Departament de Dosimetria i Física Mèdica, Institut de Tècniques Energètiques, Universitat Politècnica de Catalunya, 08028 Barcelona, Spain.
Med Phys. 2013 Aug;40(8):081704. doi: 10.1118/1.4812682.
In proton therapy, complex density heterogeneities within the beam path constitute a challenge to dose calculation algorithms. This might question the reliability of dose distributions predicted by treatment planning systems based on analytical dose calculation. For cases in which substantial dose errors are expected, resorting to Monte Carlo dose calculations might be essential to ensure a successful treatment outcome and therefore the benefit is worth a presumably long computation time. The aim of this study was to define an indicator for the accuracy of dose delivery based on analytical dose calculations in treatment planning systems for small proton therapy fields to identify those patients for which Monte Carlo dose calculation is warranted.
Fourteen patients treated at our facility with small passively scattered proton beams (apertures diameters below 7 cm) were selected. Plans were generated in the XiO treatment planning system in combination with a pencil beam algorithm developed at the Massachusetts General Hospital and compared to Monte Carlo dose calculations. Differences in the dose to the 50% of the gross tumor volume (D50, GTV) were assessed in a field-by-field basis. A simple and fast methodology was developed to quantify the inhomogeneity of the tissue traversed by a single small proton beam using a heterogeneity index (HI)-a concept presented by Plugfelder et al. [Med. Phys. 34, 1506-1513 (2007)] for scanned proton beams. Finally, the potential correlation between the error made by the pencil beam based treatment planning algorithm for each field and the level of tissue heterogeneity traversed by the proton beam given by the HI was evaluated.
Discrepancies up to 5.4% were found in D50 for single fields, although dose differences were within clinical tolerance levels (<3%) when combining all of the fields involved in the treatment. The discrepancies found for each field exhibited a strong correlation to their associated HI-values (Spearman's ρ=0.8, p<0.0001); the higher the level of tissue inhomogeneities for a particular field, the larger the error by the analytical algorithm. With the established correlation a threshold for HI can be set by choosing a tolerance level of 2-3%-commonly accepted in radiotherapy.
The HI is a good indicator for the accuracy of proton field delivery in terms of GTV prescription dose coverage when small fields are delivered. Each HI-value was obtained from the CT image in less than 3 min on a computer with 2 GHz CPU allowing implementation of this methodology in clinical routine. For HI-values exceeding the threshold, either a change in beam direction (if feasible) or a recalculation of the dose with Monte Carlo would be highly recommended.
在质子治疗中，射束路径内的复杂密度不均匀性对剂量计算算法构成了挑战。这可能会对基于解析剂量计算的治疗计划系统预测的剂量分布的可靠性提出质疑。对于预计会出现大量剂量误差的情况，为确保成功的治疗效果并因此受益，采用蒙特卡罗剂量计算可能是必要的，而计算时间可能会相应延长。本研究的目的是定义一个指标，用于根据小质子治疗野的治疗计划系统中的解析剂量计算来评估剂量传递的准确性，以确定哪些患者需要进行蒙特卡罗剂量计算。
选择了在我院接受小散射质子束治疗的 14 名患者（孔径直径小于 7cm）。在 XiO 治疗计划系统中生成计划，并结合马萨诸塞州综合医院开发的铅笔束算法进行比较，并与蒙特卡罗剂量计算进行比较。基于场的方法评估了肿瘤 50%体积（D50，GTV）处剂量的差异。开发了一种简单快速的方法，使用不均匀性指数（HI）来量化单个小质子束穿过的组织的不均匀性，这是 Plugfelder 等人提出的概念。[Med. Phys. 34, 1506-1513 (2007)]用于扫描质子束。最后，评估了铅笔束治疗计划算法对每个射野的误差与 HI 给出的质子束穿过的组织不均匀性水平之间的潜在相关性。
对于单个射野，发现 D50 差异高达 5.4%，但当组合治疗中涉及的所有射野时，剂量差异处于临床可接受水平（<3%）。对于每个射野发现的差异与它们各自的 HI 值呈强烈相关性（Spearman's ρ=0.8，p<0.0001）；对于特定射野，组织不均匀性水平越高，解析算法的误差越大。通过建立相关性，可以通过选择 2-3%的容限水平来设置 HI 的阈值-放射治疗中通常接受的容限水平。
当使用小射野时，HI 是评估 GTV 处方剂量覆盖的质子射野传递准确性的一个很好的指标。每个 HI 值都是在具有 2GHz CPU 的计算机上从 CT 图像中获得的，耗时不到 3 分钟，允许在临床常规中实施这种方法。对于超过阈值的 HI 值，强烈建议改变射束方向（如果可行）或使用蒙特卡罗重新计算剂量。
