Deep network ensemble in breast cancer recognition
DOI:
https://doi.org/10.24425/mms.2025.154682Abstract
This paper presents an ensemble-based approach that uses convolutional neural network (CNN) classifiers to recognise breast cancer from mammogram images. The proposed method integrates several well-performing CNN models, each selected on the basis of its individual efficiency, into a unified ensemble framework. The classifiers are aggregated using a majority voting strategy that considers the predicted class probabilities to make the final decision. This ensemble technique aims to enhance robustness, reduce the impact of misclassifications by individual models, and improve overall diagnostic reliability. The system was evaluated in a data set that contained mammograms classified into three diagnostic classes: malignant, benign, and normal. Numerical experiments demonstrated that the proposed approach significantly improves classification performance compared to classical machine learning methods and standalone CNN models. The ensemble achieved higher accuracy, sensitivity, and specificity, particularly in distinguishing between benign and malignant cases - a critical challenge in breast cancer diagnostics. These results highlight the potential of CNN ensembles in supporting more accurate computer-aided diagnosis in breast cancer screening.References
[1] Sung, H., Ferlay, J., Siegel, R. L., Laversanne, M., Soerjomataram, I., Jemal, A., & Bray, F. (2021). Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA a Cancer Journal for Clinicians, 71(3), 209-249. https://doi.org/10.3322/caac.21660
[2] http://www.eng.usf.edu/cvprg/mammography/database.html
[3] Osowski S., Szmurlo R., Matematyczne modele uczenia maszynowego w językach MATLAB i Python. 2023, OWPW, Warszawa
[4] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. In MIT Press eBooks. https://dl.acm.org/citation.cfm?id=3086952
[5] Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90. https://doi.org/10.1145/3065386
[6] Grochowski, M., Mikołajczyk, A., & Kwasigroch, A. (2019). Diagnosis of malignant melanoma by neural network ensemble-based system utilising hand-crafted skin lesion features. Metrology and Measurement Systems, 65-80. https://doi.org/10.24425/mms.2019.126327
[7] MATLAB user interface. MathWorks, 2024.
[8] He, K., Zhang, X., Ren, S., & Sun, J. (2015a). Deep residual learning for image recognition. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1512.03385
[9] Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017). Inception-V4, Inception-ResNet and the impact of residual connections on learning. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.11231
[10] Thawkar, S. (2022). Feature selection and classification in mammography using hybrid crow search algorithm with Harris hawks optimization. Journal of Applied Biomedicine, 42(4), 1094-1111. https://doi.org/10.1016/j.bbe.2022.09.001
[11] Swiderski, B., Osowski, S., Kurek, J., Kruk, M., Lugowska, I., Rutkowski, P., & Barhoumi, W. (2017). Novel methods of image description and ensemble of classifiers in application to mammogram analysis. Expert Systems with Applications, 81, 67-78. https://doi.org/10.1016/j.eswa.2017.03.031
[12] Swiderski, B., Gielata, L., Olszewski, P., Osowski, S., & Kołodziej, M. (2020). Deep neural system for supporting tumor recognition of mammograms using modified GAN. Expert Systems with Applications, 164, 113968. https://doi.org/10.1016/j.eswa.2020.113968
[13] Logan, J., Kennedy, P. J., & Catchpoole, D. (2023). A review of the machine learning datasets in mammography, their adherence to the FAIR principles and the outlook for the future. Scientific Data, 10(1). https://doi.org/10.1038/s41597-023-02430-6
[14] Ansar, W., Shahid, A. R., Raza, B., & Dar, A. H. (2020). Breast cancer detection and localization using MobileNet based transfer learning for mammograms. In Communications in Computer and Information Science (pp. 11-21). https://doi.org/10.1007/978-3-030-43364-2_2
[15] Alhsnony, F. H., & Sellami, L. (2024). Advancing breast cancer detection with convolutional neural networks: A comparative analysis of MIAS and DDSM datasets. In IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP) (pp. 194-199). https://doi.org/10.1109/atsip62566.2024.10638886
[16] Murty, P. S. R. C., Anuradha, C., Naidu, P. A., Mandru, D., Ashok, M., Atheeswaran, A., Rajeswaran, N., & Saravanan, V. (2024). Integrative hybrid deep learning for enhanced breast cancer diagnosis: leveraging the Wisconsin Breast Cancer Database and the CBIS-DDSM dataset. Scientific Reports, 14(1). https://doi.org/10.1038/s41598-024-74305-8
[17] Gil, F., Osowski, S., Świderski, B., & Słowińska, M. (2022). Ensemble of classifiers based on deep learning for medical image recognition. Metrology and Measurement Systems, 139-156. https://doi.org/10.24425/mms.2023.144400
[18] Mohammadi, S., & Livani, M. A. (2024). Enhanced breast mass segmentation in mammograms using a hybrid transformer UNet model. Computers in Biology and Medicine, 184, 109432. https://doi.org/10.1016/j.compbiomed.2024.109432
[19] Kuncheva, L. I. (2014). Combining Pattern Classifiers: Methods and Algorithms. John Wiley & Sons. https://doi.org/10.1002/9781118914564
[20] Kingma, D. P., & Ba, J. L. (2014). Adam: A method for stochastic optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1412.6980
[21] Tan P.N., Steinbach M., Kumar V., (2014) Introduction to Data Mining, Pearson Education Inc., Boston.
