Abstract

Globally, breast cancer is the most common form of cancer and affects millions of women each year. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is considered an effective modality for diagnosing breast cancer. However, despite its widespread use in breast cancer classification, the diagnostic performance of DCE-MRI remains suboptimal, with frequent occurrences of misclassification. This article introduces a deep learning (DL) approach, termed the dual attention deep convolutional neural network (DADCNN), for classifying breast cancer as benign or malignant. The proposed method is evaluated using the DCE-MRI, RIDER Breast MRI, and Breast MRI datasets. Preprocessing is conducted through data augmentation techniques to increase dataset variability. The augmented data is then passed through a feature extraction process utilizing DenseNet-121 and ResNet-101 architectures. The extracted features are fused using a feature fusion model, followed by classification to determine the cancer type. The DADCNN model effectively manages long input features by selectively focusing on the most relevant aspects of the breast lesion, thereby enhancing classification accuracy. Experimental results demonstrate that the proposed approach outperforms existing methods, including the multi-modality network (MUM-Net) and the multivariate rocket algorithm, across all evaluated performance metrics. The DADCNN approach improves classification accuracy of 0.954, 0.992 and 0.990 on the DCE-MRI, Breast MRI and Rider Breast MRI datasets respectively by leveraging dual attention mechanisms to focus on the most relevant features associated with breast cancer.

Keywords

Breast cancer classification, DCE-MRI, Deep learning, Dual attention mechanism, Feature fusion, Dual attention deep convolutional neural network.

References

[1] Sahu A, Das PK, Meher S. Recent advancements in machine learning and deep learning-based breast cancer detection using mammograms. Physica Medica. 2023; 114:1-16.

[2] Chen H, Wang N, Du X, Mei K, Zhou Y, Cai G. Classification prediction of breast cancer based on machine learning. Computational Intelligence and Neuroscience. 2023; 2023(1):1-9.

[3] Obayya M, Maashi MS, Nemri N, Mohsen H, Motwakel A, Osman AE, et al. Hyperparameter optimizer with deep learning-based decision-support systems for histopathological breast cancer diagnosis. Cancers. 2023; 15(3):1-19.

[4] Park HS, Chong Y, Lee Y, Yim K, Seo KJ, Hwang G, et al. Deep learning-based computational cytopathologic diagnosis of metastatic breast carcinoma in pleural fluid. Cells. 2023; 12(14):1-14.

[5] Atban F, Ekinci E, Garip Z. Traditional machine learning algorithms for breast cancer image classification with optimized deep features. Biomedical Signal Processing and Control. 2023; 81:104534.

[6] Zuo D, Yang L, Jin Y, Qi H, Liu Y, Ren L. Machine learning-based models for the prediction of breast cancer recurrence risk. BMC Medical Informatics and Decision Making. 2023; 23(1):1-14.

[7] Misra S, Yoon C, Kim KJ, Managuli R, Barr RG, Baek J, et al. Deep learning‐based multimodal fusion network for segmentation and classification of breast cancers using B‐mode and elastography ultrasound images. Bioengineering & Translational Medicine. 2023; 8(6):1-13.

[8] Kwak D, Choi J, Lee S. Rethinking breast cancer diagnosis through deep learning based image recognition. Sensors. 2023; 23(4):1-17.

[9] Sharma A, Weitz P, Wang Y, Liu B, Vallon-christersson J, Hartman J, et al. Development and prognostic validation of a three-level NHG-like deep learning-based model for histological grading of breast cancer. Breast Cancer Research. 2024; 26(1):1-13.

[10] Sharma N, Sharma KP, Mangla M, Rani R. Breast cancer classification using snapshot ensemble deep learning model and t-distributed stochastic neighbor embedding. Multimedia Tools and Applications. 2023; 82(3):4011-29.

[11] Mahesh TR, Vinoth KV, Vivek V, Karthick RKM, Sindhu MG. Early predictive model for breast cancer classification using blended ensemble learning. International Journal of System Assurance Engineering and Management. 2024; 15(1):188-97.

[12] Zourhri M, Hamida S, Akouz N, Cherradi B, Nhaila H, El KM. Deep learning technique for classification of breast cancer using ultrasound images. In 3rd international conference on innovative research in applied science, engineering and technology (IRASET) 2023 (pp. 1-8). IEEE.

[13] Hamedani-karazmoudehfar F, Tavakkoli-moghaddam R, Tajally AR, Aria SS. Breast cancer classification by a new approach to assessing deep neural network-based uncertainty quantification methods. Biomedical Signal Processing and Control. 2023; 79:104057.

[14] Sahu A, Das PK, Meher S. An efficient deep learning scheme to detect breast cancer using mammogram and ultrasound breast images. Biomedical Signal Processing and Control. 2024; 87:105377.

[15] Chakravarthy SS, Bharanidharan N, Rajaguru H. Deep learning-based metaheuristic weighted k-nearest neighbor algorithm for the severity classification of breast cancer. IRBM. 2023; 44(3):100749.

[16] Jadoon EK, Khan FG, Shah S, Khan A, Elaffendi M. Deep learning-based multi-modal ensemble classification approach for human breast cancer prognosis. IEEE Access. 2023; 11:85760-9.

[17] Subramanian AA, Venugopal JP. A deep ensemble network model for classifying and predicting breast cancer. Computational Intelligence. 2023; 39(2):258-82.

[18] Uddin KM, Biswas N, Rikta ST, Dey SK. Machine learning-based diagnosis of breast cancer utilizing feature optimization technique. Computer Methods and Programs in Biomedicine Update. 2023; 3:1-17.

