Background
Quality assurance (QA) of clinical trial radiation therapy (RT) treatment and planning is essential to ensure protocol compliance and trial quality. Knowledge based planning (KBP) uses machine learning to generate a knowledge based dose-volume histogram (DVH) estimation model. The TROG 18.01 NINJA trial aims to compare two emerging schedules of RT in the treatment of intermediate/high-risk prostate cancer. A novel approach to plan quality assessment was implemented, using KBP (Varian RapidPlan), in addition to standard RT QA peer review processes.
Aim
Assess the impact and feasibility of prospective plan quality feedback using KBP for the NINJA trial.
Methods
Across 271 patients recruited, 100 (37%) underwent pre-treatment (real-time) KBP feedback and 76 (28%) were retrospectively analysed. A feedback report comparing the KBP generated DVH versus the initial plan was collated using a customised script (ClearCheck software) and sent to sites within 24 hours. Centres were asked to review the report and decide whether they would amend their clinical plan. Protocol compliance was assessed including dose constraints for the rectum, bladder, urethra, penile bulb, femoral heads, sigmoid and small bowel.
Results
High plan quality was observed, with only 3 (3%) clinical plans amended following KBP feedback. There was a high level of agreement between the KBP generated plan and the clinical plan. Of the organ at risk (OAR) parameters assessed, 56% demonstrated no difference between the KBP and the clinical DVH, 24% showed the clinical plan could be improved and in 20% the submitted plan was better (Table A).
Table A: Total Cases KBP versus Clinical
Conclusion
The use of KBP real-time plan quality feedback was successfully implemented for the NINJA trial. This novel approach provided a valuable plan quality benchmark in which to assess the clinical plan.