Detection of Micro Calcifications in Mammogram Images Using Texture Analysis and Logistic Regression
Kemal Tütüncü, Özcan Çataltaş · International Journal of Intelligent Systems and Applications in Engineering · 2019
Micro-calcification in the breast is a symptom of breast cancer.Therefore, detection of micro-calcification in mammogram image plays an important role in the early diagnosis of breast cancer.Because the mammogram images are 2-dimensional, different tissues in the breast are seen on top of each other.Therefore, it is a compelling task for radiologists to identify the masses found in mammogram images.There are different methods for detecting micro-calcification in mammogram images.In this study, different image processing techniques were applied on mammogram images and a region of 80x80 pixel was taken from breast tissue.Texture features of this region were extracted using co-occurrence matrix and classified by logistic regression analysis.Classification success of 88% was achieved with the proposed model.