Use of a constrained hierarchical optimization dataset enhances knowledge-based planning as a quality assurance tool...

To investigate whether building a knowledge-based planning (KBP) model with prostate bed plans constructed from constrained hierarchical optimization (CHO) would result in more efficient model construction with more consistent output than a model built using plans from a traditional, trial-and-error-based optimization (TEO) technique.

Three KBP models were constructed from plans from subsets of 58 post-prostatectomy patients treated with intensity-modulated radiation therapy. TEO₅₄ was built from 54 TEO plans, selected to represent typical clinical variations in target and organ-at-risk sizes and shapes. CHO₃₀ and TEO₃₀ were built from the same 30 patients populated with CHO and TEO plans, respectively. The three models were each applied to a new set of 18 patient scans and dose-volume histogram estimates (DVHEs) were generated for rectal and bladder walls and compared for each patient.

CHO₃₀ resulted in a significantly tighter range in DVHEs (P < 0.01) for both the rectal and bladder walls compared with either of the TEO models, indicating less uncertainty in the dose estimation. Plans resulting from KBP optimization using each model were very similar.

Populating a KBP model with CHO data resulted in a high quality model. Since CHO plans can be generated automatically offline in a process that necessitates little to no user interaction, a CHO-KBP model can quickly adapt to changes in plan evaluation criteria or planning techniques without the need to wait to accrue sufficient numbers of clinical TEO plans. This may facilitate the use of KBP approaches for initial or ongoing quality assurance procedures and plan quality audits.