Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Use of knowledge based DVH predictions to enhance automated re-planning strategies in head and neck adaptive radiotherapy

Cagni, Elisabetta, Botti, Andrea, Chendi, Agnese, Iori, Mauro and Spezi, Emiliano 2021. Use of knowledge based DVH predictions to enhance automated re-planning strategies in head and neck adaptive radiotherapy. Physics in Medicine and Biology 66 (13) , 135004. 10.1088/1361-6560/ac08b0

[thumbnail of Spezi E - Use of knowledge based DVH ....pdf]
PDF - Accepted Post-Print Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (2MB) | Preview


This study aimed to investigate if a commercial, knowledge-based tool for radiotherapy planning could be used to estimate potential organs at risk (OARs), which would spare the re-planning strategy for adaptive radiotherapy (ART). Sixty-four head and neck (HN) VMAT Pareto plans from our institute's database were used to train a knowledge-based planning (KBP) model. An evaluation set of 10 HN patients was randomly selected. For each patient in the evaluation set, the planning computed tomography (CT) and 2 sets of on-board cone-beam CT (CBCT), corresponding to the 16th and the 26th radiotherapy treatment fraction, were extracted. The original plan was re-calculated on a daily deformed CT (delivered DVH) and compared with the KBP DVH predictions and with the final KBP DVH after optimisation of the plan, which was performed on the same image sets. To evaluate the feasibility of this method, the range of KBP DVH estimation uncertainties were compared with the gains obtained from re-planning. DVH differences and ROC curve analysis were used for this purpose. On average, KBP uncertainties shared the same order of magnitude as the gain in re-planning. However, statistical tests confirmed significant differences between the two groups (p=0.02). There were statistically significant differences between the predicted and true values (after optimisation) (p<0.01). Overall, for 48% of cases, KBP predicted a desirable outcome from re-planning, and the final dose confirmed an effective gain in 67% of cases. We established a systematic workflow to identify effective OAR sparing in re-planning based on KBP predictions that can be implemented in an on-line, adaptive radiotherapy process. However, inaccuracies in KBP predictions were observed even when Pareto optimal plans were used for model training, which should be the subject of further investigations.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Engineering
Publisher: IOP Publishing
ISSN: 0031-9155
Date of First Compliant Deposit: 17 June 2021
Date of Acceptance: 7 June 2021
Last Modified: 28 Sep 2022 08:11

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics