Abstract

 Breast cancer is a heterogeneous disease characterized by molecular complexity. This research utilized three genetic expression profiles—gene expression, deoxyribonucleic acid (DNA) methylation, and micro ribonucleic acid (miRNA) expression—to deepen the understanding of breast cancer biology and contribute to the development of a reliable survival rate prediction model. During the preprocessing phase, principal component analysis (PCA) was applied to reduce the dimensionality of each dataset before computing consensus features across the three omics datasets. By integrating these datasets with the consensus features, the model's ability to uncover deep connections within the data was significantly improved. The proposed multimodal deep learning multigenetic features (MDL-MG) architecture incorporates a custom attention mechanism (CAM), bidirectional long short-term memory (BLSTM), and convolutional neural networks (CNNs). Additionally, the model was optimized to handle contrastive loss by extracting distinguishing features using a Siamese network (SN) architecture with a Euclidean distance metric. To assess the effectiveness of this approach, various evaluation metrics were applied to the cancer genome atlas (TCGA-BREAST) dataset. The model achieved 100% accuracy and demonstrated improvements in recall (16.2%), area under the curve (AUC) (29.3%), and precision (10.4%) while reducing complexity. These results highlight the model's efficacy in accurately predicting cancer survival rates.

Keywords

Breast cancer, Genetic expression, Survival prediction, Multimodal deep learning, Siamese network, Principal component analysis.

References

[1] https://www.nomisweb.co.uk/datasets/mortsa. Accessed 22 February 2025.

[2] Giaquinto AN, Sung H, Newman LA, Freedman RA, Smith RA, Star J, et al. Breast cancer statistics 2024. CA: a Cancer Journal for Clinicians. 2024; 74(6):477-95.

[3] Kayikci S, Khoshgoftaar TM. Breast cancer prediction using gated attentive multimodal deep learning. Journal of Big Data. 2023; 10(1):1-11.

[4] Hernandez-cruz N, Saha P, Sarker MM, Noble JA. Review of federated learning and machine learning-based methods for medical image analysis. Big Data and Cognitive Computing. 2024; 8(9):1-37.

[5] Hao Y, Jing XY, Sun Q. Cancer survival prediction by learning comprehensive deep feature representation for multiple types of genetic data. BMC Bioinformatics. 2023; 24(1):1-16.

[6] American Cancer Society. Cancer prevention & early detection facts & figures 2023-2024.

[7] Cardoso MJ, Poortmans P, Senkus E, Gentilini OD, Houssami N. Breast cancer highlights from 2023: knowledge to guide practice and future research. The Breast. 2024; 74:1-11.

[8] Yu P. The future prospects of deep learning and neural networks: artificial intelligence's impact on education. Applied and Computational Engineering. 2024; 33:94-101.

[9] Zhang H, Xi Q, Zhang F, Li Q, Jiao Z, Ni X. Application of deep learning in cancer prognosis prediction model. Technology in Cancer Research & Treatment. 2023; 22:1-10.

[10] Jain R, Sarvakar K, Patel C, Mishra S. An exhaustive examination of deep learning algorithms: present patterns and prospects for the future. GRENZE International Journal of Engineering and Technology. 2024; 10(1):105-11.

[11] Masoud TD, Abdulazeez AM. Deep learning classification algorithms applications: a review. Indonesian Journal of Computer Science. 2024; 13(3):4287-11.

[12] Dandekar AR, Sharma A, Mishra JK. Optimized federated learning algorithm for breast cancer detection using the marine predators algorithm. Journal of Electrical Systems. 2024; 20(1):911-20.https://journal.esrgroups.org/jes/article/view/842/835

[13] Zhu Z, Wang SH, Zhang YD. A survey of convolutional neural network in breast cancer. Computer Modeling in Engineering & Sciences: CMES. 2023; 136(3):2127-72.

[14] Karuppasamy A, Abdesselam A, Hedjam R, Zidoum H, Al-bahri M. Recent CNN-based techniques for breast cancer histology image classification. The Journal of Engineering Research [TJER]. 2022; 19(1):41-53.

[15] Elwahsh H, Tawfeek MA, Abdel-aziz AA, Mahmood MA, Alsabaan M, El-shafeiy E. A new approach for cancer prediction based on deep neural learning. Journal of King Saud University-Computer and Information Sciences. 2023; 35(6):1-12.

[16] Vasanthakumari RK, Nair RV, Krishnappa VG. Improved learning by using a modified activation function of a convolutional neural network in multi-spectral image classification. Machine Learning with Applications. 2023; 14:1-13.

[17] Taye MM. Theoretical understanding of convolutional neural network: concepts, architectures, applications, future directions. Computation. 2023; 11(3):1-23.

[18] Rakhshan P. Breast cancer detection basedon CNN and federated learningusing embedded devices. School of Innovation Design and Engineering, Mälardalens University, Sweden.2023.

[19] Salim AT, Khammas BM. Performance evaluation of deep learning techniques in the detection of IOT malware. Iraqi Journal of Information and Communication Technology. 2023; 6(3):12-25.

[20] Maurya R, Aggarwal D, Gopalakrishnan T, Pandey NN. Enhancing deep neural network convergence and performance: a hybrid activation function approach by combining ReLU and ELU activation function. In second international conference on informatics 2023 (pp. 1-5). IEEE.

[21] Akgül İ. Activation functions used in artificial neural networks. Book: Academic Studies in Engineering. Geçe Kitaplılğı: Turkey. 2023:41-58.

[22] Salehin I, Kang DK. A review on dropout regularization approaches for deep neural networks within the scholarly domain. Electronics. 2023; 12(14):1-23.

[23] Sinha J, Manollas M. Efficient deep CNN-BiLSTM model for network intrusion detection. In proceedings of the 3rd international conference on artificial intelligence and pattern recognition 2020 (pp. 223-31). ACM.

[24] Yılmaz RE, Serbes G. Breast cancer detection using transformer and BiLSTM based ensemble learning. In 31st signal processing and communications applications conference 2023 (pp. 1-4). IEEE.

[25] Yousaf K, Nawaz T. A deep learning-based approach for inappropriate content detection and classification of YouTube videos. IEEE Access. 2022; 10:16283-98.

[26] Farhan BI, Jasim AD. Improving detection for intrusion using deep LSTM with hybrid feature selection method. Iraqi Journal of Information and Communication Technology. 2023; 6(1):40-50.

[27] Agana MA, Agwu CO, Ukpoho NA. Breast cancer prediction and control using BiLSTM and two-dimensional convolutional neural network. International Journal of Software Innovation (IJSI). 2023; 11(1):1-9.

[28] Manshahia MS, Litvinchev IS, Weber GW, Thomas JJ, Vasant P. Human-assisted Intelligent Computing: Modeling, Simulations and Applications. IOP Publishing; 2023.

[29] De SCA, Colombini EL. Attention, please! a survey of neural attention models in deep learning. Artificial Intelligence Review. 2022; 55(8):6037-124.

[30] Xie S, Zhang Y, Lv D, Chen X, Lu J, Liu J. A new improved maximal relevance and minimal redundancy method based on feature subset. The Journal of Supercomputing. 2023; 79(3):3157-80.

[31] Lu M, Yin J, Zhu Q, Lin G, Mou M, Liu F, et al. Artificial intelligence in pharmaceutical sciences. Engineering. 2023; 27:37-69.

[32] Syms C. Principal components analysis. Elsevier. 2008: 2940-9.

[33] Rahbar K, Taheri F. Enhancing image retrieval through entropy-based deep metric learning. Multimedia Tools and Applications. 2024:1-27.

[34] Caliskan A, O’brien C, Panduru K, Walsh J, Riordan D. An efficient siamese network and transfer learning-based predictive maintenance system for more sustainable manufacturing. Sustainability. 2023; 15(12):1-23.

[35] De RGH, Papa JP. Learning to weight similarity measures with siamese networks: a case study on optimum-path forest. Optimum-Path Forest. 2022:155-73.

[36] Tseng YJ, Huang CE, Wen CN, Lai PY, Wu MH, Sun YC, et al. Predicting breast cancer metastasis by using serum biomarkers and clinicopathological data with machine learning technologies. International Journal of Medical Informatics. 2019; 128:79-86.

