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

Autor: Kaderka R; Department of Radiation Oncology, University of Miami Miller School of Medicine, Miami, Florida, USA., Dogan N; Department of Radiation Oncology, University of Miami Miller School of Medicine, Miami, Florida, USA., Jin W; Department of Radiation Oncology, University of Miami Miller School of Medicine, Miami, Florida, USA., Bossart E; Department of Radiation Oncology, University of Miami Miller School of Medicine, Miami, Florida, USA.
Jazyk: angličtina
Zdroj: Journal of applied clinical medical physics [J Appl Clin Med Phys] 2024 Feb; Vol. 25 (2), pp. e14168. Date of Electronic Publication: 2023 Oct 05.
DOI: 10.1002/acm2.14168
Abstrakt: 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.
(© 2023 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.)
Databáze: MEDLINE
Externí odkaz: