Citation :

Sujitha Priya Duraipandi, Radha Venkatachalam, "A Logarithmic Mean Optimized EfficientNet with Joint Contrastive Learning for Improving Breast Cancer Detection from Mammogram Images," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 9, pp. 435-451, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I9P130

Abstract

Early prediction of breast cancer plays a critical role in improving patient survival rates and effective treatment planning. Mammography is the most often utilized imaging method for early breast cancer monitoring because of its ability to detect microcalcifications and subtle tissue abnormalities at an early stage. However, Mammography suffers from low sensitivity in dense breast tissue, overlapping structures and inter-observer variability, leading to high false positive rates and potential misdiagnosis. Recently, Deep Learning (DL) techniques have been utilised for mammography-based breast cancer detection, as they can automatically learn features from images. However, some models struggle with the conflation of malignant and benign areas, irrelevant feature extraction, and suboptimal training strategies. Their reliance on labelled data and classification-focused learning limits discriminative feature representation, resulting in poor differentiation of visually similar benign and malignant tissues. Hence, in this paper, an advanced DL approach is developed for efficient breast carcinoma prediction using mammography images. Initially, collected mammography images are augmented to enhance data diversity and reduce overfitting. Then, EfficientNet B7 with Joint Contrastive Learning (ENB7-JCL) is developed to learn discriminative visual representations. In ENB7-JCL, EfficientNetB7 is employed for deep feature extraction from mammography images, while JCL jointly optimizes contrastive and classification objectives by modelling similarity and dissimilarity relationships between samples. This improves the class separability and reduces misclassification of visually similar benign and malignant tissues. Additionally, the Logarithmic Mean Optimization Algorithm (LMOA) is applied to optimize the hyperparameters of EfficientNet B7 for effective training. Finally, a softmax classifier is used to perform breast cancer classification. The complete work is termed Optimized ENB7-JCL (OENB7-JCL). The experimental states that the proposed model achieves 94.85% and 95.12% of accuracy on the MIAS and INBreast dataset outperforming other existing models.

Keywords

Breast cancer, Mammography, Deep Learning, Feature extraction, Hyperparameter tuning.

References

[1] Adrienne G. Waks, and Eric P. Winer, “Breast Cancer Treatment: A Review,” JAMA, vol. 321, no. 3, pp. 288-300, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Joshi Zankhna Rajeshbhai, Mayank Bapna, and Bhagirath Patel, “Breast Cancer and its Treatments: A Comprehensive Review,” Asian Pacific Journal of Health Sciences, vol. 8, no. 2, pp. 90-94, 2021.
[CrossRef] [Publisher Link]

[3] Tracy-Ann Moo et al., “Overview of Breast Cancer Therapy,” PET Clinics, vol. 13, no. 3, pp. 339-354, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Ganesh N. Sharma et al., “Various Types and Management of Breast Cancer: An Overview,” Journal of Advanced Pharmaceutical Technology and Research, vol. 1, no. 2, pp. 109-126, 2010.
[Google Scholar] [Publisher Link]

[5] Christoph Engel, and Christine Fischer, “Breast Cancer Risks and Risk Prediction Models,” Breast Care, vol. 10, no. 1, pp. 7-12, 2015.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Subbhuraam Vinitha Sree et al., “Breast Imaging: A Survey,” World Journal of Clinical Oncology, vol. 2, no. 4, pp. 171-178, 2011.
[CrossRef] [Google Scholar] [Publisher Link]

[7] William E. Barlow et al., “Prospective Breast Cancer Risk Prediction Model for Women Undergoing Screening Mammography,” Journal of the National Cancer Institute, vol. 98, no. 17, pp. 1204-1214, 2006.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Lars J. Grimm et al., “Benefits and Risks of Mammography Screening in Women Ages 40 to 49 Years,” Journal of Primary Care and Community Health, vol. 13, pp. 1-6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Jocelyn Lippey et al., “Impact of a Risk based Breast Screening Decision Aid on Understanding, Acceptance and Decision Making,” NPJ Breast Cancer, vol. 9, no. 1, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Mostafa Alabousi et al., “Performance of Digital Breast Tomosynthesis, Synthetic Mammography, and Digital Mammography in Breast Cancer Screening: A Systematic Review and Meta-Analysis,” Journal of the National Cancer Institute, vol. 113, no. 6, pp. 680-690, 2021.
[CrossRef] [Google Scholar] [Publisher Link] 

