ESTRO 2025 - Abstract Book

S2470

Physics - Autosegmentation

ESTRO 2025

Conclusion: With the increased use of autocontouring in radiation therapy, it is necessary that centres develop an effective method for conducting ongoing monitoring into its use. This pilot study demonstrates that ongoing monitoring is able to detect differences in the use of autocontouring software between commissioning and routine clinical use, between different staff members, and for different structures. Interventions, such as reviewing autocontouring use with staff responsible for editing, is a possible solution to mitigate automation bias and review fatigue.

Keywords: Autocontouring, monitoring

References: [1] Doolan P J et al, 2023 A clinical evaluation of the performance of five commercial artificial intelligence contouring systems for radiotherapy Front. Oncol. 13 1–13 [2] Hurkmans C et al, 2024 A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy Radiother. Oncol. 197 110345 [3] Nikolov S et al, 2018 Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy 1–31