Evaluating and comparing algorithms for respiratory motion prediction
Evaluating and comparing algorithms for respiratory motion prediction
复制标题
DOI：
10.1088/0031-9155/58/11/3911
复制
发表时间：
2013-06-07
影响因子：
3.5
通讯作者：
Schweikard, A.
中科院分区：
文献类型：
--
作者：
Ernst, F.;Duerichen, R.;Schweikard, A.
在机器人放射外科手术中，有必要补偿由目标跟踪和机械约束引起的系统延迟。这种补偿通常通过计算未来目标位置的算法来实现。在大多数有关呼吸运动预测的科学著作中，仅在有限数量的非常短的运动轨迹上评估一两种算法。这项工作的目的是通过对前所未有的数据量评估许多算法，更深入地了解呼吸运动预测方法的现实世界功能。我们在包含 304 个呼吸运动轨迹的广泛数据库上评估了六种算法，即归一化最小均方 (nLMS)、递归最小二乘 (RLS)、多步线性方法 (MULIN)、基于小波的多尺度自回归 (wLMS)、扩展卡尔曼滤波和 epsilon 支持向量回归 (SVRpred) 方法。这些痕迹是在使用 CyberKnife（Accuray, Inc., Sunnyvale, CA, USA）治疗期间收集的，平均长度为 71 分钟。评估是使用图形预测工具包完成的，该工具包可供公众使用，我们使用的数据也是如此。实验表明，nLMS 算法（CyberKnife 目前使用的算法之一）的性能优于所有其他方法。对于性能更好的 wLMS、SVRpred 和 MULIN 算法来说尤其如此。 nLMS 算法仅在 38% 的测试用例中产生 75% 或更低的相对均方根 (RMS) 误差（即，与不进行预测相比，误差降低 25% 或更多），而 MULIN 和 SVRpred 方法在超过 77% 的测试用例中达到此水平，wLMS 算法在超过 84% 的测试用例中达到此水平。我们的工作表明，wLMS 算法是最准确的算法，并且不需要参数调整，使其成为临床实施的理想候选者。此外，我们还发现患者呼吸运动轨迹的结构对预测结果有很大影响。需要进一步的工作来先验地确定个体呼吸行为对运动预测的适用性。
In robotic radiosurgery, it is necessary to compensate for systematic latencies arising from target tracking and mechanical constraints. This compensation is usually achieved by means of an algorithm which computes the future target position. In most scientific works on respiratory motion prediction, only one or two algorithms are evaluated on a limited amount of very short motion traces. The purpose of this work is to gain more insight into the real world capabilities of respiratory motion prediction methods by evaluating many algorithms on an unprecedented amount of data. We have evaluated six algorithms, the normalized least mean squares (nLMS), recursive least squares (RLS), multi-step linear methods (MULIN), wavelet-based multiscale autoregression (wLMS), extended Kalman filtering, and epsilon-support vector regression (SVRpred) methods, on an extensive database of 304 respiratory motion traces. The traces were collected during treatment with the CyberKnife (Accuray, Inc., Sunnyvale, CA, USA) and feature an average length of 71 min. Evaluation was done using a graphical prediction toolkit, which is available to the general public, as is the data we used. The experiments show that the nLMS algorithm-which is one of the algorithms currently used in the CyberKnife-is outperformed by all other methods. This is especially true in the case of the wLMS, the SVRpred, and the MULIN algorithms, which perform much better. The nLMS algorithm produces a relative root mean square (RMS) error of 75% or less (i.e., a reduction in error of 25% or more when compared to not doing prediction) in only 38% of the test cases, whereas the MULIN and SVRpred methods reach this level in more than 77%, the wLMS algorithm in more than 84% of the test cases. Our work shows that the wLMS algorithm is the most accurate algorithm and does not require parameter tuning, making it an ideal candidate for clinical implementation. Additionally, we have seen that the structure of a patient's respiratory motion trace has strong influence on the outcome of prediction. Further work is needed to determine a priori the suitability of an individual's respiratory behaviour to motion prediction.