A practical method to quantify knowledge-based DVH prediction accuracy and uncertainty with reference cohorts.
A practical method to quantify knowledge-based DVH prediction accuracy and uncertainty with reference cohorts.
复制标题
一种实用方法，可以用参考人群量化基于知识的DVH预测准确性和不确定性。
DOI：
10.1002/acm2.13199
复制
发表时间：
2021-03
影响因子：
2.1
通讯作者：
Moore KL
中科院分区：
文献类型：
--
作者：
Covele BM;Carroll CJ;Moore KL
采用基于知识的剂量体积直方图（DVH）预测模型评估放射治疗中的危及器官（OAR）保留需要量化预测准确性和不确定性。此外，DVH预测误差带应该容易解释为置信区间，在其中找到临床可接受的DVH的百分比。在这种DVH误差带不可用的情况下，我们使用高质量治疗计划的本地参考队列提出了一种独立的误差量化方法，并将其应用于两个DVH预测模型，ORBIT-RT和RapidPlan，在同一组90个体积调制弧治疗（VMAT）计划上训练。然后，针对一组单独的45个前列腺VMAT计划，生成每个模型的风险器官DVH预测。然后将剂量体积直方图预测与其类似的临床DVH进行比较，以定义预测误差（ith计划），由此可以计算队列的预测偏倚μ、预测误差变化σ和均方根误差。然后将经验与模型提供的DVH误差估计进行对比。对于所有前列腺OAR，超过50% Rx剂量，ORBIT-RT μ和σ与RapidPlan相当或更低。两种模型的Rx剂量高于80%时，μ < 1%，σ < 3 - 4%。因此，当Rx剂量高于50%时，ORBIT-RT低于RapidPlan，表明该队列的准确性略有提高。因为μ ε 0很容易解释为典型标准差σ，其误差带预计可正确预测68%的正态分布临床DVH。相比之下，RapidPlan提供的误差带，尽管在文献中描述为标准差范围，但预测性略低于（55-70%成功率），而提供的ORBIT-RT误差带被证实类似于所述的四分位数范围（40-65%成功率）。临床医生可以使用他们自己机构的参考队列应用该方法，以（a）独立评估基于知识的模型对局部治疗计划的预测准确性，以及（B）从任何误差带解释是否可能实现进一步的OAR剂量节省。
The adoption of knowledge‐based dose‐volume histogram (DVH) prediction models for assessing organ‐at‐risk (OAR) sparing in radiotherapy necessitates quantification of prediction accuracy and uncertainty. Moreover, DVH prediction error bands should be readily interpretable as confidence intervals in which to find a percentage of clinically acceptable DVHs. In the event such DVH error bands are not available, we present an independent error quantification methodology using a local reference cohort of high‐quality treatment plans, and apply it to two DVH prediction models, ORBIT‐RT and RapidPlan, trained on the same set of 90 volumetric modulated arc therapy (VMAT) plans. Organ‐at‐risk DVH predictions from each model were then generated for a separate set of 45 prostate VMAT plans. Dose‐volume histogram predictions were then compared to their analogous clinical DVHs to define prediction errors (ith plan), from which prediction bias μ, prediction error variation σ, and root‐mean‐square error could be calculated for the cohort. The empirical was then contrasted to the model‐provided DVH error estimates. For all prostate OARs, above 50% Rx dose, ORBIT‐RT μ and σ were comparable to or less than those of RapidPlan. Above 80% Rx dose, μ < 1% and σ < 3‐4% for both models. As a result, above 50% Rx dose, ORBIT‐RT was below that of RapidPlan, indicating slightly improved accuracy in this cohort. Because μ ≈ 0, is readily interpretable as a canonical standard deviation σ, whose error band is expected to correctly predict 68% of normally distributed clinical DVHs. By contrast, RapidPlan's provided error band, although described in literature as a standard deviation range, was slightly less predictive than (55–70% success), while the provided ORBIT‐RT error band was confirmed to resemble an interquartile range (40–65% success) as described. Clinicians can apply this methodology using their own institutions’ reference cohorts to (a) independently assess a knowledge‐based model's predictive accuracy of local treatment plans, and (b) interpret from any error band whether further OAR dose sparing is likely attainable.
登录
查看更多内容
影响因子：
3.8
作者：
Appenzoller, Lindsey M.;Michalski, Jeff M.;Moore, Kevin L.
通讯作者：
Moore, Kevin L.
影响因子：
3.3
作者：
Kaderka, Robert;Mundt, Robert C.;Moore, Kevin L.
通讯作者：
Moore, Kevin L.
影响因子：
4.2
作者：
Covele, Brent M.;Puri, Kartikeya S.;Moore, Kevin L.
通讯作者：
Moore, Kevin L.
影响因子：
3.8
作者：
Moore, Kevin L.;Kagadis, George C.;Mutic, Sasa
通讯作者：
Mutic, Sasa
DOI：
10.1016/j.ijrobp.2015.01.046
发表时间：
2015-06-01
影响因子：
7
作者：
Moore, Kevin L.;Schmidt, Rachel;Moiseenko, Vitali;Olsen, Lindsey A.;Tan, Jun;Xiao, Ying;Galvin, James;Pugh, Stephanie;Seider, Michael J.;Dicker, Adam P.;Bosch, Walter;Michalski, Jeff;Mutic, Sasa
通讯作者：
Mutic, Sasa