MRI-based 2.5D deep learning radiomics nomogram for the differentiation of benign versus malignant vertebral compression fractures
Our study integrates handcrafted radiomics, 2.5D deep learning features, and clinical data into a nomogram (DLRN). This approach not only enhances diagnostic accuracy but also provides superior clinical utility. The novel 2.5D DL framework and comprehensive feature fusion strategy represent significant advancements in the field, offering a robust tool for radiologists to differentiate benign from malignant VCFs.
Authors
- Wenhua Liang (ORCID: https://orcid.org/0000-0002-1391-8238)
- Lisha Duan (ORCID: https://orcid.org/0000-0003-0692-5154)
- Hong Yu (ORCID: https://orcid.org/0000-0003-0521-8933)
- Ming Wang (ORCID: https://orcid.org/0000-0002-3258-6961)
- Xiaona Li (ORCID: https://orcid.org/0000-0002-7041-2604)
- Bing Wang (ORCID: https://orcid.org/0000-0002-1480-3301)
- Jianling Cui
Institutions
- Hebei Medical University (CN)
- Third Hospital of Hebei Medical University (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-05-14
- DOI
- https://doi.org/10.3389/fonc.2025.1603672
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00