Effects of model size and composition on quality of head‐and‐neck knowledge‐based plans

Abstract

Purpose

Knowledge‐based planning (KBP) aims to automate and standardize treatment planning. New KBP users are faced with many questions: How much does model size matter, and are multiple models needed to accommodate specific physician preferences? In this study, six head‐and‐neck KBP models were trained to address these questions.

Methods

The six models differed in training size and plan composition: The KBP _Full ( n = 203 plans), KBP ₁₀₁ ( n = 101), KBP ₅₀ ( n = 50), and KBP ₂₅ ( n = 25) were trained with plans from two head‐and‐neck physicians. KBP _A and KBP _B each contained n = 101 plans from only one physician, respectively. An independent set of 39 patients treated to 6000–7000 cGy by a third physician was re‐planned with all KBP models for validation. Standard head‐and‐neck dosimetric parameters were used to compare resulting plans. KBP _Full plans were compared to the clinical plans to evaluate overall model quality. Additionally, clinical and KBP _Full plans were presented to another physician for blind review. Dosimetric comparison of KBP _Full against KBP ₁₀₁ , KBP ₅₀ , and KBP ₂₅ investigated the effect of model size. Finally, KBP _A versus KBP _B tested whether training KBP models on plans from one physician only influences the resulting output. Dosimetric differences were tested for significance using a paired t‐test ( p < 0.05).

Results

Compared to manual plans, KBP _Full significantly increased PTV Low D95% and left parotid mean dose but decreased dose cochlea, constrictors, and larynx. The physician preferred the KBP _Full plan over the manual plan in 20/39 cases. Dosimetric differences between KBP _Full , KBP ₁₀₁ , KBP ₅₀ , and KBP ₂₅ plans did not exceed 187 cGy on aggregate, except for the cochlea. Further, average differences between KBP _A and KBP _B were below 110 cGy.

Conclusions

Overall, all models were shown to produce high‐quality plans. Differences between model outputs were small compared to the prescription. This indicates only small improvements when increasing model size and minimal influence of the physician when choosing treatment plans for training head‐and‐neck KBP models.