Seminar: Improving Specificity in Mammography Using Cross-correlation between Wavelet and Fourier Tr
Co-Supervisors: Dr. Adrian Fiech and Dr. Edward Kendall
Improving Specificity in Mammography Using Cross-correlation between Wavelet and Fourier Transform
Department of Computer Science
Thursday, September 19, 2013, 1:00 p.m., Room EN 2022
Breast cancer is in the most common malignant tumor in women. It accounted for 30% of new malignant tumor cases. Although the incidence of breast cancer remains high around the world, the mortality rate has been continuously reduced. This is mainly due to recent developments in molecular biology technology and improved level of comprehensive diagnosis and standard treatment. Early detection by mammography is an integral part of that.
The most common breast abnormalities that may indicate breast cancer are masses and calcifications. Previous detection approaches usually obtain relatively high sensitivity but unsatisfactory specificity. We will investigate an approach that applies the discrete wavelet transform and Fourier transform to parse the images and extracts statistical features that characterize an image’s content, such as the mean intensity and the skewness of the intensity. In the study, we tested on three combination of wavelet and Fourier features, including Db2, Db4, and Bior 6.8, and selected the top appropriate amounts offeatures which related most to the breast cancer according to the information gain. At last, there classifiers, including Back-propagation (BP) Network, Linear Discriminant Analysis (LDA), and Naïve Bayes (NB) Classifier, were tested in the original and new database, and significant figures such as sensitivity and specificity were calculated and compared.