Influence of Cleaned-up Commercial Knowledge-Based Treatment Planning on Volumetric-Modulated Arc Therapy of Prostate Cancer.

Abstract

Purpose:This study aimed to investigate the influence of cleaned-up knowledge-based treatment planning (KBP) models on the plan quality for volumetric-modulated arc therapy (VMAT) of prostate cancer.Materials and Methods:Thirty prostate cancer VMAT plans were enrolled and evaluated according to four KBP modeling methods as follows: (1) model not cleaned – trained by fifty other clinical plans (KBPORIG); (2) cases cleaned by removing plans that did not meet all clinical goals of the dosimetric parameters, derived from dose–volume histogram (DVH) (KBPC-DVH); (3) cases cleaned outside the range of ±1 standard deviation through the principal component analysis regression plots (KBPC-REG); and (4) cases cleaned using both methods (2) and (3) (KBPC-ALL). Rectal and bladder structures in the training models numbered 34 and 48 for KBPC-DVH, 37 and 33 for KBPC-REG, and 26 and 33 for KBPC-ALL, respectively. The dosimetric parameters for each model with one-time auto-optimization were compared.Results:All KBP models improved target dose coverage and conformity and provided comparable sparing of organs at risks (rectal and bladder walls). There were no significant differences in plan quality among the KBP models. Nevertheless, only the KBPC-ALL model generated no cases of >1% V78 Gy (prescribed dose) to the rectal wall, whereas the KBPORIG, KBPC-DVH, and KBPC-REG models included two, four, and three cases, respectively, which were difficult to overcome with KBP because the planning target volume (PTV) and rectum regions overlapped.Conclusions:The cleaned-up KBP model based on DVH and regression plots improved plan quality in the PTV–rectum overlap region.