Delft University of Technology, Department of Radiation Science & Technology, Delft, The Netherlands.
Stanford University, Department of Radiation Oncology, Stanford, CA, United States of America.
Phys Med Biol. 2023 Apr 10;68(8):085018. doi: 10.1088/1361-6560/acc71d.
. In radiotherapy, the internal movement of organs between treatment sessions causes errors in the final radiation dose delivery. To assess the need for adaptation, motion models can be used to simulate dominant motion patterns and assess anatomical robustness before delivery. Traditionally, such models are based on principal component analysis (PCA) and are either patient-specific (requiring several scans per patient) or population-based, applying the same set of deformations to all patients. We present a hybrid approach which, based on population data, allows to predict patient-specific inter-fraction variations for an individual patient.. We propose a deep learning probabilistic framework that generates deformation vector fields warping a patient's planning computed tomography (CT) into possible patient-specific anatomies. This daily anatomy model (DAM) uses few random variables capturing groups of correlated movements. Given a new planning CT, DAM estimates the joint distribution over the variables, with each sample from the distribution corresponding to a different deformation. We train our model using dataset of 312 CT pairs with prostate, bladder, and rectum delineations from 38 prostate cancer patients. For 2 additional patients (22 CTs), we compute the contour overlap between real and generated images, and compare the sampled and 'ground truth' distributions of volume and center of mass changes.. With a DICE score of 0.86 ± 0.05 and a distance between prostate contours of 1.09 ± 0.93 mm, DAM matches and improves upon previously published PCA-based models, using as few as 8 latent variables. The overlap between distributions further indicates that DAM's sampled movements match the range and frequency of clinically observed daily changes on repeat CTs.. Conditioned only on planning CT values and organ contours of a new patient without any pre-processing, DAM can accurately deformations seen during following treatment sessions, enabling anatomically robust treatment planning and robustness evaluation against inter-fraction anatomical changes.
在放射治疗中，治疗过程中器官的内部运动导致最终辐射剂量输送中的误差。为了评估适应的必要性，可以使用运动模型来模拟主导运动模式，并在输送前评估解剖结构的稳健性。传统上，此类模型基于主成分分析（PCA），要么是针对特定患者的（每个患者需要多次扫描），要么是针对人群的，对所有患者应用相同的变形集。我们提出了一种混合方法，该方法基于人群数据，可以预测个体患者的特定分次间变化。我们提出了一种深度学习概率框架，该框架生成变形矢量场，将患者的计划计算机断层扫描（CT）变形为可能的特定于患者的解剖结构。这个每日解剖模型（DAM）使用少数随机变量来捕获相关运动的群组。给定新的计划 CT，DAM 估计变量的联合分布，分布中的每个样本对应于不同的变形。我们使用 38 名前列腺癌患者的 312 对 CT 对以及前列腺、膀胱和直肠轮廓的数据集来训练我们的模型。对于另外 2 名患者（22 个 CT），我们计算真实和生成图像之间的轮廓重叠，并比较体积和质心变化的采样和“真实”分布。DAM 的 DICE 评分为 0.86±0.05，前列腺轮廓之间的距离为 1.09±0.93mm，与之前发表的基于 PCA 的模型相匹配，并使用了 8 个潜在变量。分布之间的重叠进一步表明，DAM 采样的运动与重复 CT 上临床观察到的每日变化的范围和频率相匹配。仅基于新患者的计划 CT 值和器官轮廓，无需任何预处理，DAM 可以准确地变形在随后的治疗过程中看到的变形，从而实现解剖结构稳健的治疗计划和对分次间解剖变化的稳健性评估。
