Cavinato Samuele, Bettinelli Andrea, Dusi Francesca, Fusella Marco, Germani Alessandra, Marturano Francesca, Paiusco Marta, Pivato Nicola, Rossato Marco Andrea, Scaggion Alessandro
Medical Physics Department, Veneto Institute of Oncology IOV-IRCCS, Padova, Italy.
Department of Physics and Astronomy 'G. Galilei', University of Padova, Padova, Italy.
Phys Imaging Radiat Oncol. 2023 Mar 28;26:100435. doi: 10.1016/j.phro.2023.100435. eCollection 2023 Apr.
Prediction models may be reliable decision-support tools to reduce the workload associated with the measurement-based patient-specific quality assurance (PSQA) of radiotherapy plans. This study compared the effectiveness of three different models based on delivery parameters, complexity metrics and sinogram radiomics features as tools for virtual-PSQA (vPSQA) of helical tomotherapy (HT) plans.
A dataset including 881 RT plans created with two different treatment planning systems (TPSs) was collected. Sixty-five indicators including 12 delivery parameters (DP) and 53 complexity metrics (CM) were extracted using a dedicated software library. Additionally, 174 radiomics features (RF) were extracted from the plans' sinograms. Three groups of variables were formed: A (DP), B (DP + CM) and C (DP + CM + RF). Regression models were trained to predict the gamma index passing rate (3%G, 2mm) and the impact of each group of variables was investigated. ROC-AUC analysis measured the ability of the models to accurately discriminate between 'deliverable' and 'non-deliverable' plans.
The best performance was achieved by model C which allowed detecting around 16% and 63% of the 'deliverable' plans with 100% sensitivity for the two TPSs, respectively. In a real clinical scenario, this would have decreased the whole PSQA workload by approximately 35%.
The combination of delivery parameters, complexity metrics and sinogram radiomics features allows for robust and reliable PSQA gamma passing rate predictions and high-sensitivity detection of a fraction of deliverable plans for one of the two TPSs. Promising yet improvable results were obtained for the other one. The results foster a future adoption of vPSQA programs for HT.
预测模型可能是可靠的决策支持工具，可减少与基于测量的放射治疗计划患者特异性质量保证（PSQA）相关的工作量。本研究比较了基于交付参数、复杂性指标和正弦图放射组学特征的三种不同模型作为螺旋断层放疗（HT）计划虚拟PSQA（vPSQA）工具的有效性。
收集了一个包含使用两种不同治疗计划系统（TPS）创建的881个放疗计划的数据集。使用专用软件库提取了65个指标，包括12个交付参数（DP）和53个复杂性指标（CM）。此外，从计划的正弦图中提取了174个放射组学特征（RF）。形成了三组变量：A（DP）、B（DP + CM）和C（DP + CM + RF）。训练回归模型以预测伽马指数通过率（3%G，2mm），并研究每组变量的影响。ROC-AUC分析测量了模型准确区分“可交付”和“不可交付”计划的能力。
模型C表现最佳，对于两种TPS，分别以100%的灵敏度检测到约16%和63%的“可交付”计划。在实际临床场景中，这将使整个PSQA工作量减少约35%。
交付参数、复杂性指标和正弦图放射组学特征的组合能够对PSQA伽马通过率进行稳健可靠的预测，并对两种TPS之一的一部分可交付计划进行高灵敏度检测。对于另一种TPS，虽然取得了有前景但仍有待改进的结果。这些结果促进了未来HT的vPSQA计划的采用。