[11] Rachel Farber et al., “Impact of Full-Field Digital Mammography Versus Film-Screen Mammography in Population Screening: A Meta-Analysis,” Journal of the National Cancer Institute, vol. 113, no. 1, pp. 16-26, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Dooman Arefan et al., “Deep Learning Modeling using Normal Mammograms for Predicting Breast Cancer Risk,” Medical Physics, vol. 47, no. 1, pp. 110-118, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Lulu Wang, “Mammography with Deep Learning for Breast Cancer Detection,” Frontiers in Oncology, vol. 14, pp. 1-16, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Zahra Jafari, and Ebrahim Karami, “Breast Cancer Detection in Mammography Images: A CNN-based Approach with Feature Selection,” Information, vol. 14, no. 7, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Olasubomi J. Omoleye et al., “External Evaluation of a Mammography-based Deep Learning Model for Predicting Breast Cancer in an Ethnically Diverse Population,” Radiology: Artificial Intelligence, vol. 5, no. 6, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Salman Zakareya, Habib Izadkhah, and Jaber Karimpour, “A New Deep-Learning-based Model for Breast Cancer Diagnosis from Medical Images,” Diagnostics, vol. 13, no. 11, pp. 1-23, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Amel Ali Alhussan et al., “Classification of Breast Cancer using Transfer Learning and Advanced Al-Biruni Earth Radius Optimization,” Biomimetics, vol. 8, no. 3, pp. 1-24, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Safak Kayikci, and Taghi M. Khoshgoftaar, “Breast Cancer Prediction using Gated Attentive Multimodal Deep Learning,” Journal of Big Data, vol. 10, no. 1, pp. 1-11, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Inzamam Mashood Nasir, Masad A. Alrasheedi, and Nasser Aedh Alreshidi, “MFAN: Multi-Feature Attention Network for Breast Cancer Classification,” Mathematics, vol. 12, no. 23, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Rengarajan Karthiga et al., “A Novel Exploratory Hybrid Deep Neural Network to Predict Breast Cancer for Mammography based on Wavelet Features,” Multimedia Tools and Applications, vol. 83, no. 24, pp. 65441-65467, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[21] Su Myat Thwin et al., “Attention-based Ensemble Network for Effective Breast Cancer Classification Over Benchmarks,” Technologies, vol. 12, no. 2, pp. 1-19, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Santoresh Kumari Dhimann, and Rakesh Yadav, “Patch-based Mammogram Cancer Detection using Attention-Driven CNNs,” Advances in Artificial Intelligence and Machine Learning, vol. 5, no. 4, pp. 4797-4818, 2025.
[CrossRef] [Google Scholar]

[23] Dilawar Shah et al., “Dual-View Deep Learning Model for Accurate Breast Cancer Detection in Mammograms,” International Journal of Intelligent Systems, vol. 2025, no. 1, pp. 1-14, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[24] S. Vijayalakshmi et al., “Innovative Deep Learning Classifiers for Breast Cancer Detection through Hybrid Feature Extraction Techniques,” Scientific Reports, vol. 15, no. 1, pp. 1-16, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Fajar Walayat et al., “Deep Learning-based Analysis of Mammographic Images for Breast Cancer Detection using Transfer Learning,” Healthcare Technology Letters, vol. 12, no. 1, pp. 1-20, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Long Jun Yan et al., “A Hybrid Deep Learning Model for Mammographic Breast Cancer Detection: Multi-Autoencoder and Attention Mechanisms,” Journal of Radiation Research and Applied Sciences, vol.  18, no. 3, pp. 1-17, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Aniruddha Deka et al., “An Improved Hybrid Feature Selection and Classification Framework for Breast Cancer Detection using Mammography Images,” Ain Shams Engineering Journal, vol. 17, no. 1, pp. 1-13, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Kevin Scott Mader, MIAS Mammography Dataset, Kaggle, 2017. [Online]. Available: https://www.kaggle.com/datasets/kmader/mias-mammography

[29] Ramanathan Subramanian, INbreast Dataset, Kaggle, 2020. https://www.kaggle.com/datasets/ramanathansp20/inbreast-dataset