Dose-Guided Hybrid AI Model with Deep and Handcrafted Radiomics for Explainable Radiation Dermatitis Prediction in Breast Cancer VMAT
The proposed hybrid AI framework, which integrates DLR, clinical, and DVH features, provides accurate and explainable predictions of Grade ≥ 2 RD after VMAT in breast cancer patients. By combining ensemble learning with XAI methods, the model offers reliable high-risk stratification and potential clinical utility for personalized treatment planning.
Authors
- Pei‐Ju Chao (ORCID: https://orcid.org/0000-0003-4155-853X)
- Yang-Wei Hsieh (ORCID: https://orcid.org/0000-0002-1374-0775)
- Shyh‐An Yeh (ORCID: https://orcid.org/0000-0002-0580-9111)
- Chia-Hui Chen
- Tsair-Fwu Lee (ORCID: https://orcid.org/0000-0002-3112-3594)
- Jun‐Ping Shiau (ORCID: https://orcid.org/0000-0003-0443-962X)
- Ping-Chen Tseng
- Yu‐Wei Lin (ORCID: https://orcid.org/0009-0006-6910-2939)
- C.S. Wuu
- L. Ken Tsai (ORCID: https://orcid.org/0009-0002-1404-6758)
- Ling-Chuan Chang-Chien
Institutions
- Kaohsiung Medical University (TW)
- Chang Gung University (TW)
- E-Da Hospital (TW)
- Kaohsiung Chang Gung Memorial Hospital (TW)
- Kaohsiung Veterans General Hospital (TW)
- National Kaohsiung University of Science and Technology (TW)
- Columbia University (US)
- I-Shou University (TW)
Publication Details
- Journal
- Cancers
- Published
- 2025-11-26
- DOI
- https://doi.org/10.3390/cancers17233767
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science and Technology Council