Breast cancer is one of the primary causes of death among women in developing countries, highlighting the urgent need for effective methods of early diagnosis and treatment. This disease, which originates in breast tissue, is generally categorized into two main types: Invasive Ductal Carcinoma (IDC) and Ductal Carcinoma in Situ (DCIS). In the recent years, advancements in Artificial Intelligence (AI) and Machine Learning (ML) have significantly transformed approaches to diagnosis and prevention, particularly with the use of technologies like Magnetic Resonance Imaging (MRI) and Convolutional Neural Networks (CNNs). This paper examines the various classifications of breast cancer, emphasizing the importance of mammography in detection. It also provides an in-depth comparison of AI-based methods used in breast cancer research, analyzing their advantages, challenges, and the datasets employed. The insights offered aim to guide future developments in early detection techniques and predictive modeling for this critical health issue.