Breast cancer is a pervasive malignancy worldwide, claiming numerous lives each year. Early and accurate detection of cancer through efficient and cost-effective methods is crucial in minimizing its impact. While mammography has been foundational in breast cancer diagnosis, there is still a need to improve its accuracy and efficiency, particularly in the detection and classification of calcifications and masses. These elements are critical indicators of potential malignancies, and their precise identification and classification are essential for effective treatment planning. The interpretation of mammographic images, especially the detailed analysis of calcifications and masses, requires specialized expertise. However, the limited availability of skilled radiologists and the growing demand for mammographic screenings highlight the necessity for a reliable and automated solution. Our project was initiated to address this challenge by integrating artificial intelligence into mammographic image analysis. By leveraging advanced deep learning techniques, we aim to enhance the accuracy and efficiency of detecting and classifying calcifications and masses in mammographic images. We employ a state-of-the-art deep learning model to achieve detailed segmentation and classification of calcifications and masses in breast mammograms. The primary architecture used in our approach is a modified version of the widely acclaimed U-Net. The integration of AI in mammographic image analysis represents a significant advancement in breast cancer screening. Early detection through precise image analysis not only helps halt the disease's progression but also significantly enhances patient survival rates. Our project's outcomes have the potential to reduce the workload on radiologists, provide timely and accurate diagnoses, and ultimately improve the overall effectiveness of breast cancer management.Results show that the proposed approach improves performance on new tasks while maintaining robust performance on previously learned tasks, outperforming existing methods.