EXTRACTING FEATURES FROM MAMMOGRAPHIC IMAGES FOR BREAST CANCER DETECTION

Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, making early and accurate detection crucial for successful treatment and improved survival rates. Mammography is currently the most effective and widely used imaging modality for early screening. However, manual interpretation of mammograms is time-consuming and subject to inter-observer variability. This paper focuses on feature extraction techniques from mammographic images to enhance computer-aided diagnosis (CAD) systems for breast cancer detection. We explore both traditional handcrafted feature extraction methods—such as texture analysis (GLCM), shape features, and intensity distribution—and modern deep learning-based approaches, including Convolutional Neural Networks (CNNs). The extracted features are evaluated based on their ability to distinguish between benign and malignant lesions. Experimental results demonstrate that combining deep features with spatial-texture descriptors significantly improves classification accuracy, sensitivity, and specificity. The proposed approach offers a reliable and efficient diagnostic tool to assist radiologists in clinical decision-making.