Accuracy Enhancement of a Hybrid CNN–VGG16 Architecture through Dropout Regularization Strategy for Breast Cancer Histopathology Classification
Abstract
Breast cancer remains the leading cause of cancer-related mortality among women globally, necessitating accurate diagnosis through histopathological image analysis. However, manual examination of these images is time-consuming and susceptible to inter-observer variability, highlighting the critical need for reliable automated computer-aided diagnostic (CAD) systems. This study was conducted to systematically evaluate and optimize convolutional neural network (CNN) architectures for automated classification of breast cancer histopathology images, with a focus on mitigating overfitting and enhancing diagnostic accuracy through hybrid deep learning methodologies. The principal innovation is the development of a CNN-VGG16 hybrid architecture that strategically integrates pre-trained feature extraction with a customized CNN framework, hypothesized to substantially improve classification accuracy and model generalization. Three model configurations were developed and comparatively analyzed: (1) baseline CNN, (2) CNN with dropout regularization, and (3) hybrid CNN-VGG16 model. Input images underwent preprocessing, including resizing to 150×150 pixels, normalization, and data augmentation. All models were trained with identical hyperparameters: an Adam optimizer with a learning rate of 0.001, a batch size of 32, and 10 epochs. Dropout regularization with a fixed rate of 0.5 was applied to fully-connected layers to mitigate overfitting. Model evaluation was conducted utilizing standard performance metrics. The proposed CNN-VGG16 hybrid model achieved superior performance: accuracy of 85.19%, precision of 87.16%, recall of 92.75%, and F1-score of 88.37%. These metrics represent significant improvements of 4.2% relative to baseline CNN and 3.4% compared to the dropout-regularized variant, indicating substantially enhanced diagnostic capability and reduced false-negative rates. Strategic integration of pre-trained feature extraction with customizable CNN architectures significantly improves generalization and classification performance in histopathological image analysis. Future investigations should incorporate larger heterogeneous datasets, attention mechanisms, and explainable artificial intelligence (XAI) to enhance clinical interpretability and strengthen practitioner confidence in digital pathology systems
Downloads
References
F. Bray, J. Ferlay, I. Soerjomataram, R. L. Siegel, and A. Jemal, "Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries," CA: A Cancer J. Clin., vol. 72, no. 6, pp. 601–649, Nov. 2022. https://doi.org/10.3322/caac.21834
American Cancer Society, Breast Cancer Statistics 2024, 2024. [Online]. Available: https://www.cancer.org
S. Alimuddin, et al., "Application of VGG16 transfer learning for breast cancer detection," Information, vol. 16, no. 3, pp. 227, 2023. https://doi.org/10.3390/info16030227
M. Ramasamy, et al., "Performance analysis of breast cancer histopathology image classification using transfer learning," Int. J. Electrical & Computer Eng., vol. 72, pp. 24, 2024. http://doi.org/10.11591/ijece.v14i5.pp6006-6015
A. Bagchi, P. Pramanik, and R. Sarkar, “A multi-stage approach to breast cancer classification using histopathology images,” Diagnostics, vol. 13, no. 1, p. 126, Dec. 2022, doi: 10.3390/diagnostics13010126.
M. Yusuf, A. F. Donfack Kana, M. A. Bagiwa, and M. Abdullahi, "Multi-classification of breast cancer histopathological image using enhanced shallow convolutional neural network," J. Eng. Appl. Sci., vol. 72, pp. 24, 2025. doi: 10.1186/s44147-025-00589-w.
X. Zhao, T. Wang, Z. Liu, and H. Chen, "Breast Cancer Histopathological Image Classification Based on High-Order Modeling and Multi-Branch Receptive Fields," Applied Sciences, vol. 15, no. 11, pp. 6085, 2025. doi: 10.3390/app15116085.
A. Sani, M. Royat, and M. Baghshah, "Classification of breast cancer histopathology images using a modified supervised contrastive learning method," Journal of Imaging, vol. 45, no. 3, pp. 156-168, 2025. doi: 10.1007/s11517-024-03245-6.
T. A. Smrity, M. Muntaqim, and et al., "Recent advancements in machine learning and deep learning for early detection of breast cancer: A comprehensive review," Intelligence-Based Medicine, 2026, doi: 10.1016/j.ibreh.2026.100050.
V. Sureshkumar et al., "Breast Cancer Detection and Analytics Using Hybrid CNN and RNN Model," Journal of Personalized Medicine, vol. 14, no. 8, Art. no. 792, 2024. DOI: https://doi.org/10.3390/jpm14080792
R. B. Eshun et al., "A deep convolutional neural network for the classification of imbalanced breast cancer dataset," Intelligence-Based Medicine, 2024, Art. no. 100270, doi: 10.1016/j.ibmed.2024.100270.
S. P. Jakkaladiki and F. Maly, “Integrating hybrid transfer learning with attention‑enhanced deep learning models to improve breast cancer diagnosis,” PeerJ Computer Science, vol. 10, Art. no. e1850, 2024. doi: 10.7717/peerj-cs.1850.
