Abstract
Breast cancer recurrence prediction is an important feature of post-treatment therapy, requiring accurate identification of both recurrence risk and time-to-event outcomes. In this paper, we offer a unified deep learning system that jointly performs survival analysis and multi-class recurrence classification, enabling full risk stratification for breast cancer patients. The proposed model includes a Transformer-based survival module to estimate time-until-recurrence, and an attention-guided classification module to differentiate between second primary cancer, low-risk, and high-risk recurrence instances. A multi-modal dataset comprising clinical, molecular, demographic, and lifestyle data is created from established sources like METABRIC, GSE2034, GSE2990, BCSC, and the Breast Cancer Coimbra dataset. The model uses cross-modal feature fusion, autoencoder-based dimensionality reduction, and attention-based feature attribution for applicability and accessibility. Experimental results show better accuracy, precision, recall, and F1-score of 99.12%, 98.75%, 99.08%, and 98.91%, outperforming standard machine learning and survival models. This unified paradigm gives doctors a powerful, interpretable tool for early intervention and personalized breast cancer treatment.
Data availability
The data that supports the findings of this study are available within the article.
Code availability
The source code for the proposed framework is publicly available at the following GitHub repository: https://github.com/saleem-saleem/Breast-Cancer-Multimodal-Transformer.
Abbreviations
- AI:
-
Artificial intelligence
- AE:
-
Autoencoder
- BCSC:
-
Breast cancer surveillance consortium
- BMI:
-
Body mass index
- BRCA:
-
Breast cancer gene (BRCA1/BRCA2)
- CI:
-
Confidence interval
- CNN:
-
Convolutional neural network
- C-index:
-
Concordance Index
- CoxPH:
-
Cox proportional hazards
- DBT:
-
Digital breast tomosynthesis
- DL:
-
Deep learning
- ER:
-
Estrogen receptor
- FFDM:
-
Full-field digital mammography
- F1:
-
F1-score (Harmonic mean of precision and recall)
- GEO:
-
Gene expression omnibus
- HER2:
-
Human epidermal growth factor receptor 2
- H&E:
-
Hematoxylin and eosin
- HR:
-
Hazard ratio
- KM:
-
Kaplan–meier
- LASSO:
-
Least absolute shrinkage and selection operator
- MLP:
-
Multilayer perceptron
- METABRIC:
-
Molecular taxonomy of breast cancer international consortium
- MMT:
-
Multi-modal transformer
- MRI:
-
Magnetic resonance imaging
- PH:
-
Proportional hazards
- ReLU:
-
Rectified linear unit
- ROC:
-
Receiver operating characteristic
- SHAP:
-
SHapley additive exPlanations
- SMOTE:
-
Synthetic minority oversampling technique
- TCGA:
-
The cancer genome atlas
- TNBC:
-
Triple-negative breast cancer
- TIL:
-
Tumor-infiltrating lymphocyte
- VAE:
-
Variational autoencoder
- ViT:
-
Vision transformer
- λ₁, λ₂:
-
Task weighting coefficients for survival and classification losses
- γ:
-
Temperature scaling parameter in contrastive loss
- τ:
-
Temperature parameter in similarity normalization
- αₘ:
-
Modality attention weight
- ψ(x;θ):
-
Log-risk function parameterized by network weights
References
Kulothungan, V. et al. Burden of female breast cancer in India: Estimates of YLDs, YLLs, and DALYs at national and subnational levels based on the national cancer registry programme. Breast Cancer Res. Treat. 205, 323–332. https://doi.org/10.1007/s10549-024-07264-3 (2024).
Soldato, D. et al. The Future of breast cancer research in the survivorship field. Oncol. Ther. 11, 199–229. https://doi.org/10.1007/s40487-023-00225-8 (2023).
Beiranvand, M., Akbari, A. & Akbari, M. E. Evaluation of recurrence and survival in multifocal versus unifocal breast cancer patients at a tertiary center: A case-control study. Cancer Treat. Res. Commun. 43, 100894. https://doi.org/10.1016/j.ctarc.2025.100894 (2025).
van Maaren, M. C. et al. The effectiveness of personalised surveillance and aftercare in breast cancer follow-up: A systematic review. Support Care Cancer 32, 323. https://doi.org/10.1007/s00520-024-08530-2 (2024).
