Effect of Different Parameter Values for Pre-processing of Using Mammography Images

Authors : Hanife AVCI, Jale KARAKAYA

Pages : 345-354

Doi:10.28979/jarnas.1199343

View : 44 | Download : 35

Publication Date : 2023-06-30

Article Type : Research Paper

Abstract :Breast cancer is one of the most common types of cancer in women. To make a fast diagnosis, mammography images should have high contrast. Computer-assisted diagnosis insert ignore into journalissuearticles values(CAD); models are computer systems that help diagnose lesioned areas on medical images. The aim of this study is to examine the contribu-tion of the changes in parameter values of various pre-processing methods used to increase the visibility of mammography images and reduce the noise in the images, to the classification performance. In this study, the mini-MIAS database were used. Gaussian filter, Contrast Limited Adaptive Histogram Equalization and Fast local Laplacian filtering methods were applied as pre-processing method. In this study, two different parameter values were applied for two different image processing methods insert ignore into journalissuearticles values(Ⅰ. Parameter values are Gauss filter ????=3, Laplacian filter ????=0.6 and ????=0.6; Ⅱ. Parameter values are Gauss filter ????=1, Laplacian filter ????=2 and ????=2);. In the normal-abnormal tissue classification, higher accuracy and area under the curve were obtained in the 2nd parameter values in all classification methods. As a result, it has been acquired that different parameter values of the pre-processing methods used to improve mammography images can change the success of the classification methods.
Keywords : Computer Assisted, image enhancement, image processing, machine learning, classification