An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis

Ragheed Mokhtar; Mahir Kaya

doi:10.54287/gujsa.1804559

An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis

Abstract

Breast cancer continues to be one of the most prevalent as well as life-threatening malignancies because it affects women globally. Ultrasound images get diagnostic interpretation that is customarily variable, with limitations in sensitivity and specificity. For breast ultrasound image classification, we propose a novel fully optimized Convolutional Neural Network (CNN) architecture. This study's classification includes three clinically important categories: normal, malignant, and benign. We used the Breast Ultrasound Images (BUSI) dataset, and we tackled intrinsic issues like small dataset size, class imbalance, and inter-class similarity via a diverse augmentation pipeline. The proposed CNN architecture integrates state-of-the-art deep learning techniques that include hierarchical feature extraction, attention mechanisms, batch normalization, dropout regularization, along with adaptive learning rates. The best-performing model reached a test accuracy of 99.33%, demonstrating the effectiveness of the proposed approach. This performance gain was obtained through systematic hyperparameter optimization involving the number of convolutional layers, learning rates, batch sizes, and input image resolutions. Although trained without pre-existing knowledge, the model showed similar performance when evaluated against popular transfer learning models like MobileNetV2, VGG16, VGG19, InceptionV3, ResNet50, EfficientNetB0, DenseNet121, and Xception. The proposed model, interpretable through Grad-CAM, effectively focuses on disease-related regions and enables specialists to make fast and reliable decisions.

Keywords

References

Alotaibi, M., Aljouie, A., Alluhaidan, N., Qureshi, W., Almatar, H., Alduhayan, R., Alsomaie, B., & Almazroa, A. (2023). Breast cancer classification based on convolutional neural network and image fusion approaches using ultrasound images. Heliyon, 9(11), e22406. https://doi.org/10.1016/j.heliyon.2023.e22406
Alrubaie, H., Aljobouri, H. K., AL-Jobawi, Z. J., & Çankaya, I. (2023). Convolutional neural network deep learning model for improved ultrasound breast tumor classification. Al-Nahrain Journal for Engineering Sciences, 26(2), 57–62. https://doi.org/10.29194/njes.26020057
Arooj, S., Zubair, M., Khan, M. F., Alissa, K., Khan, M. A., & Mosavi, A. (2022). Breast cancer detection and classification empowered with transfer learning. Frontiers in Public Health, 10, 924432. https://doi.org/10.3389/fpubh.2022.924432
Boulenger, A., Luo, Y., Zhang, C., Zhao, C., Gao, Y., Xiao, M., Zhu, Q., & Tang, J. (2023). Deep learning-based system for automatic prediction of triple-negative breast cancer from ultrasound images. Medical and Biological Engineering and Computing, 61(2), 567–578. https://doi.org/10.1007/s11517-022-02728-4
Cheyi, J., & Çetin-Kaya, Y. (2024). Advanced CNN-based classification and segmentation for enhanced breast cancer ultrasound imaging. Gazi University Journal of Science Part A: Engineering and Innovation, 11(4), 647–667. https://doi.org/10.54287/gujsa.1529857
Ciobotaru, A., Bota, M. A., Goța, D. I., & Miclea, L. C. (2023). Multi-Instance Classification of Breast Tumor Ultrasound Images Using Convolutional Neural Networks and Transfer Learning. Bioengineering, 10(12). https://doi.org/10.3390/bioengineering10121419
Çetin-Kaya, Y. (2024). Equilibrium optimization-based ensemble CNN framework for breast cancer multiclass classification using histopathological image. Diagnostics, 14(19), 2253. https://doi.org/10.3390/diagnostics14192253
Daoud, M. I., Abdel-Rahman, S., & Alazrai, R. (2019, November 26-29). Breast ultrasound image classification using a pre-trained convolutional neural network. In: Proceedings of the 2019 15th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) (pp. 167–171), Sorrento, Italy. https://doi.org/10.1109/SITIS.2019.00037

