Breast Cancer Detection using CNN & GAN

Breast cancer is a leading cause of cancer-related deaths among women worldwide, making early and accurate detection essential for improving survival outcaomes.Histopathological examination is the diagnostic gold standard but is time-consuming, labour-intensive, and prone to variability among pathologists.This project proposes a Python-based framework for automated breast cancer detection using a hybrid Convolutional Neural Network and Generative Adversarial Network (CNN-GAN) approach.The system incorporates preprocessing techniques such as noise reduction, contrast enhancement, and normalization to improve image quality.A GAN is used to generate synthetic histopathology images to address class imbalance and enhance dataset diversity.The augmented dataset is then used to train a CNN capable of extracting hierarchical features for benign-malignant tissue classification.Model performance is evaluated using accuracy, precision, recall and F1-score.Results show that GAN-based augmentation significantly boosts classification performance compared to traditional CNN models.The proposed methodology demonstrates the potential of deep learning to assist pathologists by providing faster, more reliable diagnostic support.This approach enhances consistency in breast cancer detection and contributes to advancements in computer-aided medical imaging.