REDUCE OVERLAPPING IN MAMMOGRAPHY BY DEEP LEARNING CLASSIFICATION

Breast cancer is the leading cause of cancer death among women. Screening mammography is the only method currently available for the reliable detection of early and potentially curable breast cancer. Research indicates that the mortality rate could decrease by 30% if women age 50 and older have regular mammograms. In this dissertation, we propose a new full-field mammogram analysis method focusing on characterizing and identifying normal mammograms. A mammogram is analyzed region by region and is classified as normal or abnormal. The methods for extracting features are presented in this thesis which are used to distinguish normal and abnormal regions of a mammogram. In this book, convolution neural network classifier is used to boost the classification performance. This classifier performs better than previous classifiers. In that it shows more accuracy than the others classifiers, the misclassification rate of normal mammograms as abnormal.This approach performs good on overlapping problem.