A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer
Abstract 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...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-08-01
|
| Series: | Radiation Oncology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13014-025-02695-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849234632351940608 |
|---|---|
| author | Bingzhen Wang Jinghua Liu Xiaolei Zhang Jianpeng Lin Shuyan Li Zhongxiao Wang Zhendong Cao Dong Wen Tiange Liu Hafiz Rashidi Harun Ramli Hazreen Haizi Harith Wan Zuha Wan Hasan Xianling Dong |
| author_facet | Bingzhen Wang Jinghua Liu Xiaolei Zhang Jianpeng Lin Shuyan Li Zhongxiao Wang Zhendong Cao Dong Wen Tiange Liu Hafiz Rashidi Harun Ramli Hazreen Haizi Harith Wan Zuha Wan Hasan Xianling Dong |
| author_sort | Bingzhen Wang |
| collection | DOAJ |
| description | Abstract 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. |
| format | Article |
| id | doaj-art-8db70bfbc6f3432b98a8da0190263de4 |
| institution | Kabale University |
| issn | 1748-717X |
| language | English |
| publishDate | 2025-08-01 |
| publisher | BMC |
| record_format | Article |
| series | Radiation Oncology |
| spelling | doaj-art-8db70bfbc6f3432b98a8da0190263de42025-08-20T04:03:06ZengBMCRadiation Oncology1748-717X2025-08-0120111410.1186/s13014-025-02695-8A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancerBingzhen Wang0Jinghua Liu1Xiaolei Zhang2Jianpeng Lin3Shuyan Li4Zhongxiao Wang5Zhendong Cao6Dong Wen7Tiange Liu8Hafiz Rashidi Harun Ramli9Hazreen Haizi Harith10Wan Zuha Wan Hasan11Xianling Dong12Department of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra MalaysiaDepartment of Nursing, Faculty of Medicine and Health Sciences, Universiti Putra MalaysiaDepartment of Biomedical Engineering, Chengde Medical UniversityDepartment of Biomedical Engineering, Chengde Medical UniversityDepartment of Medical Engineering, Tianjin Armed Police Corps HospitalDepartment of Biomedical Engineering, Chengde Medical UniversityDepartment of Radiology, the Affiliated Hospital of Chengde Medical UniversityInstitute of Artificial Intelligence, University of Science and Technology BeijingInstitute of Artificial Intelligence, University of Science and Technology BeijingDepartment of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra MalaysiaDepartment of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra MalaysiaDepartment of Electrical and Electronic Engineering, Faculty of Engineering, Universiti Putra MalaysiaDepartment of Biomedical Engineering, Chengde Medical UniversityAbstract 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.https://doi.org/10.1186/s13014-025-02695-8Head and neck CancerRadiomicsDenseNetStackingEnsemblePrognostic |
| spellingShingle | Bingzhen Wang Jinghua Liu Xiaolei Zhang Jianpeng Lin Shuyan Li Zhongxiao Wang Zhendong Cao Dong Wen Tiange Liu Hafiz Rashidi Harun Ramli Hazreen Haizi Harith Wan Zuha Wan Hasan Xianling Dong A stacking ensemble framework integrating radiomics and deep learning for prognostic prediction in head and neck cancer Radiation Oncology Head and neck Cancer Radiomics DenseNet Stacking Ensemble Prognostic |
| 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 |
| topic | Head and neck Cancer Radiomics DenseNet Stacking Ensemble Prognostic |
| url | https://doi.org/10.1186/s13014-025-02695-8 |
| work_keys_str_mv | AT bingzhenwang astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT jinghualiu astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT xiaoleizhang astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT jianpenglin astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT shuyanli astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT zhongxiaowang astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT zhendongcao astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT dongwen astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT tiangeliu astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT hafizrashidiharunramli astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT hazreenhaiziharith astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT wanzuhawanhasan astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT xianlingdong astackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT bingzhenwang stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT jinghualiu stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT xiaoleizhang stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT jianpenglin stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT shuyanli stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT zhongxiaowang stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT zhendongcao stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT dongwen stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT tiangeliu stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT hafizrashidiharunramli stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT hazreenhaiziharith stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT wanzuhawanhasan stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer AT xianlingdong stackingensembleframeworkintegratingradiomicsanddeeplearningforprognosticpredictioninheadandneckcancer |