A CAD System for the Detection of Abnormalities in the Mammograms Using the Metaheuristic Algorithm Particle Swarm Optimization (PSO)

The discovery of a malignant mass in the breast is considered one of the most devastating and depressing health issue women can face. However an early detection can be so helpful and could bring hope to control the disease and even cure it. Nowadays In spite the fact that Digital mammograms have proven to be an efficient tool for the screening of breast cancer, an accurate detection of the abnormalities remains a challenging task for radiologists. In this paper, we propose an effective method for the detection and classification of the suspicious regions. In our proposed approach, we use Entropy thresholding for pectoral muscle removal, and we extract the region of interest (ROI) using the Metaheuristic algorithm Particle Swarm Optimization (PSO). Then we extract Shape and texture features from the abnormalities using Fourier transform and Gray Level Co-Occurrence Matrix (GLCM) respectively. The classification of the detected abnormalities is carried out through the Support Vector Machine, which classifies the segmented region into normal and abnormal based on the extracted features.