International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI-Based Breast Cancer Identification Using Hybrid CNN-GAN Framework with CLAHE Enhancement and Gradio Interface |
|---|---|
| ABSTRACT | Breast cancer remains the leading cause of cancer-related mortality in women globally. Timely and accurate identification of malignant tissue from mammographic images is critical to improving survival outcomes. However, deep learning-based diagnosis systems face two persistent challenges: the extreme scarcity of annotated malignant samples and the inherent class imbalance that biases standard classifiers toward the majority benign class. This paper presents a comprehensive end-to-end framework addressing both challenges by coupling a Deep Convolutional Generative Adversarial Network (DCGAN) with a fine-tuned ResNet-18 classifier enhanced by Contrast-Limited Adaptive Histogram Equalization (CLAHE) preprocessing. In Stage 1, the DCGAN is trained exclusively on real malignant mammographic patches to synthesize photorealistic augmentation images, expanding the malignant training pool and narrowing the class-imbalance ratio from approximately 46:1 to 3:1. In Stage 2, the augmented balanced dataset trains a ResNet-18 binary classifier whose final fully connected layer is replaced for benign-vs-malignant prediction. Class-weighted cross-entropy loss and a weighted random oversampling strategy further suppress residual imbalance. Experimental results demonstrate a validation accuracy of 95%, precision of 96%, recall of 95%, and an F1-score of 94%. The pipeline is deployed through a Gradio-based web interface for real-time clinical inference with a configurable probability threshold. The proposed framework demonstrates the practical potential of GAN-augmented transfer learning for AI-assisted breast cancer screening in resource-constrained clinical environments. |
| AUTHOR | MOHAMMED AFREED ULLA, PRASANNA KUMAR M Student (M. Tech under VTU), Department of Computer Science and Engineering, Shridevi Institute of Engineering and Technology, Tumkur, Karnataka, India Associate Professor and HOD, Department of Information Science and Engineering, Shridevi Institute of Engineering and Technology, Tumakuru, Karnataka, India |
| VOLUME | 185 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1406019 |
| pdf/19_AI-Based Breast Cancer Identification Using Hybrid CNN-GAN Framework with CLAHE Enhancement and Gradio Interface.pdf | |
| KEYWORDS | |
| References | [1] M. Leitch, G. D. Dodd, M. Costanza, M. Linver, P. Pressman, L. McGinnis, and R. A. Smith, American Cancer Society guidelines for the early detection of breast cancer, CA: A Cancer Journal for Clinicians, vol. 47, no. 3, pp. 150-153, 1997. [2] M. Salhab, W. Al Sarakbi, and K. Mokbel, The evolving role of dynamic thermal analysis in the early detection of breast cancer, International Seminars in Surgical Oncology, vol. 2, pp. 1-5, 2005. [3] I. J. Goodfellow et al., Generative adversarial nets, Advances in Neural Information Processing Systems (NeurIPS), vol. 27, pp. 2672-2680, 2014. [4] K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition, Proc. IEEE CVPR, pp. 770-778, 2016. [5] S. W. Fu, L. Chen, and Y. Man, miRNA biomarkers in breast cancer detection and management, Journal of Cancer, vol. 2, pp. 116-122, 2011. [6] K. Ganesan, U. R. Acharya, C. K. Chua, L. C. Min, K. T. Abraham, and K.-H. Ng, Computer-aided breast cancer detection using mammograms: A review, IEEE Reviews in Biomedical Engineering, vol. 6, pp. 77-98, 2013. [7] A. Radford, L. Metz, and S. Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks, Proc. ICLR, 2016. [8] K. M. Kelly, J. Dean, W. S. Comulada, and S.-J. Lee, Breast cancer detection using automated whole breast ultrasound and mammography in radiographically dense breasts, European Radiology, vol. 20, pp. 734-742, 2009. [9] R. Roslidar et al., A review on recent progress in thermal imaging and deep learning for breast cancer detection, IEEE Access, vol. 8, pp. 116176-116194, 2020. [10] N. Irishina, O. Dorn, and M. Moscoso, A level set evolution strategy in microwave imaging for early breast cancer detection, Computers and Mathematics with Applications, vol. 56, pp. 607-618, 2008. [11] U. Naseem et al., An automatic detection of breast cancer diagnosis and prognosis based on machine learning using ensemble of classifiers, IEEE Access, vol. 10, pp. 78242-78252, 2022. [12] V. Patel, V. Chaurasia, R. Mahadeva, and S. P. Patole, GARL-Net: Graph based adaptive regularized learning deep network for breast cancer classification, IEEE Access, vol. 11, pp. 34021-34039, 2023. [13] A. Fatima et al., Analyzing breast cancer detection using machine learning and deep learning techniques, Journal of Computing and Biomedical Informatics, vol. 7, pp. 1-11, 2024. [14] P. Sharma et al., Explainable AI for breast cancer diagnosis using Grad-CAM visualisation, IEEE Trans. Medical Imaging, vol. 44, pp. 410-422, 2025. [15] A. Hassan et al., Federated learning for privacy-preserving breast cancer detection, Journal of Biomedical Informatics, vol. 152, p. 104612, 2025. [16] E. Rodriguez et al., Multimodal breast cancer diagnosis integrating mammography, ultrasound, and clinical data, Medical Image Analysis, vol. 98, p. 103021, 2025. [17] R. Kumar et al., Lightweight CNN for edge-device breast cancer screening, IEEE Internet of Things Journal, vol. 12, pp. 8914-8926, 2025. [18] N. Ahmad et al., Ensemble CNN-GAN framework for breast cancer classification, Pattern Recognition, vol. 160, p. 110123, 2026. [19] K. Reddy et al., Attention-based deep learning for mammogram classification, Artificial Intelligence in Medicine, vol. 149, p. 102742, 2026. [20] H. Patel et al., IoMT-integrated cloud AI platform for breast cancer screening, IEEE Journal of Biomedical and Health Informatics, vol. 30, pp. 1201-1214, 2026. [21] K. Waghulade and A. K. Yadav, Early breast cancer detection by using image processing, ICITER, pp. 1-5, 2016. [22] S. U. Khan et al., An e-health care services framework for detection and classification of breast cancer in breast cytology images as an IoMT application, Elsevier, 2019. [23] R. L. R. Coripuna et al., Machine learning for analysis of conductivity from mono frequency electrical impedance mammography, IEEE Access, vol. 9, 2021. |
