Wang Bingzhen, Liu Jinghua, Zhang Xiaolei, Lin Jianpeng, Li Shuyan, Wang Zhongxiao, Cao Zhendong, Wen Dong, Liu Tiange, Ramli Hafiz Rashidi Harun, Harith Hazreen Haizi, Hasan Wan Zuha Wan, Dong Xianling
Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra Malaysia, Serdang, Malaysia.
Department of Biomedical Engineering, Chengde Medical University, Chengde City, Hebei Province, China.
Radiat Oncol. 2025 Aug 13;20(1):127. doi: 10.1186/s13014-025-02695-8.
BACKGROUND: Radiomics models frequently face challenges related to reproducibility and robustness. To address these issues, we propose a multimodal, multi-model fusion framework utilizing stacking ensemble learning for prognostic prediction in head and neck cancer (HNC). This approach seeks to improve the accuracy and reliability of survival predictions. METHODS: A total of 806 cases from nine centers were collected; 143 cases from two centers were assigned as the external validation cohort, while the remaining 663 were stratified and randomly split into training (n = 530) and internal validation (n = 133) sets. Radiomics features were extracted according to IBSI standards, and deep learning features were obtained using a 3D DenseNet-121 model. Following feature selection, the selected features were input into Cox, SVM, RSF, DeepCox, and DeepSurv models. A stacking fusion strategy was employed to develop the prognostic model. Model performance was evaluated using Kaplan-Meier survival curves and time-dependent ROC curves. RESULTS: On the external validation set, the model using combined PET and CT radiomics features achieved superior performance compared to single-modality models, with the RSF model obtaining the highest concordance index (C-index) of 0.7302. When using deep features extracted by 3D DenseNet-121, the PET + CT-based models demonstrated significantly improved prognostic accuracy, with Deepsurv and DeepCox achieving C-indices of 0.9217 and 0.9208, respectively. In stacking models, the PET + CT model using only radiomics features reached a C-index of 0.7324, while the deep feature-based stacking model achieved 0.9319. The best performance was obtained by the multi-feature fusion model, which integrated both radiomics and deep learning features from PET and CT, yielding a C-index of 0.9345. Kaplan-Meier survival analysis further confirmed the fusion model's ability to distinguish between high-risk and low-risk groups. CONCLUSION: The stacking-based ensemble model demonstrates superior performance compared to individual machine learning models, markedly improving the robustness of prognostic predictions.
背景：放射组学模型经常面临与可重复性和稳健性相关的挑战。为了解决这些问题，我们提出了一种多模态、多模型融合框架，利用堆叠集成学习对头颈部癌（HNC）进行预后预测。这种方法旨在提高生存预测的准确性和可靠性。 方法：收集了来自9个中心的806例病例；将来自2个中心的143例病例分配为外部验证队列，其余663例病例进行分层并随机分为训练集（n = 530）和内部验证集（n = 133）。根据IBSI标准提取放射组学特征，并使用3D DenseNet - 121模型获得深度学习特征。在特征选择之后，将选定的特征输入到Cox、支持向量机（SVM）、随机生存森林（RSF）、深度Cox和深度生存（DeepSurv）模型中。采用堆叠融合策略来开发预后模型。使用Kaplan - Meier生存曲线和时间依赖性ROC曲线评估模型性能。 结果：在外部验证集上，与单模态模型相比，使用PET和CT联合放射组学特征的模型表现更优，RSF模型获得了最高的一致性指数（C指数），为0.7302。当使用由3D DenseNet - 121提取的深度特征时，基于PET + CT的模型显示出显著提高的预后准确性，DeepSurv和深度Cox的C指数分别达到0.9217和0.9208。在堆叠模型中，仅使用放射组学特征的PET + CT模型的C指数达到0.7324，而基于深度特征的堆叠模型达到0.9319。多特征融合模型表现最佳，该模型整合了来自PET和CT的放射组学和深度学习特征，C指数为0.9345。Kaplan - Meier生存分析进一步证实了融合模型区分高风险和低风险组的能力。 结论：与单个机器学习模型相比，基于堆叠的集成模型表现出卓越的性能，显著提高了预后预测的稳健性。
Comput Methods Programs Biomed. 2025-4
Comput Biol Med. 2025-2
Geroscience. 2024-11-22
Comput Biol Med. 2024-12
Zotero 插件