Tizi, W. & Berrado, A. Machine learning for survival analysis in cancer research: A comparative study. Sci. Afr. 21, e01880. https://doi.org/10.1016/j.sciaf.2023.e01880 (2023).
Kumari, D. et al. Predicting breast cancer recurrence using deep learning. Discov. Appl. Sci. 7, 113. https://doi.org/10.1007/s42452-025-06512-5 (2025).
Zhang, X. et al. Adaptive transformer modelling of density function for nonparametric survival analysis. Mach. Learn. 114, 31. https://doi.org/10.1007/s10994-024-06686-w (2025).
Wang, Z. et al. Surformer: An interpretable pattern-perceptive survival transformer for cancer survival prediction from histopathology whole slide images. Comput. Methods Programs Biomed. 241, 107733. https://doi.org/10.1016/j.cmpb.2023.10773 (2023).
Chen, X. et al. Artificial intelligence and multimodal data fusion for smart healthcare: Topic modeling and bibliometrics. Artif. Intell. Rev. 57, 91. https://doi.org/10.1007/s10462-024-10712-7 (2024).
https://www.kaggle.com/datasets/raghadalharbi/breast-cancer-gene-expression-profiles-metabric
https://www.kaggle.com/datasets/saurabhshahane/gene-expression-profiles-of-breast-cancer
https://www.kaggle.com/datasets/sabahesaraki/bcsc-digital-mammography-dataset
https://archive.ics.uci.edu/dataset/451/breast+cancer+coimbra
Islam, T. et al. Predictive modeling for breast cancer classification in the context of Bangladeshi patients by use of machine learning approach with explainable AI. Sci. Rep. 14, 8487. https://doi.org/10.1038/s41598-024-57740-5 (2024).
Silveira, J. A., da Silva, A. R. & de Lima, M. Z. T. Harnessing artificial intelligence for predicting breast cancer recurrence: A systematic review of clinical and imaging data. Discov. Onc. 16, 135. https://doi.org/10.1007/s12672-025-01908-6 (2025).
Azeroual, S. et al. Predicting disease recurrence in breast cancer patients using machine learning models with clinical and radiomic characteristics: A retrospective study. J. Egypt. Natl. Canc. Inst. 36, 20. https://doi.org/10.1186/s43046-024-00222-6 (2024).
Vazifehdan, M., Moattar, M. H. & Jalali, M. hybrid Bayesian network and tensor factorization approach for missing value imputation to improve breast cancer recurrence prediction. J. King Saud Univ. – Comput. Inform. Sci. 31(2), 175–184. https://doi.org/10.1016/j.jksuci.2018.01.002 (2019A).
Terven, J. et al. A comprehensive survey of loss functions and metrics in deep learning. Artif. Intell. Rev. 58, 195. https://doi.org/10.1007/s10462-025-11198-7 (2025).
Jiang, S., Suriawinata, A. A. & Hassanpour, S. MHAttnSurv: Multi-head attention for survival prediction using whole-slide pathology images. Comput. Biol. Med. 158, 106883. https://doi.org/10.1016/j.compbiomed.2023.106883 (2023).
Zadeh Shirazi, A. et al. DeepSurvNet: Deep survival convolutional network for brain cancer survival rate classification based on histopathological images. Med. Biol. Eng. Comput. 58, 1031–1045. https://doi.org/10.1007/s11517-020-02147-3 (2020).
Mienye, I. D. et al. A survey of explainable artificial intelligence in healthcare: Concepts, applications, and challenges. Inform. Med. Unlocked 51, 101587. https://doi.org/10.1016/j.imu.2024.101587 (2024).
Mienye, I. D. & Swart, T. G. Deep autoencoder neural networks: A comprehensive review and new perspectives. Arch. Computat. Methods Eng. https://doi.org/10.1007/s11831-025-10260-5 (2025).
Schouten, D. et al. Navigating the landscape of multimodal AI in medicine: A scoping review on technical challenges and clinical applications. Med. Image Anal. 105, 103621. https://doi.org/10.1016/j.media.2025.103621 (2025).
