Breast Cancer Diagnosis in Digital Mammography Images Using Automatic Detection for the Region of Interest

Background: One of the early screening methods of breast cancer that is still used today is mammogram due to its low cost. Unfortunately, this low cost accompanied with low performance rate also. Methods: The low performance rate in mammograms is associated with low capability in determining the best region from which the features are extracted. Therefore, we offer an automatic method to detect the Region of Interest in the mammograms based on maximizing the area under receiver operating characteristic curve utilizing Genetic Algorithms. The proposed method had been applied to the MIAS mammographic database, which is widely used in literature. Its performance had been evaluated using four different classifiers; Support Vector Machine, Naïve Bayes, K-Nearest Neighbor and Logistic Regression classifiers. Results & Conclusion: The results showed good classification performances for all the classifiers used due to the rich information contained in the features extracted from the automatically selected Region of Interest.