The impact of data consistency on deep learning models for nasopharyngeal cancer organ auto-segmentation
. Annotation consistency supersedes dataset scale as the primary performance driver for OAR auto-contouring. Small high-consistency datasets enable optimal native model accuracy, whereas fine-tuning large pre-trained models with targeted physician data closes domain adaptation gaps and delivers state-of-the-art segmentation, advancing precision radiotherapy for head and neck oncology..
Authors
- Shenlun Chen
- Jiazhou Wang (ORCID: https://orcid.org/0000-0002-9012-6605)
- Jing Mi
- Xiayun He (ORCID: https://orcid.org/0000-0002-1652-3012)
- Yi Guo (ORCID: https://orcid.org/0000-0002-6419-0558)
- Yingtao Fang
- Jian Qiao
- Chaosu Hu
- Weigang Hu
- Yang Zhong
- Lei Yu
Institutions
- Shanghai University (CN)
- Shanghai Medical College of Fudan University (CN)
- Fudan University Shanghai Cancer Center (CN)
- Shanghai Clinical Research Center (CN)
Publication Details
- Journal
- Biomedical Physics & Engineering Express
- Published
- 2026-03-31
- DOI
- https://doi.org/10.1088/2057-1976/ae596e
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00