Critical review on breast cancer detection and classification using mammogram
K. Sreekala, Jayakrushna Sahoo · International Journal of Computer Mathematics Computer Systems Theory · 2025
Breast cancer is a widespread type of cancer that impacts women worldwide, and timely identification of the disease is crucial to improve the effectiveness of treatment and raise survival rates. Mammography is a commonly employed screening method to identify breast cancer. While, machine learning techniques have been increasingly used to analyse mammography images to improve accuracy and effectiveness. This review article assesses the most recent research studies, published within the last three years, that centre on breast cancer identification through the classification of mammograms. The paper highlights the importance of choosing appropriate datasets for mammogram classification, and the impact of pre-processing and data enhancement methods on classification performance. The review examines diverse approaches for image classification, comprising both traditional machine learning techniques and deep learning-based methods, and evaluates how they perform on different datasets. The paper emphasizes the need for hyperparameter tuning and optimization for achieving optimal classification performance.