Sallauka, R. et al. Scoping review: (Bio)markers for the prognostication of breast cancer recurrence. BMC Cancer 25, 1081. https://doi.org/10.1186/s12885-025-14515-z (2025).
Jannusch, K. et al. Prediction of therapy response of breast cancer patients with machine learning based on clinical data and imaging data derived from breast [18F]FDG-PET/MRI. Eur. J. Nucl. Med. Mol. Imaging 51, 1451–1461. https://doi.org/10.1007/s00259-023-06513-9 (2024).
Salvi, M. et al. Multi-modality approaches for medical support systems: A systematic review of the last decade. Inform. Fusion 103, 102134. https://doi.org/10.1016/j.inffus.2023.102134 (2024).
Luo, H. et al. Multimodal multi-instance evidence fusion neural networks for cancer survival prediction. Sci. Rep. 15, 10470. https://doi.org/10.1038/s41598-025-93770-3 (2025).
Javed, H., El-Sappagh, S. & Abuhmed, T. Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust AI applications. Artif. Intell. Rev. 58, 12. https://doi.org/10.1007/s10462-024-11005-9 (2025).
Nazir, S., Dickson, D. M. & Akram, M. U. Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks. Comput. Biol. Med. 156, 106668. https://doi.org/10.1016/j.compbiomed.2023.106668 (2023).
Aghajanpour, S. et al. Utilizing machine learning for predicting drug release from polymeric drug delivery systems. Comput. Biol. Med. 188, 109756. https://doi.org/10.1016/j.compbiomed.2025.10975 (2025).
Senan, E. M., Alsaade, F. W., AlMashhadani, M. I. A., Theyazn, H. H. & Al-Adhaileh, M. H. Classification of histopathological images for early detection of breast cancer using deep learning. J. Appl. Sci. Eng. 24(3), 323–329 (2021).
Hameed, Z., Zahia, S., Garcia-Zapirain, B., Javier Aguirre, J. & María Vanegas, A. Breast cancer histopathology image classification using an ensemble of deep learning models. Sensors 20(16), 4373. https://doi.org/10.3390/s20164373 (2020).
Alom, M. R. et al. An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images. Sci. Rep. 15, 17531. https://doi.org/10.1038/s41598-025-97718-5 (2025).
Sánchez-Cauce, R., Pérez-Martín, J. & Luque, M. Multi-input convolutional neural network for breast cancer detection using thermal images and clinical data. Comput. Methods Programs Biomed. 204, 106045. https://doi.org/10.1016/j.cmpb.2021.106045 (2021).
Asadi, B. & Memon, Q. Efficient breast cancer detection via cascade deep learning network. Int. J. Intell. Netw. 4, 46–52. https://doi.org/10.1016/j.ijin.2023.02.001 (2023).
Sohail, A., Khan, A., Nisar, H., Tabassum, S. & Zameer, A. Mitotic nuclei analysis in breast cancer histopathology images using deep ensemble classifier. Med. Image Anal. 72, 102121. https://doi.org/10.1016/j.media.2021.10212 (2021).
Guo, D. et al. Classify breast cancer pathological tissue images using multi-scale bar convolution pooling structure with patch attention. Biomed. Signal Process. Control 96, 106607. https://doi.org/10.1016/j.bspc.2024.106607 (2024).
Saha, M. et al. Breast-NET: A lightweight DCNN model for breast cancer detection and grading using histological samples. Neural Comput. Applic. 36, 20067–20087. https://doi.org/10.1007/s00521-024-10298-9 (2024).
Ibraheem, A. M., Rahouma, K. H. & Hamed, H. F. A. 3PCNNB-Net: Three parallel CNN branches for breast cancer classification through histopathological images. J. Med. Biol. Eng. 41, 494–503. https://doi.org/10.1007/s40846-021-00620-4 (2021).
Wang, P. et al. Automatic classification of breast cancer histopathological images based on deep feature fusion and enhanced routing. Biomed. Signal Process. Control 65, 102341. https://doi.org/10.1016/j.bspc.2020.102341 (2021).
Huang, Z. et al. A novel nomogram for predicting locoregional recurrence risk in breast cancer patients treated with neoadjuvant chemotherapy and mastectomy. Radiother. Oncol. 161, 191–197. https://doi.org/10.1016/j.radonc.2021.06.015 (2021).
