Validating knowledge-based volumetric modulated arc therapy plans with a multi-institution model (broad model) using a complete open-loop dataset for prostate cancer

This study examined the characteristics of the broad model (KBP ) through a complete open-loop evaluation of volumetric modulated arc therapy (VMAT) plans for prostate cancer in 30 patients at two institutions. KBP , trained using 561 prostate cancer VMAT plans from five institutions with different treatment protocols, was shared with two institutions. The institutions were not involved in the creation of KBP . Plan created with KBP were compared with clinical plans (CPs) and plans created using a single-institution model at each institution (KBP ). KBP maintained the target coverage of CPs while meeting dose limits across varied settings at each institution. At institution X, KBP provided 40, 60, and 70 Gy (V , V , and V , respectively) to 30.8% ± 9.9%, 15.3% ± 8.5%, and 9.0% ± 6.4% of the volume at the rectal wall, respectively, which were significantly smaller than those provided by KBP and CPs. At institution Y, compared with CPs, KBP provided significantly greater V , V , dose to 2% of the volume (D ) at the rectum, and D at the bladder but significantly lower V and V at the bladder, in addition to superior dose homogeneity and conformality at the planning target volume. Our complete open-loop evaluation of VMAT plans for prostate cancer at two institutions demonstrated the clinical effectiveness of KBP at institutions producing plans with insufficient reductions in OAR doses. Thus, the quality of KBP plans is likely greater than that of KBP plans and CPs.