Off-campus South Dakota State University users: To download campus access theses, please use the following link to log into our proxy server with your South Dakota State University ID and password.
Non-South Dakota State University users: Please talk to your librarian about requesting this thesis through interlibrary loan.
Thesis - University Access Only
Master of Science (MS)
Electrical Engineering and Computer Science
Sung Y. Shin
Early stage breast cancer detection is a critical challenge to improve survive rate, and thus it is extremely important to perform breast tumor image classification. In this thesis, a new method based on Gaussian Mixture Model (GMM) to perform the breast tumor classification into two different classes (benign class and malignant class) was proposed. Also a new Enhance Roughness Index (ERI) was developed. In the meanwhile, the two different factors (intensity and irregularity index) as input into GMM are investigated, to compare and show which factor for GMM is better than the other one. This algorithm based on the intensity and irregularity index was applied on the mammograms. Through extensive experiments, the results show that this GMM based method is effective and accurate to perform breast tumor image into different classes. Also with ERI as input, the more accurate performance can be obtained.
Library of Congress Subject Headings
Breast -- Imaging.
Breast -- Cancer -- Diagnosis.
Includes bibliographical references.
Number of Pages
South Dakota State University
In Copyright - Non-Commercial Use Permitted
Li, Zhe, "A New Breast Cancer Image Classifier Using Gaussian Mixture Model Based on Histogram and Enhanced Roughness Index" (2013). Electronic Theses and Dissertations. 1455.