Plan evaluation is a key step in the radiotherapy treatment workflow. Central to this step is the assessment of treatment plan quality. Hence, it is important to agree on what we mean by plan quality and to be fully aware of which parameters it depends on. We understand plan quality in radiotherapy as the clinical suitability of the delivered dose distribution that can be realistically expected from a treatment plan. Plan quality is commonly assessed by evaluating the dose distribution calculated by the treatment planning system (TPS). Evaluating the 3D dose distribution is not easy, however; it is hard to fully evaluate its spatial characteristics and we still lack the knowledge for personalising the prediction of the clinical outcome based on individual patient characteristics. This advocates for standardisation and systematic collection of clinical data and outcomes after radiotherapy. Additionally, the calculated dose distribution is not exactly the dose delivered to the patient due to uncertainties in the dose calculation and the treatment delivery, including variations in the patient set-up and anatomy. Consequently, plan quality also depends on the robustness and complexity of the treatment plan. We believe that future work and consensus on the best metrics for quality indices are required. Better tools are needed in TPSs for the evaluation of dose distributions, for the robust evaluation and optimisation of treatment plans, and for controlling and reporting plan complexity. Implementation of such tools and a better understanding of these concepts will facilitate the handling of these characteristics in clinical practice and be helpful to increase the overall quality of treatment plans in radiotherapy.
Purpose
The dosimetric accuracies of volumetric modulated arc therapy (VMAT) plans were predicted using plan complexity parameters via machine learning.
Methods
The dataset consisted of 600 cases of clinical VMAT plans from a single institution. The predictor variables (n = 28) for each plan included complexity parameters, machine type, and photon beam energy. Dosimetric measurements were performed using a helical diode array (ArcCHECK), and the dosimetric accuracy of the passing rates for a 5% dose difference (DD5%) and gamma index of 3%/3 mm (γ3%/3 mm) were predicted using three machine learning models: regression tree analysis (RTA), multiple regression analysis (MRA), and neural networks (NNs). First, the prediction models were applied to 500 cases of the VMAT plans. Then, the dosimetric accuracy was predicted using each model for the remaining 100 cases (evaluation dataset). The error between the predicted and measured passing rates was evaluated.
Results
For the 600 cases, the mean ± standard deviation of the measured passing rates was 92.3% ± 9.1% and 96.8% ± 3.1% for DD5% and γ3%/3 mm, respectively. For the evaluation dataset, the mean ± standard deviation of the prediction errors for DD5% and γ3%/3 mm was 0.5% ± 3.0% and 0.6% ± 2.4% for RTA, 0.0% ± 2.9% and 0.5% ± 2.4% for MRA, and –0.2% ± 2.7% and –0.2% ± 2.1% for NN, respectively.
Conclusions
NNs performed slightly better than RTA and MRA in terms of prediction error. These findings may contribute to increasing the efficiency of patient‐specific quality‐assurance procedures.
Positional tracking errors correlated strongly with 4D-modeling errors in IR tracking. Thus, the accuracy of the 4D model must be verified before treatment, and margins are required to compensate for the 4D-modeling error.
Application of IR Tracking substantially reduced the geometric error caused by respiratory motion; however, an intrafractional error due to baseline drift of >3 mm was occasionally observed. To compensate for EBD, the authors recommend checking the target and IR marker positions constantly and updating the 4D model several times during a treatment session.
The intrafractional variations differed according to the amount of tumour motion and the tumour-marker distance. Additionally, interfractional variations of up to 2.5mm were observed. Thus, a corresponding margin should be considered during implanted marker-based beam delivery to account for these variations.
Prediction errors were the primary cause of overall targeting errors, whereas mechanical errors were negligible. Furthermore, improvement of the prediction accuracy could be achieved by correcting systematic prediction errors in the previous field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.