[37] Magna AA, Allende-cid H, Taramasco C, Becerra C, Figueroa RL. Application of machine learning and word embeddings in the classification of cancer diagnosis using patient anamnesis. IEEE Access. 2020; 8:106198-213.

[38] Tong L, Wu H, Wang MD. Integrating multi-omics data by learning modality invariant representations for improved prediction of overall survival of cancer. Methods. 2021; 189:74-85.

[39] Arya N, Saha S. Multi-modal advanced deep learning architectures for breast cancer survival prediction. Knowledge-Based Systems. 2021; 221:106965.

[40] Vale-silva LA, Rohr K. Long-term cancer survival prediction using multimodal deep learning. Scientific Reports. 2021; 11(1):1-12.

[41] Chen RJ, Lu MY, Williamson DF, Chen TY, Lipkova J, Noor Z, et al. Pan-cancer integrative histology-genomic analysis via multimodal deep learning. Cancer Cell. 2022; 40(8):865-78.

[42] Wu X, Shi Y, Wang M, Li A. CAMR: cross-aligned multimodal representation learning for cancer survival prediction. Bioinformatics. 2023; 39(1):1-8.

[43] Alsalman H, Al-rakhami MS, Alfakih T, Hassan MM. Federated learning approach for breast cancer detection based on DCNN. IEEE Access. 2024; 12:40114-38

[44] Wang Z, Lin R, Li Y, Zeng J, Chen Y, Ouyang W, et al. Deep learning-based multi-modal data integration enhancing breast cancer disease-free survival prediction. Precision Clinical Medicine. 2024; 7(2):1-20.

[45] Yang Z, Liu H, Wang X. A multimodal object-level contrast learning method for cancer survival risk prediction. In proceedings of the 1st international workshop on multimedia computing for health and medicine. 2024(pp.64-69).

[46] Rintala TJ, Napolitano F, Fortino V. Multi-task deep latent spaces for cancer survival and drug sensitivity prediction. Bioinformatics. 2024; 40(Supplement_2):182-9.

[47] Gomaa A, Huang Y, Hagag A, Schmitter C, Höfler D, Weissmann T, et al. Comprehensive multimodal deep learning survival prediction enabled by a transformer architecture: a multicenter study in glioblastoma. Neuro-Oncology Advances. 2024; 6(1):1-14.

[48] Zhang G, Ma C, Yan C, Luo H, Wang J, Liang W, et al. Multimodal deep learning for cancer survival prediction: a review. Current Bioinformatics. 2025; 20(4):299-22.

[49] Wang B, Mezlini AM, Demir F, Fiume M, Tu Z, Brudno M, et al. Similarity network fusion for aggregating data types on a genomic scale. Nature Methods. 2014; 11(3):333-7.

[50] https://www.cancer.gov/tcga. Accessed 22 February 2025.

[51] Abdi H, Williams LJ. Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics. 2010; 2(4):433-59.

[52] Ghojogh B, Crowley M, Karray F, Ghodsi A. Principal component analysis. In elements of dimensionality reduction and manifold learning 2023 (pp. 123-54). Cham: Springer International Publishing.

[53] Istighosah M, Sunyoto A, Hidayat T. Breast cancer detection in histopathology images using ResNet101 architecture. Sinkron: Jurnal Dan Penelitian Teknik Informatika. 2023; 7(4):2138-49.

[54] Paoletti ME, Haut JM, Tao X, Plaza J, Plaza A. FLOP-reduction through memory allocations within CNN for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing. 2020; 59(7):5938-52.

[55] Patel C, Bhatt D, Sharma U, Patel R, Pandya S, Modi K et al. DBGC: dimension-based generic convolution block for object recognition. Sensors. 2022; 22(5):1-25.

[56] Wagner J. Generalised model-independent characterisation of strong gravitational lenses. Astronomy & Astrophysics. 2022; 663:1-13.

[57] Hamilton RI, Papadopoulos PN. Using SHAP values and machine learning to understand trends in the transient stability limit. IEEE Transactions on Power Systems. 2023; 39(1):1384-97.

Cite this article