[19] Qawqzeh YK, Alourani A, Ghwanmeh S. An improved breast cancer classification method using an enhanced adaboost classifier. International Journal of Advanced Computer Science and Applications. 2023; 14(1):473-8.

[20] Kaur H. Dense convolutional neural network based deep learning framework for the diagnosis of breast cancer. Wireless Personal Communications. 2023; 132(3):1765-80.

[21] Li Y, Fan Y, Xu D, Li Y, Zhong Z, Pan H, et al. Deep learning radiomic analysis of DCE-MRI combined with clinical characteristics predicts pathological complete response to neoadjuvant chemotherapy in breast cancer. Frontiers in Oncology. 2023; 12:1-13.

[22] Sun L, Tian H, Ge H, Tian J, Lin Y, Liang C, et al. Cross-attention multi-branch CNN using DCE-MRI to classify breast cancer molecular subtypes. Frontiers in Oncology. 2023; 13:1-12.

[23] Carvalho ED, Da SNOP, De CFAO. Deep learning-based tumor segmentation and classification in breast MRI with 3TP method. Biomedical Signal Processing and Control. 2024; 93:106199.

[24] Gao J, Zhong X, Li W, Li Q, Shao H, Wang Z, et al. Attention‐based deep learning for the preoperative differentiation of axillary lymph node metastasis in breast cancer on DCE‐MRI. Journal of Magnetic Resonance Imaging. 2023; 57(6):1842-53.

[25] Park GE, Kim SH, Nam Y, Kang J, Park M, Kang BJ. 3D breast cancer segmentation in DCE‐MRI using deep learning with weak annotation. Journal of Magnetic Resonance Imaging. 2024; 59(6):2252-62.

[26] Prinzi F, Orlando A, Gaglio S, Vitabile S. Breast cancer classification through multivariate radiomic time series analysis in DCE-MRI sequences. Expert Systems with Applications. 2024; 249:1-12.

[27] Debbi K, Habert P, Grob A, Loundou A, Siles P, Bartoli A, et al. Radiomics model to classify mammary masses using breast DCE-MRI compared to the BI-RADS classification performance. Insights in to Imaging. 2023; 14(1):1-9.

[28] Hasan AM, Qasim AF, Jalab HA, Ibrahim RW. Breast cancer MRI classification based on fractional entropy image enhancement and deep feature extraction. Baghdad Science Journal. 2023; 20(1).

[29] Zhang Y, Liu YL, Nie K, Zhou J, Chen Z, Chen JH, et al. Deep learning-based automatic diagnosis of breast cancer on MRI using mask R-CNN for detection followed by ResNet50 for classification. Academic Radiology. 2023; 30: S161-71.

[30] Wang W, Wang Y. Deep learning-based modified YOLACT algorithm on magnetic resonance imaging images for screening common and difficult samples of breast cancer. Diagnostics. 2023; 13(9):1-15.

[31] Hasan AM, Al-waely NK, Aljobouri HK, Jalab HA, Ibrahim RW, Meziane F. Molecular subtypes classification of breast cancer in DCE-MRI using deep features. Expert Systems with Applications. 2024; 236:121371.

[32] Iqbal A, Sharif M. BTS-ST: swin transformer network for segmentation and classification of multimodality breast cancer images. Knowledge-Based Systems. 2023; 267:110393.

[33] Zhao X, Liao Y, Xie J, He X, Zhang S, Wang G, et al. BreastDM: a DCE-MRI dataset for breast tumor image segmentation and classification. Computers in Biology and Medicine. 2023; 164:107255.

[34] Verma M, Abdelrahman L, Collado-mesa F, Abdel-mottaleb M. Multimodal spatiotemporal deep learning framework to predict response of breast cancer to neoadjuvant systemic therapy. Diagnostics. 2023; 13(13):1-11.

[35] Rehman NU, Wang J, Weiyan H, Ali I, Akbar A, Assam M, et al. Edge of discovery: enhancing breast tumor MRI analysis with boundary-driven deep learning. Biomedical Signal Processing and Control. 2024; 95:1-15.

[36] https://www.kaggle.com/datasets/kaillashkumar/dce-mri-breast-cancer-dataset. Accessed 20 May 2025.

[37] https://wiki.cancerimagingarchive.net/display/Public/RIDER+Breast+MRI. Accessed 20 May 2025.

[38] https://www.kaggle.com/datasets/uzairkhan45/breast-cancer-patients-mris. Accessed 20 May 2025.

[39] Jabeen K, Khan MA, Balili J, Alhaisoni M, Almujally NA, Alrashidi H, et al. BC2NetRF: breast cancer classification from mammogram images using enhanced deep learning features and equilibrium-Jaya controlled Regula Falsi-based features selection. Diagnostics. 2023; 13(7):1-22.

[40] Ranjitha KV, Pushphavathi TP. Analysis on improved gaussian-wiener filtering technique and GLCM based feature extraction for breast cancer diagnosis. Procedia Computer Science. 2024; 235:2857-66.

[41] Arulananth TS, Prakash SW, Ayyasamy RK, Kavitha VP, Kuppusamy PG, Chinnasamy P. Classification of paediatric pneumonia using modified DenseNet-121 deep-learning model. IEEE Access. 2024; 12:35716-27.

[42] Kalshetty R, Parveen A. Abnormal event detection model using an improved ResNet101 in context aware surveillance system. Cognitive Computation and Systems. 2023; 5(2):153-67.

[43] Islam MM, Nooruddin S, Karray F, Muhammad G. Multi-level feature fusion for multimodal human activity recognition in internet of healthcare things. Information Fusion. 2023; 94:17-31.

Cite this article