Enhanced Multi-Modal Feature Fusion Algorithm for Early-Stage Cancer Detection: A Comparative Study of Optimization Strategies
Main Article Content
Abstract
This study presents an adaptive multi-modal fusion algorithm for early-stage cancer detection that dynamically integrates imaging, genomic, and clinical data using learned attention mechanisms. Unlike traditional approaches that treat fusion weights as fixed parameters, our method models them as probabilistic distributions, allowing adaptation to variations in data quality and modality availability in clinical environments. The key innovation is a meta-learning framework that predicts optimal fusion strategies based on the characteristics of incoming data. Experimental validation across 12,847 patients from eight medical centers demonstrates an AUROC of 0.947, with 89.3% sensitivity at 95% specificity. The algorithm exhibits particular robustness in managing minority cancer classes through hierarchical attention mechanisms that capture both local and global patterns. Comparative analysis against current state-of-the-art methods shows consistent performance improvements while maintaining computational efficiency suitable for clinical deployment.
Article Details
Section
How to Cite
References
1. A. Sharma, D. P. Yadav, H. Garg, M. Kumar, B. Sharma, and D. Koundal, "Bone cancer detection using feature extraction based machine learning model," Computational and Mathematical Methods in Medicine, vol. 2021, no. 1, p. 7433186, 2021.
2. Y. Xiao, J. Wu, Z. Lin, and X. Zhao, "Breast cancer diagnosis using an unsupervised feature extraction algorithm based on deep learning," In 2018 37th Chinese Control Conference (CCC), July, 2018, pp. 9428-9433. doi: 10.23919/chicc.2018.8483140
3. F. Z. Nakach, A. Idri, and E. Goceri, "A comprehensive investigation of multimodal deep learning fusion strategies for breast cancer classification," Artificial Intelligence Review, vol. 57, no. 12, p. 327, 2024.
4. M. A. Khan, A. Khan, M. Alhaisoni, A. Alqahtani, S. Alsubai, M. Alharbi, and R. ... Damaševičius, "Multimodal brain tumor detection and classification using deep saliency map and improved dragonfly optimization algorithm," International Journal of Imaging Systems and Technology, vol. 33, no. 2, pp. 572-587, 2023.
5. D. Sarwinda, A. Bustamam, R. H. Paradisa, T. Argyadiva, and W. Mangunwardoyo, "Analysis of deep feature extraction for colorectal cancer detection," In 2020 4th International Conference on Informatics and Computational Sciences (ICICoS), November, 2020, pp. 1-5. doi: 10.1109/icicos51170.2020.9298990
6. B. Karthikeyan, N. Seethalakshmi, V. Nandhini, D. Vinoth, P. Muthusamy, and K. Bellam, "Multimodal feature fusion using optimal transfer learning approach for lung cancer detection and classification on CT images," Full Length Article, vol. 12, no. 2024, pp. 84-4, 2024.
7. M. Alamgeer, N. Alruwais, H. M. Alshahrani, A. Mohamed, and M. Assiri, "Dung beetle optimization with deep feature fusion model for lung cancer detection and classification," Cancers, vol. 15, no. 15, p. 3982, 2023. doi: 10.3390/cancers15153982
8. S. Hussain, M. Ali, U. Naseem, D. B. A. Avalos, S. Cardona-Huerta, and J. G. Tamez-Pena, "Multiview multimodal feature fusion for breast cancer classification using deep learning," IEEE Access, 2024.
9. S. Sharmin, T. Ahammad, M. A. Talukder, and P. Ghose, "A hybrid dependable deep feature extraction and ensemble-based machine learning approach for breast cancer detection," IEEE Access, vol. 11, pp. 87694-87708, 2023. doi: 10.1109/access.2023.3304628
10. J. Zheng, D. Lin, Z. Gao, S. Wang, M. He, and J. Fan, "Deep learning assisted efficient AdaBoost algorithm for breast cancer detection and early diagnosis," IEEE Access, vol. 8, pp. 96946-96954, 2020. doi: 10.1109/access.2020.2993536