Enhancing prediction accuracy for muscle invasion in bladder cancer using a dual-energy CT-based interpretable model incorporating habitat radiomics and deep learning
The integrated model, combining DECT quantitative parameters, habitat features, and 2.5D DL features, enhances the accuracy of preoperative predictions for muscle invasion status in BCa. The SHAP methodology improves the interpretability of decision-making within the model and provides valuable support for clinicians in developing personalized treatment strategies.
Authors
- Lei Liu (ORCID: https://orcid.org/0009-0003-9112-5158)
- Yijun Liu
- Mengting Hu (ORCID: https://orcid.org/0009-0002-2897-5996)
- Jianying Li (ORCID: https://orcid.org/0000-0003-4034-0555)
- Wei Wei (ORCID: https://orcid.org/0000-0002-3120-8176)
- Jian He (ORCID: https://orcid.org/0000-0002-7906-4132)
- Chunling Du (ORCID: https://orcid.org/0000-0002-4252-932X)
- Jiageng Shen
Institutions
- Dalian Medical University (CN)
- First Affiliated Hospital of Dalian Medical University (CN)
Publication Details
- Journal
- BMC Cancer
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1186/s12885-025-15107-7
- Primary Topic
- Advanced X-ray and CT Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00