Purpose: To improve the prediction accuracy of radiation dermatitis (RD) in breast cancer patients undergoing volumetric modulated arc therapy (VMAT), we developed a hybrid artificial intelligence (AI) model that integrates deep learning radiomics (DLR), handcrafted radiomics (HCR), clinical features, and dose–volume histogram (DVH) parameters, aiming to enhance the early identification of high-risk individuals and support personalized prevention strategies. Methods: A retrospective cohort of 156 breast cancer patients treated with VMAT at Kaohsiung Veterans General Hospital (2018–2023) was analyzed; 148 patients were eligible after exclusions, with RD graded according to the RTOG criteria. Clinical variables and 12 DVH indices were collected, while HCR features were extracted via PyRadiomics. DLR features were derived from a pretrained VGG16 network across four input designs: original CT images (DLROriginal), a 5 mm subcutaneous region (DLRSkin5mm), a planning target volume with a 100% prescription dose (DLRPTV100%), and a subcutaneous region receiving ≥ 5 Gy (DLRV5Gy). The features were preselected via ANOVA (p< 0.05), followed by Boruta–SHAP refinement across 11 feature sets. Predictive models were built via logistic regression, random forest, gradient boosting decision tree, and stacking ensemble (SE) methods. Explainability was assessed via SHapley Additive exPlanations (SHAPs) and gradient-weighted class activation mapping (Grad-CAM). Results: Among the 148 patients, 49 (33%) developed Grade ≥ 2 RD. The DLR models outperformed the HCR models (AUC = 0.72 vs. 0.66). The best performance was achieved with DLRV5Gy+ clinical + DVH features, yielding an AUC = 0.76, recall = 0.68, and F1 score = 0.60. SE consistently surpassed single classifiers. SHAP identified convolutional DLR features as the strongest predictors, whereas Grad-CAM focused attention on subcutaneous high-dose regions, which was consistent with the clinical RD distribution. Conclusions: 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.
目的：为提高容积旋转调强放疗（VMAT）乳腺癌患者放射性皮炎（RD）的预测准确性，我们开发了一种融合深度学习影像组学（DLR）、传统影像组学（HCR）、临床特征及剂量-体积直方图（DVH）参数的混合人工智能（AI）模型，旨在提升高危个体的早期识别能力，为个性化预防策略提供支持。方法：回顾性分析高雄荣民总医院（2018–2023年）接受VMAT治疗的156例乳腺癌患者队列；经排除后纳入148例符合条件患者，RD分级依据RTOG标准。收集临床变量及12项DVH指标，HCR特征通过PyRadiomics提取。DLR特征基于预训练VGG16网络从四种输入设计中提取：原始CT图像（DLROriginal）、5 mm皮下区域（DLRSkin5mm）、接受100%处方剂量的计划靶区（DLRPTV100%）以及接受≥5 Gy剂量的皮下区域（DLRV5Gy）。通过方差分析（p<0.05）进行特征预选，再经Boruta–SHAP算法对11组特征集进行优化。采用逻辑回归、随机森林、梯度提升决策树及堆叠集成（SE）方法构建预测模型，并通过SHAP可解释性分析及梯度加权类激活映射（Grad-CAM）评估模型可解释性。结果：148例患者中49例（33%）发生≥2级RD。DLR模型性能优于HCR模型（AUC=0.72 vs. 0.66）。最佳性能由DLRV5Gy+临床+DVH特征组合实现，AUC=0.76，召回率=0.68，F1分数=0.60。SE模型始终优于单一分类器。SHAP分析显示卷积DLR特征为最强预测因子，Grad-CAM则聚焦于皮下高剂量区域，与临床RD分布特征一致。结论：本研究提出的融合DLR、临床及DVH特征的混合AI框架，能够为乳腺癌患者VMAT后≥2级RD提供准确且可解释的预测。通过集成学习与可解释AI方法的结合，该模型可为个性化治疗规划提供可靠的高危分层依据及潜在临床转化价值。
肿瘤(癌症)患者之家