Validation of the clinical applicability of knowledge‐based planning models in single‐isocenter volumetric‐modulated arc therapy for multiple brain metastases

Abstract

Purpose To validate the clinical applicability of knowledge‐based (KB) planning in single‐isocenter volumetric‐modulated arc therapy (VMAT) for multiple brain metastases using the k ‐fold cross‐validation (CV) method. Methods This study comprised 60 consecutive patients with multiple brain metastases treated with single‐isocenter VMAT (28 Gy in five fractions). The patients were divided randomly into five groups (Groups 1–5). The data of Groups 1–4 were used as the training and validation dataset and those of Group 5 were used as the testing dataset. Four KB models were created from three of the training and validation datasets and then applied to the remaining Groups as the fourfold CV phase. As the testing phase, the final KB model was applied to Group 5 and the dose distributions were calculated with a single optimization process. The dose‐volume indices (DVIs), modified Ian Paddick Conformity Index (mIPCI), modulation complexity scores for VMAT plans (MCSv), and the total number of monitor units (MUs) of the final KB plan were compared to those of the clinical plan (CL) using a paired Wilcoxon signed‐rank test. Results In the fourfold CV phase, no significant differences were observed in the DVIs among the four KB plans (KBPs). In the testing phase, the final KB plan was statistically equivalent to the CL, except for planning target volumes (PTVs) D 2% and D 50% . The differences between the CL and KBP in terms of the PTV D 99.5% , normal brain, and D max to all organs at risk (OARs) were not significant. The KBP achieved a lower total number of MUs and higher MCSv than the CL with no significant difference. Conclusions We demonstrated that a KB model in a single‐isocenter VMAT for multiple brain metastases was equivalent in dose distribution, MCSv, and total number of MUs to a CL with a single optimization.

Single isocenter stereotactic irradiation for multiple brain metastases: current situation and prospects

“…However, VMAT can decrease the irradiated dose of normal tissue as much as possible while maintaining conformity and a steep gradient using dose-intensity modulation and inverse-planning methods. Although VMAT plans can be manually generated by modifying the optimization objects for each lesion and index, knowledge-based planning (KBP) can help clinicians to generate SI-STI-MBM with VMAT plans [ 31 ]. In SI-STI-MBM with VMAT plans, inverse-planning methods and dose-intensity modulation can realize that all multiple targets are covered by the prescribed dose while maintaining high conformity, steep dose fall-off, and a high maximum dose for each site.…”

“…RapidPlan™ (Varian Medical Systems, Palo Alto, CA, USA) is a KBP product that utilizes a machine learning system to establish a model to predict dose-volume histograms. RapidPlan™ enables less-experienced physicians to easily create high-quality plans in a short time [ 31 , 32 ]. RapidPlan™ can be used to make SI-STI-MBM plans.…”

Machine learning for dose-volume histogram based clinical decision-making support system in radiation therapy plans for brain tumors

“…Data availability is a common problem in radiation therapy studies involving the application of ML. There are many papers where ML models are trained using <150 and as little as 11 patients 9,31,49,50 . A second limitation of this study is the simplified, binary classification of plans.…”

“…Knowledge-based planning (KBP) is a commonly studied application that leverages relevant features of previous, successfully delivered treatment plans in order to predict specific treatment planning parameters or the possible attainable dose-volume histograms (DVHs) 17,18 . KBP has been successfully used across various clinical sites such as head and neck 19,20 , prostate 21,22 , lung [23][24][25] , rectum 26,27 , breast 28,29 , pelvis 30 , and brain 31 .…”

Dosimetric potential of knowledge‐based planning model trained with HyperArc plans for brain metastases

“… 12 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 Several studies applying KBP to SRS for multiple brain metastases have also been reported. 19 , 21 However, the sparing performance of KBP model depends on the quality of library plans included in the model. 22 …”