Development and validation of a deep learning model using MR imaging for predicting brain metastases: an accuracy-focused study
The model demonstrated strong robustness and perfect specificity across demographics. While showing cancer type dependency (requiring improved lung cancer sensitivity), its high efficiency (40%-50% time reduction) and generalization provide a solid foundation for clinical translation.
Authors
- Yinsu Zhu (ORCID: https://orcid.org/0000-0001-9279-8192)
- Dan Shi (ORCID: https://orcid.org/0000-0003-0138-3958)
- Xiaoxiao Lv (ORCID: https://orcid.org/0009-0001-7849-582X)
- Min Dong (ORCID: https://orcid.org/0000-0002-5907-8318)
- Xuan Ning (ORCID: https://orcid.org/0000-0003-1459-2847)
- Meng Yang (ORCID: https://orcid.org/0000-0001-5630-6357)
- Lanlan Xu
- Fei Xia (ORCID: https://orcid.org/0000-0003-3998-4898)
- Na Yin (ORCID: https://orcid.org/0000-0003-1244-2837)
- Chao Xie (ORCID: https://orcid.org/0000-0002-9137-3835)
- Qinglei Zhang (ORCID: https://orcid.org/0000-0003-0797-7423)
Institutions
- Nanjing Drum Tower Hospital (CN)
- Film Independent (US)
- Jiangsu Cancer Hospital (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-09-23
- DOI
- https://doi.org/10.3389/fonc.2025.1657604
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.00