ESTRO 2024 - Abstract Book

S2890

Interdiscplinary - Other

ESTRO 2024

rest reporting some minor intervention, particularly around import/export between contouring and planning. Commercial auto-contouring solutions were used by 11 participants, while commercial auto-planning was used by 9 of them. 8 of the entries used commercial systems for both. 69% (9) reported visually checking the results prior to submission to the challenge website.

Conclusion:

For routine prostate cases, full automation of radiotherapy treatment planning from simulation CT to treatment plan was possible. Such a fully automated approach would require a reconsideration of the risks, their mitigations, and what quality assurance is appropriate. It is notable that although no patients were to be treated with the submitted plans, many of the participants still felt the need to visually check their entry prior to submission, perhaps suggesting a lack of confidence in full automation at this time. While full automation is a technical possibility, it does not necessarily mean it is desirable. Therefore, this challenge adds to a discussion as to what outcome/benefit is sought through automation.

Keywords: Automation,

References:

[1] Nelms BE et al. Variation in external beam treatment plan quality: an inter-institutional study of planners and planning systems. Practical radiation oncology. 2012 Oct 1;2(4):296-305.