Mass detection on mammograms with image processing techniques and benign-malignant distinction

Abstract

In this study, it is aimed the determination of the masses and the masses in mammograms whether benign or malignant is intended to determine. Firstly; was carried out preprocessing on MIAS(Mammogram Image Analysis Society) database of international images. Mass separation was implemented with an appropriate threshold value. Then, Morphological filtering was performed for beter seggmentation. At classification phase, the area covered by the tumor and surrounding area using the criteria irregularity was any distinction between good and evil. At made research were observed more irregular environment of malignant tumors and their areas values certain limits. By using this values, segmented areas are classified as benign and malignant. © 2014 IEEE.