Computer-Aided Diagnosis for the Early Breast Cancer Detection

Abstract

Computer-aided diagnosis (CAD) system is a prominent tool for the detection of different forms of diseases, especially cancers, based on medical imaging. Digital image processing is a critical in the processing and analysis of medical images for the disease diagnosis and detection. This study introduces a CAD system for detecting breast cancer. Once the breast region is segmented from the mammograms image, certain texture and statistical features are extracted. GLRLM feature extraction technique is implemented to extracted texture features. On the other hand, statistical features such as skewness, mean, entropy, and standard deviation are extracted. Consequently, on the basis of the extracted features, SVM and kNN classifier techniques are utilized to classify the segmented region as normal or abnormal. The performance of the proposed approach has been investigated via extensive experiments conducted on the well-known MIAS dataset of mammography images. The experimental findings show that the suggested approach outperforms other existing approaches, with an accuracy rate of 99.7%.