Establishment of a CT-based radiomic feature robustness databank for OPC patients via image perturbation in a multi-institutional study: a practical method to safeguard model generalizability
The methodology employed to establish the RF-RobustDB is highly transferable to other tumor sites and different imaging modalities, which will facilitate the creation of RF-RobustDBs to guide the development of universally applicable radiomic models.
Authors
- Hong Ge (ORCID: https://orcid.org/0000-0002-2958-3866)
- Xinzhi Teng (ORCID: https://orcid.org/0000-0001-7515-8302)
- Ta Zhou (ORCID: https://orcid.org/0000-0003-3238-7257)
- Saikit Lam (ORCID: https://orcid.org/0000-0003-0293-2381)
- Jing Cai (ORCID: https://orcid.org/0000-0002-2032-8711)
- Zongrui Ma (ORCID: https://orcid.org/0000-0003-0217-3688)
- Alex Zwanenburg (ORCID: https://orcid.org/0000-0002-0342-9545)
- Yongqiang Wang (ORCID: https://orcid.org/0000-0001-8715-128X)
- Jiang Zhang (ORCID: https://orcid.org/0000-0001-5807-1686)
- Yuanpeng Zhang (ORCID: https://orcid.org/0000-0001-7706-2865)
- Jin Xin Cao (ORCID: https://orcid.org/0000-0001-5768-8190)
Institutions
- Hong Kong Polytechnic University (HK)
- German Cancer Research Center (DE)
- Shenzhen Polytechnic University (CN)
- Heidelberg University (DE)
- Helmholtz-Zentrum Dresden-Rossendorf (DE)
- Zhengzhou University (CN)
- National Center for Tumor Diseases (DE)
- Henan Cancer Hospital (CN)
- DKFZ-ZMBH Alliance (DE)
- University Hospital Carl Gustav Carus (DE)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-11-24
- DOI
- https://doi.org/10.3389/fonc.2025.1464884
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Hong Kong Polytechnic University
- Shenzhen Municipal Science and Technology Innovation Council
- Health and Medical Research Fund