Paper Title
EXPLORING MACHINE LEARNING FOR BREAST CANCER DETECTION IN X-RAY IMAGING

Abstract
Breast X-ray imaging is a primary method for early breast cancer screening. However, applying machine learning techniques to this task presents significant challenges, particularly in capturing fine-grained details from high-resolution medical images. This study explores multiple machine learning approaches for breast cancer detection, including image-level and patch-level CNN-based classification, diffusion model-based anomaly detection, and federated learning (FL) for training models across distributed datasets. We evaluate these methods on real-world breast cancer X-ray datasets. Our findings suggest that FL offers a promising balance between performance and privacy preservation, underscoring its potential for real-world medical AI applications. Keywords - Breast Cancer Detection, Convolutional Neural networks (CNN), Diffusion Models, Federated Learning (FL), Medical Imaging.