Automatic VMAT planning for post-operative prostate cancer cases using particle swarm optimization: A proof of concept study

Abstract

To investigate the potential of Particle Swarm Optimization (PSO) for fully automatic VMAT radiotherapy (RT) treatment planning. Material and Methods: In PSO a solution space of planning constraints is searched for the best possible RT plan in an iterative, statistical method, optimizing a population of candidate solutions. To identify the best candidate solution and for final evaluation a plan quality score (PQS), based on dose volume histogram (DVH) parameters, was introduced. Automatic PSO-based RT planning was used for N = 10 postoperative prostate cancer cases, retrospectively taken from our clinical database, with a prescribed dose of EUD = 66 Gy in addition to two constraints for rectum and one for bladder. Resulting PSO-based plans were compared dosimetrically to manually generated VMAT plans. Results: PSO successfully proposed treatment plans comparable to manually optimized ones in 9/10 cases. The median (range) PTV EUD was 65.4 Gy (64.7-66.0) for manual and 65.3 Gy (62.5-65.5) for PSO plans, respectively. However PSO plans achieved significantly lower doses in rectum D 2% 67.0 Gy (66.5-67.5) vs. 66.1 Gy (64.7-66.5, p = 0.016). All other evaluated parameters (PTV D 98% and D 2% , rectum V 40Gy and V 60Gy , bladder D 2% and V 60Gy) were comparable in both plans. Manual plans had lower PQS compared to PSO plans with −0.82 (−16.43-1.08) vs. 0.91 (−5.98-6.25). Conclusion: PSO allows for fully automatic generation of VMAT plans with plan quality comparable to manually optimized plans. However, before clinical implementation further research is needed concerning further adaptation of PSO-specific parameters and the refinement of the PQS.

Full automation of spinal stereotactic radiosurgery and stereotactic body radiation therapy treatment planning using Varian Eclipse scripting

“…Automated and semiautomated treatment planning approaches have the potential to produce high-quality clinical plans while reducing the time spent on treatment optimization, allowing for unsupervised optimization and calculation, therefore decreasing the planning time. Exploratory demonstrations in head and neck, 33 breast, 34,35 and other sites [36][37][38] have produced results comparable to corresponding clinical plans. However, most studies focused on optimization approaches alone, which does not account for the complete treatment planning process.…”

“…Automatic treatment planning is a topic of increased interest for different sites to reduce treatment planning times and increase robustness and standardization. 33,[36][37][38] However, most studies have focused on plan optimization, using either knowledge-based techniques, automatic iterative optimization, or multicriteria optimization approaches. In this study, we have included scripting into our planning approach to automate the process of treatment planning after normal structure and target contouring.…”

“…In addition, there is not a clear consensus as to which fractionation scheme should be employed for spine SRS treatments, 32 and, in general, it would be very time consuming to create several plans manually for different fractionation schemes. Automatic treatment planning is a topic of increased interest for different sites to reduce treatment planning times and increase robustness and standardization 33,36–38 . However, most studies have focused on plan optimization, using either knowledge‐based techniques, automatic iterative optimization, or multicriteria optimization approaches.…”

First experience of autonomous, un-supervised treatment planning integrated in adaptive MR-guided radiotherapy and delivered to a patient with prostate cancer

“…Automatic planning was carried out using particle swarm optimization (PSO), a statistical optimization method, described earlier by Künzel et al [24]. PSO started directly after automatic structure generation (Fig.…”

“…Consequently, evaluation of plan quality is essential for automatic planning. Here, a plan quality score (PQS) adapted from Künzel et al [24] was used. It was based on the dose volume histogram (DVH)-parameters according to our institutional standard operating procedure for plan acceptance (Table 1).…”