A New Breast Cancer Image Classifier Using Gaussian Mixture Model Based on Histogram and Enhanced Roughness Index

<p>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.</p>

Name thesis:degree_name

Master of Science (MS)

Level thesis:degree_level

Thesis - University Access Only

Discipline thesis:degree_discipline

Electrical Engineering and Computer Science

Year dc:date.available

2013

Author dc:creator

• Li, Zhe

Contributors dc:contributor

• Sung Y. Shin

• Analytical, Diagnostic and Therapeutic Techniques and Equipment
• Electrical and Computer Engineering

Statement dc:rights

• <p>In Copyright - Non-Commercial Use Permitted<br /><a href="http://rightsstatements.org/vocab/InC-NC/1.0/">http://rightsstatements.org/vocab/InC-NC/1.0/</a></p>

Language dc:language

en

Repository record dc:identifier

https://openprairie.sdstate.edu/etd/1455

OAI identifier oai:identifier

oai:openprairie.sdstate.edu:etd-2461