Daoud, M. I., Abdel-Rahman, S., Bdair, T. M., Al-Najar, M. S., Al-Hawari, F. H., & Alazrai, R. (2020). Breast tumor classification in ultrasound images using combined deep and handcrafted features. Sensors, 20(23), 6838. https://doi.org/10.3390/s20236838
Eroğlu, Y., Yildirim, M., & Çinar, A. (2021). Convolutional neural networks based classification of breast ultrasonography images by hybrid method with respect to benign, malignant, and normal using mRMR. Computers in Biology and Medicine, 133, 104407. https://doi.org/10.1016/j.compbiomed.2021.104407
Fujioka, T., Katsuta, L., Kubota, K., Mori, M., Kikuchi, Y., Kato, A., Oda, G., Nakagawa, T., & Tateishi, U (2020). Classification of breast masses on ultrasound shear wave elastography using convolutional neural networks. Ultrasonic Imaging, 42(4–5), 213–220. https://doi.org/10.1177/0161734620932609
Güldoğan, E., Ucuzal, H., Küçükakçalı, Z., & Çolak, C. (2021). Transfer learning-based classification of breast cancer using ultrasound images. Middle Black Sea Journal of Health Science, 7(1), 74–80. https://doi.org/10.19127/mbsjohs.876667
Hijab, M. A., Rushdi, M., Gomaa, M. M., & Eldeib, A. (2019, October 17-19). Breast cancer classification in ultrasound images using transfer learning. In: Proceedings of the 2019 Fifth International Conference on Advances in Biomedical Engineering (ICABME), Tripoli, Lebanon https://doi.org/10.1109/ICABME47164.2019.8940291
Karthik, R., Menaka, R., Kathiresan, G. S., Anirudh, M., & Nagharjun, M. (2022). Gaussian dropout based stacked ensemble CNN for classification of breast tumor in ultrasound images. IRBM, 43(6), 715–733. https://doi.org/10.1016/j.irbm.2021.10.002
Kaya, M., & Çetin-Kaya, Y. (2024). A novel ensemble learning framework based on a genetic algorithm for the classification of pneumonia. Engineering Applications of Artificial Intelligence, 133, 108494. https://doi.org/10.1016/j.engappai.2024.108494
Kaya, M. (2025). Efficient diagnosis of retinal diseases using convolutional neural networks. Gazi University Journal of Science Part A: Engineering and Innovation, 12(1), 15–35. https://doi.org/10.54287/gujsa.1592915
Latif, G., Butt, M. O., Al Anezi, F. Y., & Alghazo, J. (2020, October 14-15). Ultrasound image despeckling and detection of breast cancer using deep CNN. In: Proceedings of the 2020 RIVF International Conference on Computing and Communication Technologies (RIVF), Ho Chi Minh City, Vietnam. https://doi.org/10.1109/RIVF48685.2020.9140767
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88. https://doi.org/10.1016/j.media.2017.07.005
Liu, H., Cui, G., Luo, Y., Guo, Y., Zhao, L., Wang, Y., Subaşı, A., Doğan, S., & Tuncer, T. (2022). Artificial intelligence-based breast cancer diagnosis using ultrasound images and grid-based deep feature generator. International Journal of General Medicine, 15, 2271–2282. https://doi.org/10.2147/IJGM.S347491
Nikmah, T. L., Syafei, R. M., & Anisa, D. N. (2024). Inception ResNet v2 for early detection of breast cancer in ultrasound images. Journal of Information System Exploration and Research, 2(2). https://doi.org/10.52465/joiser.v2i2.439
Özatılgan, A., & Kaya, M. (2024). A lightweight convolutional neural network for classification of brain tumors using magnetic resonance imaging. Sakarya University Journal of Computer and Information Sciences, 7(3), 482–493. https://doi.org/10.35377/saucis.1518139
Pathan, R. K., Alam, F. I., Yasmin, S., Hamd, Z. Y., Aljuaid, H., Khandaker, M. U., & Lau, S. L. (2022). Breast cancer classification by using multi-headed convolutional neural network modeling. Healthcare, 10(12), 2367. https://doi.org/10.3390/healthcare10122367
Saba, T., Abunadi, I., Sadad, T., Khan, A. R., & Bahaj, S. A. (2022). Optimizing the transfer-learning with pretrained deep convolutional neural networks for first stage breast tumor diagnosis using breast ultrasound visual images. Microscopy Research and Technique, 85, 1444–1453. https://doi.org/10.1002/jemt.24008
Sahu, P., Das, K., & Meher, S. (2024). An efficient deep learning scheme to detect breast cancer using mammogram and ultrasound breast images. Biomedical Signal Processing and Control, 87, 105377. https://doi.org/10.1016/j.bspc.2023.105377
Sivanandan, R., & Jayakumari, J. (2021). A new CNN architecture for efficient classification of ultrasound breast tumor images with activation map clustering based prediction validation. Medical & Biological Engineering & Computing, 59(4), 957–968. https://doi.org/10.1007/s11517-021-02357-3
Uysal, F., & Köse, M. M. (2022). Classification of breast cancer ultrasound images with deep learning-based models. Engineering Proceedings, 31(1). https://doi.org/10.3390/ASEC2022-13791
Yap, M. H., Pons, G., Marti, J., Ganau, S., Sentis, M., Zwiggelaar, R., Davision, A. K., & Marti, R. (2018). Automated breast ultrasound lesions detection using convolutional neural networks. IEEE Journal of Biomedical and Health Informatics, 22(4), 1218–1226. https://doi.org/10.1109/JBHI.2017.2731873

