Fast VMAT planning for prostate radiotherapy: dosimetric validation of a deep learning-based initial segment generation method

Objective. To develop and evaluate a deep learning based fast volumetric modulated arc therapy (VMAT) plan generation method for prostate radiotherapy. Approach. A customized 3D U-Net was trained and validated to predict initial segments at 90 evenly distributed control points of an arc, linked to our research treatment planning system (TPS) for segment shape optimization (SSO) and segment weight optimization (SWO). For 27 test patients, the VMAT plans generated based on the deep learning prediction (VMAT(DL)) were compared with VMAT plans generated with a previously validated automated treatment planning method (VMAT(ref)). For all test cases, the deep learning prediction accuracy, plan dosimetric quality, and the planning efficiency were quantified and analyzed. Main results. For all 27 test cases, the resulting plans were clinically acceptable. The V (95%) for the PTV2 was greater than 99%, and the V (107%) was below 0.2%. Statistically significant difference in target coverage was not observed between the VMAT(ref) and VMAT(DL) plans (P = 0.3243 > 0.05). The dose sparing effect to the OARs between the two groups of plans was similar. Small differences were only observed for the Dmean of rectum and anus. Compared to the VMAT(ref), the VMAT(DL) reduced 29.3% of the optimization time on average. Significance. A fully automated VMAT plan generation method may result in significant improvement in prostate treatment planning efficiency. Due to the clinically acceptable dosimetric quality and high efficiency, it could potentially be used for clinical planning application and real-time adaptive therapy application after further validation.

Automated summary

This study developed and evaluated a deep learning based fast volumetric modulated arc therapy (VMAT) plan generation method. The results showed that the VMAT plans generated based on the deep learning prediction had no significant difference compared to the plans generated with a previously validated automated treatment planning method. Moreover, the deep learning prediction method reduced the optimization time by 29.3%.