Federated radiomics analysis of preoperative MRI across institutions: toward integrated glioma segmentation and molecular subtyping
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.
Authors
- Jianming Ni (ORCID: https://orcid.org/0000-0002-2354-0232)
- Haiyan Liu (ORCID: https://orcid.org/0000-0002-4652-469X)
- Jing Gu (ORCID: https://orcid.org/0000-0002-0291-3263)
- Zengli Miao
- Huang Guo
- Yongping Li (ORCID: https://orcid.org/0000-0002-3253-4088)
- Anmin Zhu (ORCID: https://orcid.org/0000-0001-8654-7100)
- Ran Ren
Institutions
- Jiangnan University (CN)
- Soochow University (CN)
- Shanghai Medical Information Center (CN)
- Xinhui People's Hospital (CN)
- Wuxi Ninth People's Hospital (CN)
Publication Details
- Journal
- Frontiers in Radiology
- Published
- 2025-11-10
- DOI
- https://doi.org/10.3389/fradi.2025.1648145
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00