated the mean absolute error (MAE), peak-signal-to-noise ratio (PSNR), structural similarity index (SSIM), target registration error (TRE) between the deformed and target images and the Jacobian determinant of the predicted DVFs.
Within the body contour, the mean MAE, PSNR, SSIM, and TRE are 122.7 HU, 21.8 dB, 0.62 and 4.1 mm before registration and are 40.6 HU, 30.8 dB, 0.94, and 2.0 mm after registration using the proposed method. These results demonstrate the feasibility and efficacy of our proposed method for pCT and QA CT DIR.
In summary, we proposed a DL-based method for automatic DIR to match the pCT to the QA CT. Such DIR method would not only benefit current workflow of evaluating DVHs on QA CTs but may also facilitate studies of treatment response assessment and radiomics that depend heavily on the accurate localization of tissues across longitudinal images.
在癌症放射治疗过程中，通常会获取质量保证（QA）CT 扫描，以评估任何可能导致不可接受的剂量偏差的解剖结构变化，从而需要重新计划。需要准确快速的可变形图像配准（DIR）来支持从计划 CT（pCT）到 QA CT 的轮廓传播，以方便剂量体积直方图（DVH）审查。此外，生成的变形图用于跟踪整个治疗过程中的解剖变化，并计算来自一个或多个治疗计划的相应累积剂量。
在这项研究中，我们旨在开发一种基于深度学习（DL）的方法，用于自动配准 pCT 和 QA CT。我们提出的方法名为双可行框架，由一个互网络实现，该网络既是正向模块又是反向模块。互网络被训练来同时预测两个变形向量场（DVFs），然后使用这两个 DVFs 在两个方向上配准 pCT 和 QA CT。提出了一种新的双可行损失来训练互网络。双可行框架能够在网络训练过程中提供额外的 DVF 正则化，从而保留拓扑并减少折叠问题。我们对 65 例头颈部癌症患者（总共 228 个 CT）进行了实验，每个患者都有 1 个 pCT 和 2-6 个 QA CT。对于评估，我们计算了变形图像和目标图像之间的平均绝对误差（MAE）、峰值信噪比（PSNR）、结构相似性指数（SSIM）、目标配准误差（TRE）和预测的 DVFs 的雅可比行列式。
在体廓内，配准前的平均 MAE、PSNR、SSIM 和 TRE 分别为 122.7 HU、21.8 dB、0.62 和 4.1 mm，配准后分别为 40.6 HU、30.8 dB、0.94 和 2.0 mm。这些结果表明，我们提出的用于 pCT 和 QA CT DIR 的方法是可行和有效的。
总之，我们提出了一种基于深度学习的自动 DIR 方法，用于将 pCT 与 QA CT 匹配。这种 DIR 方法不仅有利于当前在 QA CT 上评估 DVH 的工作流程，而且可能有助于研究严重依赖于纵向图像中组织准确定位的治疗反应评估和放射组学。
