An interpretable machine learning model based on computed tomography radiomics for predicting programmed death ligand 1 expression status in gastric cancer
Our CT radiomics-based LGBM model may aid in preoperatively predicting PD-L1 expression status in GC patients, and the SHAP method may improve the interpretability of this model.
Authors
- Purong Zhang (ORCID: https://orcid.org/0000-0003-4317-1355)
- Shuying Lai (ORCID: https://orcid.org/0000-0001-7492-7931)
- Yuanlin Chen
- Chun Yao (ORCID: https://orcid.org/0000-0002-7147-9608)
- Xiangguang Chen (ORCID: https://orcid.org/0000-0003-4368-4820)
- Guo‐Liang Lu (ORCID: https://orcid.org/0000-0002-2094-0820)
- Jinxue Yin
- Xin Xin (ORCID: https://orcid.org/0000-0003-4899-9127)
- Jiansheng Li (ORCID: https://orcid.org/0000-0002-7761-8103)
- Xiaohong Xia (ORCID: https://orcid.org/0000-0003-2219-1162)
- Jie Huang (ORCID: https://orcid.org/0009-0006-1871-0598)
- Lei Dai (ORCID: https://orcid.org/0000-0002-4469-7386)
- Yongfang Tang
- Xi Zhong (ORCID: https://orcid.org/0000-0002-0713-105X)
Institutions
- Meizhou City People's Hospital (CN)
- Guangzhou Medical University Cancer Hospital (CN)
- Guangzhou Medical University (CN)
Publication Details
- Journal
- Cancer Imaging
- Published
- 2025-03-12
- DOI
- https://doi.org/10.1186/s40644-025-00855-3
- Citations
- 10
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 13.60
Funders
- National Natural Science Foundation of China