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

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.

The six models differed in training size and plan composition: The KBP_Full (n = 203 plans), KBP₁₀₁ (n = 101), KBP₅₀ (n = 50), and KBP₂₅ (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 KBP₁₀₁ , KBP₅₀ , and KBP₂₅ 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).

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 , KBP₁₀₁ , KBP₅₀ , and KBP₂₅ 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.

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.