Huang, H. H. & Liang, Y. A novel cox proportional hazards model for high-dimensional genomic data in cancer prognosis. IEEE/ACM Trans. Comput. Biol. Bioinform. 18(5), 1821–1830. https://doi.org/10.1109/TCBB.2019.2961667 (2021).
B. U. Maheswari, A. A, A. Avvaru, A. Tandon and R. P. de Prado. "Interpretable Machine Learning Model for Breast Cancer Prediction Using LIME and SHAP". 2024 IEEE 9th International Conference for Convergence in Technology (I2CT), Pune, India, pp. 1–6, https://doi.org/10.1109/I2CT61223.2024.10543965. (2024).
Zhong, Z. et al. Identification and validation of a novel 16-gene prognostic signature for patients with breast cancer. Sci. Rep. 12, 12349. https://doi.org/10.1038/s41598-022-16575-8 (2022).
Nemade, V. & Fegade, V. machine learning techniques for breast cancer prediction. Procedia Comput. Sci. 218, 1314–1320. https://doi.org/10.1016/j.procs.2023.01.110 (2023).
Emam, M. M., Houssein, E. H., Samee, N. A., Alohali, M. A. & Hosney, M. E. Breast cancer diagnosis using optimized deep convolutional neural network based on transfer learning technique and improved Coati optimization algorithm. Expert Syst. Appl. 255, 124581. https://doi.org/10.1016/j.eswa.2024.124581 (2024).
Noman, S. M. et al. Leveraging survival analysis and machine learning for accurate prediction of breast cancer recurrence and metastasis. Sci. Rep. 15, 3728. https://doi.org/10.1038/s41598-025-87622-3 (2025).
Luo, H., Huang, J., Ju, H., Zhou, T., & Ding, W. M2EF-NNs: Multimodal Multi-instance Evidence Fusion Neural Networks for Cancer Survival Prediction. arXiv preprint arXiv:2408.04170. (2024).
Lv, Z., Lin, Y., Yan, R., Wang, Y. & Zhang, F. TransSurv: Transformer-based survival analysis model integrating histopathological images and genomic data for colorectal cancer. IEEE/ACM Trans. Comput. Biol. Bioinform. 20(6), 3411–3420. https://doi.org/10.1109/TCBB.2022.3199244 (2022).
Ge, R., Hu, X., Huang, R., Jia, G., Wang, Y., Gu, R., Li, Y. TTMFN: Two-stream Transformer-based Multimodal Fusion Network for Survival Prediction. arXiv preprint arXiv:2311.07033. (2023).
Gomaa, A. et al. Comprehensive multimodal deep learning survival prediction enabled by a transformer architecture: A multicenter study in glioblastoma. Neuro-Oncol. Adv. 6(1), vdae122 (2024).
Maigari, A., XinYing, C. & Zainol, Z. Multimodal deep learning breast cancer prognosis models: Narrative review on multimodal architectures and concatenation approaches. J. Med. Artif. Intell. https://doi.org/10.21037/jmai-24-146 (2025).
Othman, N. A., Abdel-Fattah, M. A. & Ali, A. T. A hybrid deep learning framework with decision-level fusion for breast cancer survival prediction. Big Data Cogn. Comput. 7(1), 50. https://doi.org/10.3390/bdcc7010050 (2023).
Witowski, J., Zeng, K. G., Cappadona, J., Elayoubi, J., Choucair, K., Chiru, E. D., Geras, K. J. Multi-modal AI for comprehensive breast cancer prognostication. arXiv preprint arXiv:2410.21256. (2024).
Al-Hejri, A. M. et al. A hybrid explainable federated-based vision transformer framework for breast cancer prediction via risk factors. Sci. Rep. 15, 18453. https://doi.org/10.1038/s41598-025-96527-0 (2025).
Al-Hejri, A. M. et al. ETECADx: Ensemble self-attention transformer encoder for breast cancer diagnosis using full-field digital X-ray breast images. Diagnostics 13(1), 89. https://doi.org/10.3390/diagnostics13010089 (2023).
