Integrating deep learning features from mammography with SHAP values for a machine learning model predicting over 5-year recurrence of breast ductal carcinoma In Situ post-lumpectomy
Our study developed an interpretable GBM model incorporating mammographic and clinical data to predict DCIS recurrence (AUC = 0.918). Key predictors were mammographic signature, Ki-67, and tumor grade, offering clinicians a practical tool for personalized postoperative management.
Authors
- Yi Du (ORCID: https://orcid.org/0000-0001-9568-0907)
- Jiguang Han (ORCID: https://orcid.org/0000-0002-5973-2842)
- Xiaoshuan Liang
- Yan Sha (ORCID: https://orcid.org/0000-0002-4596-8432)
- Shanshan Sun (ORCID: https://orcid.org/0000-0002-9175-083X)
- Tong Li (ORCID: https://orcid.org/0000-0002-4642-9932)
- Shu Gong
- Quan Yuan
- Shuqi Yang
- Ming Niu
Institutions
- Fujian Medical University (CN)
- Harbin Medical University (CN)
- Third Affiliated Hospital of Harbin Medical University (CN)
Publication Details
- Journal
- Frontiers in Immunology
- Published
- 2025-09-15
- DOI
- https://doi.org/10.3389/fimmu.2025.1681072
- Citations
- 1
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.36
Funders
- Harbin Medical University
- China Primary Health Care Foundation