ORIGINAL RESEARCH article
Front. Oncol.
Sec. Cancer Imaging and Image-directed Interventions
This article is part of the Research TopicQuantitative Imaging: Revolutionizing Cancer Management with biological sensitivity, specificity, and AI integrationView all 26 articles
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
Provisionally accepted
Yongqiang Wang1
Alex Zwanenburg2
Jiang Zhang1
Xinzhi Teng1
Sai Kit Lam1
Jin Cao1
Zongrui Ma1
Ta Zhou1Yuanpeng Zhang1Hong Ge3
Jing Cai1*- 1Hong Kong Polytechnic University, Kowloon, Hong Kong, SAR China
- 2TUD Dresden University of Technology, Dresden, Germany
- 3Zhengzhou University, Zhengzhou, Henan Province, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Purpose: To guide the preselection of highly repeatable radiomic features (RFs) in downstream analysis without further analysis its repeatability, a detailed radiomic feature robustness databank (RF-RobustDB) was established via image perturbation. Methods: Data on 1,274 oropharyngeal carcinoma (OPC) patients who had undergone pretreatment computed tomography (CT) imaging, collected from a public dataset. The original images and corresponding masks underwent systematic perturbations to simulate potential variations encountered during CT image rescanning, including translational shifts, rotational changes, random noise additions, and contour modifications. For each radiomic feature (RF), including unfiltered, wavelet-filtered, and Laplacian-of-Gaussian (LoG)-filtered features, we systematically quantified robustness against these perturbations by intraclass correlation coefficients (ICCs). Results: Out of 1395 first-and high-order RFs, 470 demonstrated excellent repeatability, i.e., a mean ICC of greater than 0.9. The use of these preselected highly repeatable RFs in model development improved the mean concordance (C) index in two external validation cohorts and reduced the mean C index gap between the training and external validation cohorts. These results demonstrate that the preselected high repeatable RFs from RF-RobustDB can effectively enhance radiomic model generalizability. Conclusions: 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.
Keywords: Radiomics, Feature repeatability, Model generalizability, oropharyngeal carcinoma, Progression-free survival
Received: 15 Jul 2024; Accepted: 27 Oct 2025.
Copyright: © 2025 Wang, Zwanenburg, Zhang, Teng, Lam, Cao, Ma, Zhou, Zhang, Ge and Cai. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Jing Cai, jing.cai@polyu.edu.hk
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.