Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Radiol.

Sec. Neuroradiology

Volume 5 - 2025 | doi: 10.3389/fradi.2025.1648145

Federated Radiomics Analysis of Preoperative MRI Across Institutions: Toward Integrated Glioma Segmentation and Molecular Subtyping

Provisionally accepted
Ran  RenRan Ren1,2Anjun  ZhuAnjun Zhu1,2Yaxi  LiYaxi Li2Huli  LiuHuli Liu2Guo  HuangGuo Huang3Jing  GuJing Gu4*Jianming  NiJianming Ni1,2*Zengli  MiaoZengli Miao5*
  • 1Jiangnan University Wuxi School of Medicine, Wuxi, China
  • 2Department of Radiology, Wuxi Ninth People's Hospital, Wuxi, China
  • 3Department of Neurosurgery, Lianshui County People's Hospital, Huai'an, China
  • 4Clinical Internal Medicine Department, Shanghai Health and Medical Center, Wuxi, China
  • 5Department of Neurosurgery, Jiangnan University Medical Center (JUMC), Wuxi, China

The final, formatted version of the article will be published soon.

Background. Non-invasive and comprehensive molecular characterization of glioma is crucial for personalized treatment but remains limited by invasive biopsy procedures and stringent privacy restrictions on clinical data sharing. Federated learning (FL) provides a promising solution by enabling multi-institutional collaboration without compromising patient confidentiality. Methods. We propose a multi-task 3D deep neural network framework based on federated learning. Using multi-modal MRI images, without sharing the original data, The automatic segmentation of T2w high signal region and the prediction of four molecular markers (IDH mutation, 1p/19q co-deletion, MGMT promoter methylation, WHO grade) were completed in collaboration with multiple medical institutions. We trained the model on local patient data at independent clients and aggregated the model parameters on a central server to achieve distributed collaborative learning. The model was trained on five public datasets (n = 1,552) and evaluated on an external validation dataset (n = 466). Results. The model showed good performance in the external test set (IDH AUC=0.88, 1p/19q AUC=0.84, MGMT AUC=0.85, grading AUC=0.94), and the median Dice of the segmentation task was 0.85. Conclusions. Our federated multi-task deep learning model demonstrates the feasibility and effectiveness of predicting glioma molecular characteristics and grade from multi-parametric MRI, without compromising patient privacy. These findings suggest significant potential for clinical deployment, especially in scenarios where invasive tissue sampling is impractical or risky.

Keywords: Federated learning, Multi-institutional, Multi-task deep learning, ModelMolecular Subtyping, image segmentation

Received: 20 Jun 2025; Accepted: 01 Oct 2025.

Copyright: © 2025 Ren, Zhu, Li, Liu, Huang, Gu, Ni and Miao. 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 Gu, g950324@163.com
Jianming Ni, nijianming@jiangnan.edu.cn
Zengli Miao, drmiao858@sina.com

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.