T. E. Komolafe, Y. Tian, O. J. Awoniya, S. Chen, and X. Yang, “Comparative analysis of cone‑beam breast computed tomography and digital breast tomosynthesis for breast cancer diagnosis: A comprehensive study on reconstruction algorithms,” International Journal of Imaging Systems and Technology, vol. 34, no. 3, Art. no. e23071, 2024. DOI: https://doi.org/10.1002/ima.23071
N. Brancati and M. Frucci, "Improving Breast Tumor Multi-Classification from High-Resolution Histological Images with the Integration of Feature Space Data Augmentation," Information, vol. 15, no. 2, Art. no. 98, Feb. 2024, doi: 10.3390/info15020098.
F. Schwarzhans et al., "Image normalization techniques and their effect on the robustness and predictive power of breast MRI radiomics," European Journal of Radiology, vol. 187, Art. no. 112086, Jun. 2025, doi: 10.1016/j.ejrad.2025.112086.
Spanhol, F. A., Oliveira, L. S., Petitjean, C., & Heutte, L. (2016). A Dataset for Breast Cancer Histopathological Image Classification. IEEE Transactions on Biomedical Engineering. doi: 10.1109/TBME.2015.2496264.
LeCun, Y., Bottou, L., Orr, G. B., & Müller, K. R. (2012). Efficient BackProp. In Neural Networks: Tricks of the Trade. Springer. doi: 10.1007/978-3-642-35289-8_3.
Komura, D., & Ishikawa, S. (2018). Machine Learning Methods for Histopathological Image Analysis. Computational and Structural Biotechnology Journal. doi: 10.1016/j.csbj.2018.01.001.
M. Fatima, R. Zia, and I. A. Usmani, “A hybrid framework integrating deep learning and XAI for breast cancer detection with stratified cross-validation,” Systems and Soft Computing, vol. 7, Art. no. 200412, Dec. 2025, doi: 10.1016/j.sasc.2025.200412.
S. Bayard et al., “Screening mammography mitigates breast cancer disparities through early detection of triple negative breast cancer,” Clinical Imaging, vol. 80, pp. 430–437, Dec. 2021, doi: 10.1016/j.clinimag.2021.08.013.
M. Krichen, “Convolutional neural networks: A survey,” Computers, vol. 12, no. 8, p. 151, Aug. 2023, doi: 10.3390/computers12080151.
D. Dave, T. P. Shah, and A. Chavada, “A modified hybrid CNN-based feature selection and ANN classification framework for patient-level breast cancer histopathology analysis,” Franklin Open, vol. 15, Art. no. 100578, 2026, doi: 10.1016/j.fraope.2026.100578.
K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recognition,” arXiv preprint arXiv:1409.1556, 2015, doi: 10.48550/arXiv.1409.1556.
A. S. Wadood et al., “M3-Net++: A multi-scale, multi-level, multi-stream network for nuclei segmentation in breast cancer histopathology using hierarchical context extraction and hybrid loss optimization,” Computers in Biology and Medicine, vol. 196, Part B, Art. no. 110804, 2025, doi: 10.1016/j.compbiomed.2025.110804.
Z. Iklima et al., “Reduction of Feature Extraction for COVID-19 CXR using Depthwise Separable Convolution Network,” Journal of Electronics, Electromedical Engineering, and Medical Informatics (JEEEMI), vol. 4, no. 4, pp. 204–209, 2022, doi: 10.35882/jeeemi.v4i4.255.
W. Li et al., “Radiomics analysis combining gray-scale ultrasound and mammography for differentiating breast adenosis from invasive ductal carcinoma,” Frontiers in Oncology, vol. 14, Art. no. 1390342, 2024, doi: 10.3389/fonc.2024.1390342.
A. H. M. Z. Karim, K. B. O. Mahmud, and C. Shahnaz, “A hybrid feature extraction based ensemble model for breast cancer detection and classification using different medical images,” Intelligence-Based Medicine, vol. 12, Art. no. 100290, 2025, doi: 10.1016/j.ibmed.2025.100290.
I. Pacal and O. Attallah, “InceptionNeXt-Transformer: A novel multi-scale deep feature learning architecture for multimodal breast cancer diagnosis,” Biomedical Signal Processing and Control, vol. 110, Part B, Art. no. 108116, 2025, doi: 10.1016/j.bspc.2025.108116.
A. Ben Atitallah, J. Kamoun, M. D. Alanazi, T. M. Alanazi, M. Albekairi, and K. Kaaniche, “An advanced medical diagnosis of breast cancer histopathology using convolutional neural networks,” Computers, Materials and Continua, vol. 83, no. 3, pp. 5761–5779, 2025, doi: 10.32604/cmc.2025.063634.
F. Badri et al., “Systematic literature review: Research ethics in artificial intelligence development for breast cancer histopathology detection–data privacy, informed consent, and accountability,” Informatics, Electrical and Electronics Engineering (Infotron), vol. 5, no. 2, pp. 107–120, 2025, doi: 10.33474/infotron.v5i2.24677.
