A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer
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 impro...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BioMed Central
2025
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/120354/ http://psasir.upm.edu.my/id/eprint/120354/1/120354.pdf |
| _version_ | 1848868166539673600 |
|---|---|
| author | Wang, Bingzhen Liu, Jinghua Zhang, Xiaolei Lin, Jianpeng Li, Shuyan Wang, Zhongxiao Cao, Zhendong Wen, Dong Liu, Tiange Harun Ramli, Hafiz Rashidi Harith, Hazreen Haizi Wan Hasan, Wan Zuha Dong, Xianling |
| author_facet | Wang, Bingzhen Liu, Jinghua Zhang, Xiaolei Lin, Jianpeng Li, Shuyan Wang, Zhongxiao Cao, Zhendong Wen, Dong Liu, Tiange Harun Ramli, Hafiz Rashidi Harith, Hazreen Haizi Wan Hasan, Wan Zuha Dong, Xianling |
| author_sort | Wang, Bingzhen |
| building | UPM Institutional Repository |
| collection | Online Access |
| description | 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. |
| first_indexed | 2025-11-15T14:48:04Z |
| format | Article |
| id | upm-120354 |
| institution | Universiti Putra Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T14:48:04Z |
| publishDate | 2025 |
| publisher | BioMed Central |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | upm-1203542025-10-01T00:18:52Z http://psasir.upm.edu.my/id/eprint/120354/ A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer Wang, Bingzhen Liu, Jinghua Zhang, Xiaolei Lin, Jianpeng Li, Shuyan Wang, Zhongxiao Cao, Zhendong Wen, Dong Liu, Tiange Harun Ramli, Hafiz Rashidi Harith, Hazreen Haizi Wan Hasan, Wan Zuha Dong, Xianling 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. BioMed Central 2025 Article PeerReviewed text en cc_by_nc_nd_4 http://psasir.upm.edu.my/id/eprint/120354/1/120354.pdf Wang, Bingzhen and Liu, Jinghua and Zhang, Xiaolei and Lin, Jianpeng and Li, Shuyan and Wang, Zhongxiao and Cao, Zhendong and Wen, Dong and Liu, Tiange and Harun Ramli, Hafiz Rashidi and Harith, Hazreen Haizi and Wan Hasan, Wan Zuha and Dong, Xianling (2025) A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer. Radiation Oncology, 20 (1). art. no. 127. pp. 1-14. ISSN 1748-717X https://ro-journal.biomedcentral.com/articles/10.1186/s13014-025-02695-8 10.1186/s13014-025-02695-8 |
| spellingShingle | Wang, Bingzhen Liu, Jinghua Zhang, Xiaolei Lin, Jianpeng Li, Shuyan Wang, Zhongxiao Cao, Zhendong Wen, Dong Liu, Tiange Harun Ramli, Hafiz Rashidi Harith, Hazreen Haizi Wan Hasan, Wan Zuha Dong, Xianling A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer |
| title | A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer |
| title_full | A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer |
| title_fullStr | A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer |
| title_full_unstemmed | A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer |
| title_short | A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer |
| title_sort | stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer |
| url | http://psasir.upm.edu.my/id/eprint/120354/ http://psasir.upm.edu.my/id/eprint/120354/ http://psasir.upm.edu.my/id/eprint/120354/ http://psasir.upm.edu.my/id/eprint/120354/1/120354.pdf |