Development and validation of a deep learning algorithm for discriminating glioma recurrence from radiation necrosis on MRI
The proposed ResNet10 CNN model demonstrates promising performance on routine MRI scans, rendering it highly applicable in clinical settings. These findings contribute to enhancing the diagnostic accuracy for distinguishing between glioma recurrence and radiation necrosis using routine MRI.
Authors
- Yu-Zhe Ying
- Zhongli Jiang (ORCID: https://orcid.org/0000-0002-0247-423X)
- Zhulin An (ORCID: https://orcid.org/0000-0002-7593-8293)
- Dao Zheng (ORCID: https://orcid.org/0000-0003-2493-2454)
- Hao-Yi Li
- Yonggang Wang (ORCID: https://orcid.org/0000-0002-8412-9244)
- Guobin Zhang (ORCID: https://orcid.org/0000-0002-9881-180X)
- Yang Han (ORCID: https://orcid.org/0000-0002-8843-6970)
- Hua-Wei Huang (ORCID: https://orcid.org/0009-0000-9482-6281)
- Xiaohong Cai
- Gehong Dong
Institutions
- Capital Medical University (CN)
- Beijing Tian Tan Hospital (CN)
- Institute of Computing Technology (CN)
- University of Chinese Academy of Sciences (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-06-06
- DOI
- https://doi.org/10.3389/fonc.2025.1573700
- Citations
- 1
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.84
Funders
- Beijing Municipal Administration of Hospitals