G. Chyrmang, B. Barua, K. Bora, G. N. Ahmed, A. K. Das, L. Kakoti, B. Lemos, and S. Mallik, “Self-HER2Net: A generative self-supervised framework for HER2 classification in IHC histopathology of breast cancer,” Pathology - Research and Practice, vol. 270, Art. no. 155961, 2025, doi: 10.1016/j.prp.2025.155961.
H. A. Helaly, M. Badawy, E. M. El-Gendy, and A. Y. Haikal, “Early breast cancer detection, affected cell classification, and segmentation framework,” Engineering Applications of Artificial Intelligence, vol. 162, Part D, Art. no. 112598, 2025, doi: 10.1016/j.engappai.2025.112598.
M. Shirdel, M. Di Mauro, dan A. Liotta, “Worthiness Benchmark: A novel concept for analyzing binary classification evaluation metrics,” Information Sciences, vol. 678, art. 120882, 2024.
S. Szabó, I. J. Holb, V. É. Abriha-Molnár, G. Szatmári, S. K. Singh, and D. Abriha, “Classification assessment tool: A program to measure the uncertainty of classification models in terms of class-level metrics,” Applied Soft Computing, vol. 155, Art. no. 111468, 2024, doi: 10.1016/j.asoc.2024.111468.
J. H. Cabot and E. G. Ross, “Evaluating prediction model performance,” Surgery, vol. 174, no. 3, pp. 723–726, 2023, doi: 10.1016/j.surg.2023.05.023.
V. N. Thatha et al., “Histopathological image based breast cancer diagnosis using deep learning and bio inspired optimization,” Scientific Reports, vol. 15, Art. no. 19034, 2025, doi: 10.1038/s41598-025-04136-8.
Z. Wang et al., “Illuminating breast cancer malignancies: Lightweight histopathology computer vision classifier for precise breast cancer screening,” EngMedicine, vol. 2, no. 2, Art. no. 100053, 2025, doi: 10.1016/j.engmed.2024.100053.
N. Erlianita, M. Itqan Mazdadi, T. H. Saragih, M. Reza Faisal, and Muliadi, “Implementation of SMOTE and Whale Optimization Algorithm on Breast Cancer Classification Using Backpropagation,” J. Electron. Electromedical Eng. Med. Informat., vol. 5, no. 4, pp. 303-313, Oct. 2023, doi:10.35882/jeeemi.v5i4.334.
I. Nurcahyati, T. H. Saragih, A. Farmadi, D. Kartini, and Muliadi, “Classification of lung disease in X-ray images using gray level co-occurrence matrix method and convolutional neural network,” J. Electron. Electromedical Eng. Med. Informat., vol. 6, no. 4, pp. 332–342, Oct. 2024, doi: 10.35882/jeeemi.v6i4.457.
A. Desiani, “Data augmentation and U-Net CNN for accurate nuclei cells segmentation,” J. Electron. Electromedical Eng. Med. Informat., vol. 6, no. 3, pp. 264–275, Jul. 2024, doi: 10.35882/jeeemi.v6i3.442.
A. Chauhan and I. Kumar, “Deep feature extraction and optimized VGG16-SVM architecture for breast cancer characterization,” Discover Computing, vol. 28, art. no. 208, 2025. DOI: 10.1007/s10791-025-09736-6.
M. A. Wakili, N. Garg, A. Sinha, and M. Gupta, “Classification of Breast Cancer Histopathological Images Using DenseNet and Transfer Learning,” Procedia Computer Science, vol. 237, pp. 1079–1086, 2024. DOI: 10.1016/j.procs.2024.08.189.
A. Heikal, A. El-Ghamry, S. Elmougy, and M. Z. Rashad, “Fine-tuning deep learning models for breast tumor classification,” Scientific Reports, vol. 14, no. 10753, pp. 1–26, 2024.
I. G. S. M. Diyasa, S. Humairah, E. Y. Puspaningrum, F. D. Durry, W. D. Lestari, and W. Caesarendra, “Improving classification accuracy of breast ultrasound images using Wasserstein GAN for synthetic data augmentation,” Journal of Robotics and Control (JRC), vol. 6, no. 4, pp. 1962–1971, 2025, doi: 10.18196/jrc.v6i4.25075.
F. Badri, S. Patmanthara, and I. A. E. Zaeni, “Integration of knowledge-based CNN model for breast cancer histopathology image classification,” ILKOMNIKA, vol. 7, no. 3, pp. 340–353, 2025, doi: 10.28926/ilkomnika.v7i3.801.
A. S. Hyperastuty, A. N. Handayani, and H. W. Herwanto, “Grading breast cancer with deep learning method in the pathology image,” in Proc. 2025 2nd Beyond Technology Summit on Informatics International Conference (BTS-I2C), 2025, pp. 272–275, doi: 10.1109/BTS-I2C67944.2025.11399422.
Copyright (c) 2026 Fawaidul Badri Fawaid, Ilham Ari Elbaith Zaeni , Heru Wahyu Herwanto Heru, Muhammad Khusairi Osman
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
