Trade‐off of different deep learning‐based auto‐segmentation approaches for treatment planning of pediatric craniospinal irradiation autocontouring of OARs for pediatric CSI
LimbusAI could not adapt well to pediatric anatomy for the esophagus and the kidneys. When commercial products do not suit the study population, the nnU-Net is a viable option but requires adjustments. In resource-constrained settings, the in-house model provides an alternative. Implementing an automated segmentation tool requires careful monitoring and quality assurance regardless of the approach.
Authors
- Chia‐Ho Hua (ORCID: https://orcid.org/0000-0002-6642-4004)
- Shirin Abbasinejad Enger (ORCID: https://orcid.org/0000-0002-6037-0615)
- O. Ates (ORCID: https://orcid.org/0000-0002-9345-417X)
- James Man Git Tsui (ORCID: https://orcid.org/0000-0001-7570-2179)
- A. Thibodeau-Antonacci
- Sonia Skamene (ORCID: https://orcid.org/0000-0002-6318-8982)
- James Schneider
- Marija Popović (ORCID: https://orcid.org/0000-0002-9223-364X)
- Carolyn Freeman
Institutions
- St. Jude Children's Research Hospital (US)
- Jewish General Hospital (CA)
- McGill University (CA)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-04-01
- DOI
- https://doi.org/10.1002/mp.17782
- Citations
- 4
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 7.53