Prediction of Breast Cancer Using Mammogram Images through Deep Learning Techniques

Abstract

Breast cancer remains one of the leading causes of mortality among women worldwide, and early diagnosis significantly improves survival rates. Mammography has long been considered the gold standard for breast cancer screening due to its ability to detect abnormalities before clinical symptoms appear. However, manual interpretation of mammograms is prone to human error and variability among radiologists. With advances in artificial intelligence (AI), particularly deep learning, automated systems have emerged as powerful tools for improving the accuracy and efficiency of breast cancer detection. This paper presents a comprehensive study on the use of convolutional neural networks (CNNs) for predicting breast cancer from mammogram images. The study investigates the role of pre-processing techniques, image augmentation, feature extraction, and model optimisation in enhancing classification performance. Using a publicly available dataset of mammographic images, the proposed CNN model achieves high accuracy, sensitivity, and specificity compared to traditional machine learning methods. The results demonstrate that deep learning models, when properly trained and optimised, can support radiologists in making more accurate and consistent diagnostic decisions. The paper concludes with a discussion of current challenges, including data imbalance, model interpretability, and ethical considerations, while proposing directions for future research on explainable and multimodal AI-driven breast cancer diagnosis