Precise diagnosis of pediatric posterior cranial fossa neoplasms based on 2.5D MRI deep learning
ResSwinT achieves high-precision classification of pediatric posterior fossa tumor through 2.5D multi-sequence fusion and cross-attention mechanism. SHAP attribution analysis reveals the biological basis of the model's decision-making, providing clinicians with an interpretable AI-assisted diagnostic tool, and is expected to optimize individualized treatment strategies.
Authors
- Can Yang Zhang (ORCID: https://orcid.org/0000-0002-6975-5781)
- Guohua Zhao (ORCID: https://orcid.org/0000-0003-0593-9175)
- Xinyu Wang (ORCID: https://orcid.org/0000-0002-5665-2935)
- Yangyang Cheng (ORCID: https://orcid.org/0000-0003-4991-6610)
- Yongqiang Li (ORCID: https://orcid.org/0009-0000-2414-121X)
- Fupeng Wei (ORCID: https://orcid.org/0000-0002-2337-1483)
- Qian Zhang (ORCID: https://orcid.org/0000-0001-7174-729X)
- Chin Ping Tan (ORCID: https://orcid.org/0000-0003-4177-4072)
- Wenjing Li (ORCID: https://orcid.org/0000-0002-8267-7925)
- Jie Dong (ORCID: https://orcid.org/0000-0002-7933-6214)
- Yong Zhang (ORCID: https://orcid.org/0000-0001-7985-8031)
- Xinxin Wang (ORCID: https://orcid.org/0000-0003-4858-0705)
- Weijian Wang (ORCID: https://orcid.org/0000-0001-9691-6395)
- Limeng Zhao (ORCID: https://orcid.org/0009-0003-1116-3315)
Institutions
- Zhongyuan University of Technology (CN)
- North China University of Water Resources and Electric Power (CN)
- First Affiliated Hospital of Zhengzhou University (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2025-11-12
- DOI
- https://doi.org/10.3389/fonc.2025.1700694
- Citations
- 1
- Primary Topic
- Glioma Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 1.63
Funders
- National Natural Science Foundation of China