Radiomics-based machine learning for glioma grade classification: a multicenter study with SHapley Additive exPlanations interpretability analysis
We successfully developed and validated a robust, interpretable radiomics-based model that accurately predicts glioma WHO grade preoperatively. Its promising performance across diverse datasets suggests potential for clinical translation, though prospective validation in real-world clinical workflows is required to confirm clinical utility and assess impact on treatment decisions and patient outcomes.
Authors
- Xinran Ji (ORCID: https://orcid.org/0000-0002-1276-6658)
- Li Zhou (ORCID: https://orcid.org/0000-0003-4099-6917)
- Hongyu Zhao (ORCID: https://orcid.org/0000-0003-1195-9607)
- Ninghua Yao (ORCID: https://orcid.org/0000-0002-7607-2516)
- Yumeng Shi (ORCID: https://orcid.org/0009-0000-0679-0697)
- Yu Shi (ORCID: https://orcid.org/0000-0003-1272-8392)
- Wenjie Zheng (ORCID: https://orcid.org/0000-0001-9481-0714)
- Wei Jiang (ORCID: https://orcid.org/0000-0002-6742-5199)
Institutions
- Nantong University (CN)
- Affiliated Hospital of Nantong University (CN)
- Xian Yang Central Hospital (CN)
- Wuxi People's Hospital (CN)
Publication Details
- Journal
- Translational Cancer Research
- Published
- 2025-10-01
- DOI
- https://doi.org/10.21037/tcr-2025-2024
- Citations
- 1
- Primary Topic
- Glioma Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 1.63