Details

Primary Language

English

Subjects

Deep Learning

Journal Section

Research Article

Authors

Ragheed Mokhtar
0009-0009-2252-4116
Türkiye

Mahir Kaya ^*
0000-0001-9182-271X
Türkiye

Publication Date

December 31, 2025

Submission Date

October 15, 2025

Acceptance Date

November 26, 2025

Published in Issue

Year 2025 Volume: 12 Number: 4

DOI

https://doi.org/10.54287/gujsa.1804559

IZ

https://izlik.org/JA75EH29EC

Cite

RIS / Bibtex

APA

Mokhtar, R., & Kaya, M. (2025). An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis. Gazi University Journal of Science Part A: Engineering and Innovation, 12(4), 1121-1148. https://doi.org/10.54287/gujsa.1804559

AMA

1.Mokhtar R, Kaya M. An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis. GU J Sci, Part A. 2025;12(4):1121-1148. doi:10.54287/gujsa.1804559

Chicago

Mokhtar, Ragheed, and Mahir Kaya. 2025. “An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis”. Gazi University Journal of Science Part A: Engineering and Innovation 12 (4): 1121-48. https://doi.org/10.54287/gujsa.1804559.

EndNote

Mokhtar R, Kaya M (December 1, 2025) An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis. Gazi University Journal of Science Part A: Engineering and Innovation 12 4 1121–1148.

IEEE

[1]R. Mokhtar and M. Kaya, “An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis”, GU J Sci, Part A, vol. 12, no. 4, pp. 1121–1148, Dec. 2025, doi: 10.54287/gujsa.1804559.

ISNAD

Mokhtar, Ragheed - Kaya, Mahir. “An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis”. Gazi University Journal of Science Part A: Engineering and Innovation 12/4 (December 1, 2025): 1121-1148. https://doi.org/10.54287/gujsa.1804559.

JAMA

1.Mokhtar R, Kaya M. An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis. GU J Sci, Part A. 2025;12:1121–1148.

MLA

Mokhtar, Ragheed, and Mahir Kaya. “An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis”. Gazi University Journal of Science Part A: Engineering and Innovation, vol. 12, no. 4, Dec. 2025, pp. 1121-48, doi:10.54287/gujsa.1804559.

Vancouver

1.Ragheed Mokhtar, Mahir Kaya. An Optimized and Attention-Enhanced Convolutional Neural Network for Accurate Breast Cancer Diagnosis. GU J Sci, Part A. 2025 Dec. 1;12(4):1121-48. doi:10.54287/gujsa.1804559