Département de physique, Université de Montréal, Complexe des sciences, 1375 Avenue Thérèse-Lavoie-Roux, Montréal, Québec H2V 0B3, Canada.
Centre de recherche du Centre hospitalier de l'Université de Montréal, 900 Rue Saint-Denis, Montréal, Québec, H2X 0A9, Canada.
Phys Med Biol. 2021 May 4;66(10). doi: 10.1088/1361-6560/abf1b8.
Respiration-induced motion introduces significant positioning uncertainties in radiotherapy treatments for thoracic sites. Accounting for this motion is a non-trivial task commonly addressed with surrogate-based strategies and latency compensating techniques. This study investigates the potential of a new unified probabilistic framework to predict both future target motion in real-time from a surrogate signal and associated uncertainty.A Bayesian approach is developed, based on a Kalman filter theory adapted specifically for surrogate measurements. Breathing motions are collected simultaneously from a lung target, two external surrogates (abdominal and thoracic markers) and an internal surrogate (liver structure) for 9 volunteers during 4 min, in which severe breathing changes occur to assess the robustness of the method. A comparison with an artificial non-linear neural network (NN) is performed, although no confidence interval prediction is provided. A static worst-case scenario and a simple static design are investigated.Although the NN can reduce the prediction errors from thoracic surrogate in some cases, the Bayesian framework outperforms in most cases the NN when using the other surrogates: bias on predictions is reduced by 38% and 16% on average when using respectively the liver and the abdomen for the simple scenario, and by respectively 40% and 31% for the worst-case scenario. The standard deviation of residuals is reduced on average by up to 42%. The Bayesian method is also found to be more robust to increasing latencies. The thoracic marker appears to be less reliable to predict the target position, while the liver shows to be a better surrogate. A statistical test confirms the significance of both observations.The proposed framework predicts both the future target position and the associated uncertainty, which can be valuably used to further assist motion management decisions. Further investigation is required to improve the predictions by using an adaptive version of the proposed framework.
呼吸运动在胸部肿瘤放射治疗中引入了显著的定位不确定性。通常采用基于替代物的策略和延迟补偿技术来解决这个问题。本研究旨在探索一种新的统一概率框架的潜力，以从替代物信号实时预测未来的目标运动及其相关不确定性。基于专门为替代物测量而设计的卡尔曼滤波器理论，提出了一种贝叶斯方法。该方法从 9 名志愿者的肺部目标、2 个外部替代物（腹部和胸部标记）和 1 个内部替代物（肝脏结构）中同时收集呼吸运动，持续 4 分钟，在此期间，呼吸会发生剧烈变化，以评估该方法的稳健性。与人工非线性神经网络（NN）进行了比较，尽管没有提供置信区间预测。还研究了静态最坏情况场景和简单静态设计。尽管在某些情况下，NN 可以减少胸部替代物的预测误差，但在使用其他替代物时，贝叶斯框架在大多数情况下优于 NN：在简单情况下，使用肝脏和腹部时，预测偏差平均减少 38%和 16%；在最坏情况下，预测偏差平均减少 40%和 31%。残差的标准差平均减少了 42%。还发现，贝叶斯方法对增加的延迟更具鲁棒性。胸部标记物似乎不太可靠，无法准确预测目标位置，而肝脏则显示出更好的替代物特性。统计检验证实了这两种观察结果的显著性。该框架可以预测未来的目标位置及其相关不确定性，这对于进一步辅助运动管理决策非常有价值。需要进一步研究，通过使用该框架的自适应版本来提高预测精度。
