A Statistical Based Feature Extraction Method for Breast Cancer Diagnosis in Digital Mammogram Using Multiresolution Representation

This paper presents a method for breast cancer
diagnosis in digital mammogram images. The wavelet is
used to transform the mammogram images into a long
vector of coefficients. A matrix is constructed by putting
wavelet coefficients of each image in row vector, where
the number of row is the number of images, and the
number of columns is the number of coefficients. A feature
extraction method is developed based on the statistical ttest
method. The method is ranking the columns
(features) according to its capability to distinguish
between the different classes. The method depends on
extracting the features that can maximize the ability to
discriminate between different classes. Thus, the
dimensionality of data features is reduced and the
classification accuracy rate is improved. Then a dynamic
threshold is applied to optimize the number of feature
which can achieve the maximum classification accuracy
rate. Support vector machine (SVM) is used to classify
between the normal and abnormal and to distinguish
between benign and malignant. The obtained
classification accuracy rates reach to 100%.