ESTRO 2024 - Abstract Book

S3026

Physics - Autosegmentation

ESTRO 2024

Conclusion:

Using the weakly supervised commissioning approach to select cases for manual evaluation increases the chance of selecting atypical edge cases with low segmentation performance, as compared to a random selection. Providing a more representative range of expected segmentation performance in clinical practice to evaluate the segmentation model on. This approach could be used for model commissioning to increase the confidence that the model performs well over a wide range of expected anatomical variation, or for continuous model QA after clinical introduction.

Keywords: Clinical introduction, model commissioning, QA

References:

[1]: Isensee F., et al. (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. https://doi.org/10.1038/s41592-020-01008-z

[2]: van Griethuysen, J. J. M., et al. (2017). Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Research. https://doi.org/10.1158/0008-5472.CAN-17-0339