Park, J., Witowski, J., Xu, Y., Trivedi, H., Gichoya, J. A multi-modal AI system for screening mammography: Integrating 2D and 3D imaging to improve breast cancer detection in a prospective clinical study. arXiv preprint arXiv:2504.05636. https://arxiv.org/abs/2504.05636 (2025).
Witowski, J., Zeng, K. G., Cappadona, J., Elayoubi, J. Multi-modal AI for comprehensive breast cancer prognostication. arXiv preprint arXiv:2410.21256. https://arxiv.org/abs/2410.21256 (2024).
Shen, Y., Park, J., Yeung, F., Goldberg, E. Leveraging transformers to improve breast cancer classification and risk assessment with multi-modal and longitudinal data. arXiv preprint arXiv:2311.03217. https://arxiv.org/abs/2311.03217 (2023).
Konz, N. et al. A competition, benchmark, code, and data for using artificial intelligence to detect lesions in digital breast tomosynthesis. JAMA Netw. Open 6(2), e230524. https://doi.org/10.1001/jamanetworkopen.2023.0524 (2023).
Bai, J., Posner, R., Wang, T., Yang, C. & Nabavi, S. Applying deep learning in digital breast tomosynthesis for automatic breast cancer detection: A review. Med. Image Anal. 71, 102049. https://doi.org/10.1016/j.media.2021.102049 (2021).
Abdelhafiz, D., Yang, C., Ammar, R., Nabavi, S. & Wang, T. Deep convolutional neural networks for mammography: Advances, challenges and applications. BMC Bioinformatics 20, 281. https://doi.org/10.1186/s12859-019-2823-6 (2019).
Abdelhafiz, D., Yang, C., Wang, T., Ammar, R. & Nabavi, S. Convolutional neural network for automated mass segmentation in mammography. BMC Bioinformatics 21, 52. https://doi.org/10.1186/s12859-020-3371-7 (2020).
Bai, J., Jin, A., Wang, T., Yang, C. & Nabavi, S. Feature fusion Siamese network for breast cancer detection comparing current and prior mammograms. Med. Phys. 49(6), 3654–3669. https://doi.org/10.1002/mp.15594 (2022).
Bai, J., Jin, A., Adams, M., Yang, C. & Nabavi, S. Unsupervised feature correlation model to predict breast abnormal variation maps in longitudinal mammograms. Comput. Med. Imaging Graph. 113, 102341. https://doi.org/10.1016/j.compmedimag.2024.102341 (2024).
Acknowledgements
The authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through Small Research Project under grant number RGP1/141/46.
Funding
The authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through Small Research Project under grant number RGP1/141/46.
Author information
Authors and Affiliations
Contributions
Saleem Malik: Methodology; Software; Model development; Validation; Writing – review & editing. S. Gopal Krishna Patro: Formal analysis; Statistical analysis; Survival analysis, methodology; Validation; Writing – review & editing. Ahmed Kateb Jumaah Al-Nussairi: Clinical expertise; Domain validation; Interpretation of oncology-related results; Writing – review & editing. Chandrakanta Mahanty: Data curation; Feature engineering; Comparative analysis; Visualization; Writing – review & editing. Mohamed Ghouse: Software; Model training; Hyperparameter optimization; Experimental evaluation; Writing – review & editing. Akila Thiyagarajan: Data preprocessing; Ablation studies; Experimental support; Manuscript formatting and compliance; Writing – review & editing. Ahmed Adnan Hadi: Software implementation; Code verification; Reproducibility checks; Supplementary material preparation; Writing – review & editing. Anwar Khan: Literature review; related work synthesis; Conceptual alignment with existing oncology studies; Writing – review & editing. Mohit Mittal: Results analysis, Validation; Cross-validation design; Response to reviewer comments; Writing – review & editing. Amanuel Zewude: Conceptualization; Supervision; Project administration; multi-modal data integration, experimental workflow and submission correspondence. All authors have read and approved the final manuscript and agree to be accountable for all aspects of the work.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Malik, S., Patro, S.G.K., Al-Nussairi, A.K.J. et al. A unified multi modal transformer framework for breast cancer recurrence prediction and survival analysis. Sci Rep (2026). https://doi.org/10.1038/s41598-026-37046-4
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-37046-4