Knowledge-based planning using pseudo-structures for volumetric modulated arc therapy (VMAT) of postoperative uterine cervical cancer: a multi-institutional study

Abstract Background: The aim of this study was to investigate the performance of the RapidPlan knowledge-based treatment planning system using models including registered pseudo-structures, and to determine how many structures are required for automatic optimization of volumetric modulated arc therapy (VMAT) for postoperative uterine cervical cancer. Methods: Pseudo-structures were retrospectively contoured for patients who had completed treatment at one of five institutions. For 22 patients, RPs were generated with a single optimization for models with two (RP_2), four (RP_4), or five (RP_5) registered structures, and the dosimetric parameters of these models were compared with a clinical plan with several optimizations. The total times for pseudo-structure creation and optimization were also measured.Results: Most dosimetric parameters showed no major differences between each RP. In particular, the rectum Dmax, V50Gy, and V40Gy with RP_2, RP_4, and RP_5 were not significantly different, and were lower than those of the clinical plan. In addition, the average proportions of plans achieving acceptable criteria for all dosimetric parameters were 98%, 99%, 98%, and 98% for the clinical plan, RP_2, RP_4, and RP_5, respectively. The average times for the creation and optimization of pseudo-structures were 105, 17, 21, and 29 minutes, for the clinical plan, RP_2, RP_4, and RP_5, respectively. Conclusions: The RapidPlan model with two registered pseudo-structures could generate clinically acceptable plans while saving time. This modeling approach using pseudo-structures could possibility be used for the VMAT planning process.

Download Full-text

Evaluation of a highly refined prediction model in knowledge-based volumetric modulated arc therapy planning for cervical cancer

Radiation Oncology ◽

10.1186/s13014-021-01783-9 ◽

2021 ◽

Vol 16 (1) ◽

Author(s):

Mingli Wang ◽

Huikuan Gu ◽

Jiang Hu ◽

Jian Liang ◽

Sisi Xu ◽

...

Keyword(s):

Cervical Cancer ◽

Prediction Model ◽

Volumetric Modulated Arc Therapy ◽

Model Evolution ◽

Prediction Ability ◽

Knowledge Based ◽

Proposed Model ◽

Arc Therapy ◽

Knowledge Based Planning

Abstract Background and purpose To explore whether a highly refined dose volume histograms (DVH) prediction model can improve the accuracy and reliability of knowledge-based volumetric modulated arc therapy (VMAT) planning for cervical cancer. Methods and materials The proposed model underwent repeated refining through progressive training until the training samples increased from initial 25 prior plans up to 100 cases. The estimated DVHs derived from the prediction models of different runs of training were compared in 35 new cervical cancer patients to analyze the effect of such an interactive plan and model evolution method. The reliability and efficiency of knowledge-based planning (KBP) using this highly refined model in improving the consistency and quality of the VMAT plans were also evaluated. Results The prediction ability was reinforced with the increased number of refinements in terms of normal tissue sparing. With enhanced prediction accuracy, more than 60% of automatic plan-6 (AP-6) plans (22/35) can be directly approved for clinical treatment without any manual revision. The plan quality scores for clinically approved plans (CPs) and manual plans (MPs) were on average 89.02 ± 4.83 and 86.48 ± 3.92 (p < 0.001). Knowledge-based planning significantly reduced the Dmean and V18 Gy for kidney (L/R), the Dmean, V30 Gy, and V40 Gy for bladder, rectum, and femoral head (L/R). Conclusion The proposed model evolution method provides a practical way for the KBP to enhance its prediction ability with minimal human intervene. This highly refined prediction model can better guide KBP in improving the consistency and quality of the VMAT plans.

Download Full-text