Investigation on ROI size and location to classify mammograms

Abstract

Breast cancer is the major cause of death among women and early detection can lead to a longer survival. Computer Aided Diagnosis (CAD) system helps radiologists in the accurate detection of breast cancer. In medical images a Region of Interest (ROI) is a portion of image which carries the important information related to the diagnosis and it forms the basis for applying shape and texture techniques for cancer detection. Several ROI sizes and locations have been proposed for computer aided diagnosis systems. In the present work various ROI sizes have been used to determine the appropriate ROI size to classify fatty and dense mammograms. Two types of mammograms i.e. fatty and dense are used from the MIAS database. Various texture features have been determined from each ROI size for the analysis of texture characteristics. Fisher discriminant ratio is used to select the most relevant features for classification. Finally linear SVM is used for the purpose of classification. Highest classification accuracy of 96.1% was achieved for ROI size 200×200 pixels.

An enhancement of mammogram images for breast cancer classification using artificial neural networks

“…Amit Kamra et al [14] proposed various types of ROIs selected for diagnosis of breast cancer for diagnosis using shape and texture-based techniques. The number of ROIs and their location proposed for CAD systems.…”