ORIGINAL RESEARCH article
Front. Oncol.
Sec. Thoracic Oncology
Volume 15 - 2025 | doi: 10.3389/fonc.2025.1630485
This article is part of the Research TopicRadiomics and Artificial Intelligence in Oncology ImagingView all 12 articles
Incremental diagnostic value of tumor habitat radiomics for risk stratification in thymic epithelial tumors
Provisionally accepted
- 1The Second Affiliated Hospital of Harbin Medical University, Harbin, China
- 2Heilongjiang Red Cross Sengong General Hospital, Harbin, 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 determine the incremental diagnostic value of habitat radiomics for risk stratification of thymic epithelial tumors (TETs) based on contrast-enhanced CT (CECT).: This retrospective study included 220 patients with pathologically confirmed TETs (82 high-risk [B2/B3/thymic carcinoma] and 138 low-risk [A/AB/B1]) who underwent preoperative CECT. Tumors were segmented into 3 subregions (habitats) using k-means clustering, and radiomic features were extracted from both whole-tumor and subregions. After feature selection (variance threshold, reproducibility evaluation, XGBoost-based importance ranking, and recursive feature elimination), three machine learning models were developed: (1) a conventional radiomics model, (2) a habitat radiomics model, and (3) a combined model integrating both feature sets. Model performance was evaluated using ROC analysis, net reclassification improvement (NRI), integrated discrimination improvement (IDI), calibration metrics, and decision curve analysis (DCA).Results: The combined model demonstrated superior discrimination (AUC: 0.900) compared to the conventional (AUC: 0.819) and habitat (AUC: 0.734) radiomics models in the independent test set. Although DeLong's test showed no statistically significant difference (p=0.161), the combined model provided incremental diagnostic value (NRI: 0.286; IDI: 0.209). Calibration and DCA confirmed its robustness and higher net benefit across decision thresholds. While the models' training performance might suggest overfitting, their test results demonstrate generalizability.The habitat radiomics approach enables accurate risk stratification prediction in TETs and demonstrates potential as a clinically valuable tool to augment the performance of conventional radiomics models in routine practice.
Keywords: Thymic Epithelial Tumors, habitat radiomics, risk stratification, computed tomography, machine learning
Received: 17 May 2025; Accepted: 25 Jul 2025.
Copyright: © 2025 Wang, Shi, Sun, Wang, Ran and Zhang. 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:
Tianzuo Wang, Heilongjiang Red Cross Sengong General Hospital, Harbin, China
Zhizhen Ran, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
Jinling Zhang, The Second Affiliated Hospital of Harbin Medical University, Harbin, China
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.